# Changelog
Source: https://docs.crewai.com/changelog
View the latest updates and changes to CrewAI
**Features**
* Converted tabs to spaces in `crew.py` template
* Enhanced LLM Streaming Response Handling and Event System
* Included `model_name`
* Enhanced Event Listener with rich visualization and improved logging
* Added fingerprints
**Bug Fixes**
* Fixed Mistral issues
* Fixed a bug in documentation
* Fixed type check error in fingerprint property
**Documentation Updates**
* Improved tool documentation
* Updated installation guide for the `uv` tool package
* Added instructions for upgrading crewAI with the `uv` tool
* Added documentation for `ApifyActorsTool`
**Core Improvements & Fixes**
* Fixed issues with missing template variables and user memory configuration
* Improved async flow support and addressed agent response formatting
* Enhanced memory reset functionality and fixed CLI memory commands
* Fixed type issues, tool calling properties, and telemetry decoupling
**New Features & Enhancements**
* Added Flow state export and improved state utilities
* Enhanced agent knowledge setup with optional crew embedder
* Introduced event emitter for better observability and LLM call tracking
* Added support for Python 3.10 and ChatOllama from langchain\_ollama
* Integrated context window size support for the o3-mini model
* Added support for multiple router calls
**Documentation & Guides**
* Improved documentation layout and hierarchical structure
* Added QdrantVectorSearchTool guide and clarified event listener usage
* Fixed typos in prompts and updated Amazon Bedrock model listings
**Core Improvements & Fixes**
* Enhanced LLM Support: Improved structured LLM output, parameter handling, and formatting for Anthropic models
* Crew & Agent Stability: Fixed issues with cloning agents/crews using knowledge sources, multiple task outputs in conditional tasks, and ignored Crew task callbacks
* Memory & Storage Fixes: Fixed short-term memory handling with Bedrock, ensured correct embedder initialization, and added a reset memories function in the crew class
* Training & Execution Reliability: Fixed broken training and interpolation issues with dict and list input types
**New Features & Enhancements**
* Advanced Knowledge Management: Improved naming conventions and enhanced embedding configuration with custom embedder support
* Expanded Logging & Observability: Added JSON format support for logging and integrated MLflow tracing documentation
* Data Handling Improvements: Updated excel\_knowledge\_source.py to process multi-tab files
* General Performance & Codebase Clean-Up: Streamlined enterprise code alignment and resolved linting issues
* Adding new tool: `QdrantVectorSearchTool`
**Documentation & Guides**
* Updated AI & Memory Docs: Improved Bedrock, Google AI, and long-term memory documentation
* Task & Workflow Clarity: Added "Human Input" row to Task Attributes, Langfuse guide, and FileWriterTool documentation
* Fixed Various Typos & Formatting Issues
**Features**
* Add Composio docs
* Add SageMaker as a LLM provider
**Fixes**
* Overall LLM connection issues
* Using safe accessors on training
* Add version check to crew\_chat.py
**Documentation**
* New docs for crewai chat
* Improve formatting and clarity in CLI and Composio Tool docs
**Features**
* Conversation crew v1
* Add unique ID to flow states
* Add @persist decorator with FlowPersistence interface
**Integrations**
* Add SambaNova integration
* Add NVIDIA NIM provider in cli
* Introducing VoyageAI
**Fixes**
* Fix API Key Behavior and Entity Handling in Mem0 Integration
* Fixed core invoke loop logic and relevant tests
* Make tool inputs actual objects and not strings
* Add important missing parts to creating tools
* Drop litellm version to prevent windows issue
* Before kickoff if inputs are none
* Fixed typos, nested pydantic model issue, and docling issues
**New Features**
* Adding Multimodal Abilities to Crew
* Programatic Guardrails
* HITL multiple rounds
* Gemini 2.0 Support
* CrewAI Flows Improvements
* Add Workflow Permissions
* Add support for langfuse with litellm
* Portkey Integration with CrewAI
* Add interpolate\_only method and improve error handling
* Docling Support
* Weviate Support
**Fixes**
* output\_file not respecting system path
* disk I/O error when resetting short-term memory
* CrewJSONEncoder now accepts enums
* Python max version
* Interpolation for output\_file in Task
* Handle coworker role name case/whitespace properly
* Add tiktoken as explicit dependency and document Rust requirement
* Include agent knowledge in planning process
* Change storage initialization to None for KnowledgeStorage
* Fix optional storage checks
* include event emitter in flows
* Docstring, Error Handling, and Type Hints Improvements
* Suppressed userWarnings from litellm pydantic issues
**Changes**
* Remove all references to pipeline and pipeline router
* Add Nvidia NIM as provider in Custom LLM
* Add knowledge demo + improve knowledge docs
* Add HITL multiple rounds of followup
* New docs about yaml crew with decorators
* Simplify template crew
**Features**
* Added knowledge to agent level
* Feat/remove langchain
* Improve typed task outputs
* Log in to Tool Repository on crewai login
**Fixes**
* Fixes issues with result as answer not properly exiting LLM loop
* Fix missing key name when running with ollama provider
* Fix spelling issue found
**Documentation**
* Update readme for running mypy
* Add knowledge to mint.json
* Update Github actions
* Update Agents docs to include two approaches for creating an agent
* Improvements to LLM Configuration and Usage
**New Features**
* New before\_kickoff and after\_kickoff crew callbacks
* Support to pre-seed agents with Knowledge
* Add support for retrieving user preferences and memories using Mem0
**Fixes**
* Fix Async Execution
* Upgrade chroma and adjust embedder function generator
* Update CLI Watson supported models + docs
* Reduce level for Bandit
* Fixing all tests
**Documentation**
* Update Docs
**Fixes**
* Fixing Tokens callback replacement bug
* Fixing Step callback issue
* Add cached prompt tokens info on usage metrics
* Fix crew\_train\_success test
# Agents
Source: https://docs.crewai.com/concepts/agents
Detailed guide on creating and managing agents within the CrewAI framework.
## Overview of an Agent
In the CrewAI framework, an `Agent` is an autonomous unit that can:
* Perform specific tasks
* Make decisions based on its role and goal
* Use tools to accomplish objectives
* Communicate and collaborate with other agents
* Maintain memory of interactions
* Delegate tasks when allowed
Think of an agent as a specialized team member with specific skills, expertise, and responsibilities. For example, a `Researcher` agent might excel at gathering and analyzing information, while a `Writer` agent might be better at creating content.
CrewAI Enterprise includes a Visual Agent Builder that simplifies agent creation and configuration without writing code. Design your agents visually and test them in real-time.
The Visual Agent Builder enables:
* Intuitive agent configuration with form-based interfaces
* Real-time testing and validation
* Template library with pre-configured agent types
* Easy customization of agent attributes and behaviors
## Agent Attributes
| Attribute | Parameter | Type | Description |
| :-------------------------------------- | :----------------------- | :------------------------------------ | :------------------------------------------------------------------------------------------------------- |
| **Role** | `role` | `str` | Defines the agent's function and expertise within the crew. |
| **Goal** | `goal` | `str` | The individual objective that guides the agent's decision-making. |
| **Backstory** | `backstory` | `str` | Provides context and personality to the agent, enriching interactions. |
| **LLM** *(optional)* | `llm` | `Union[str, LLM, Any]` | Language model that powers the agent. Defaults to the model specified in `OPENAI_MODEL_NAME` or "gpt-4". |
| **Tools** *(optional)* | `tools` | `List[BaseTool]` | Capabilities or functions available to the agent. Defaults to an empty list. |
| **Function Calling LLM** *(optional)* | `function_calling_llm` | `Optional[Any]` | Language model for tool calling, overrides crew's LLM if specified. |
| **Max Iterations** *(optional)* | `max_iter` | `int` | Maximum iterations before the agent must provide its best answer. Default is 20. |
| **Max RPM** *(optional)* | `max_rpm` | `Optional[int]` | Maximum requests per minute to avoid rate limits. |
| **Max Execution Time** *(optional)* | `max_execution_time` | `Optional[int]` | Maximum time (in seconds) for task execution. |
| **Memory** *(optional)* | `memory` | `bool` | Whether the agent should maintain memory of interactions. Default is True. |
| **Verbose** *(optional)* | `verbose` | `bool` | Enable detailed execution logs for debugging. Default is False. |
| **Allow Delegation** *(optional)* | `allow_delegation` | `bool` | Allow the agent to delegate tasks to other agents. Default is False. |
| **Step Callback** *(optional)* | `step_callback` | `Optional[Any]` | Function called after each agent step, overrides crew callback. |
| **Cache** *(optional)* | `cache` | `bool` | Enable caching for tool usage. Default is True. |
| **System Template** *(optional)* | `system_template` | `Optional[str]` | Custom system prompt template for the agent. |
| **Prompt Template** *(optional)* | `prompt_template` | `Optional[str]` | Custom prompt template for the agent. |
| **Response Template** *(optional)* | `response_template` | `Optional[str]` | Custom response template for the agent. |
| **Allow Code Execution** *(optional)* | `allow_code_execution` | `Optional[bool]` | Enable code execution for the agent. Default is False. |
| **Max Retry Limit** *(optional)* | `max_retry_limit` | `int` | Maximum number of retries when an error occurs. Default is 2. |
| **Respect Context Window** *(optional)* | `respect_context_window` | `bool` | Keep messages under context window size by summarizing. Default is True. |
| **Code Execution Mode** *(optional)* | `code_execution_mode` | `Literal["safe", "unsafe"]` | Mode for code execution: 'safe' (using Docker) or 'unsafe' (direct). Default is 'safe'. |
| **Embedder** *(optional)* | `embedder` | `Optional[Dict[str, Any]]` | Configuration for the embedder used by the agent. |
| **Knowledge Sources** *(optional)* | `knowledge_sources` | `Optional[List[BaseKnowledgeSource]]` | Knowledge sources available to the agent. |
| **Use System Prompt** *(optional)* | `use_system_prompt` | `Optional[bool]` | Whether to use system prompt (for o1 model support). Default is True. |
## Creating Agents
There are two ways to create agents in CrewAI: using **YAML configuration (recommended)** or defining them **directly in code**.
### YAML Configuration (Recommended)
Using YAML configuration provides a cleaner, more maintainable way to define agents. We strongly recommend using this approach in your CrewAI projects.
After creating your CrewAI project as outlined in the [Installation](/installation) section, navigate to the `src/latest_ai_development/config/agents.yaml` file and modify the template to match your requirements.
Variables in your YAML files (like `{topic}`) will be replaced with values from your inputs when running the crew:
```python Code
crew.kickoff(inputs={'topic': 'AI Agents'})
```
Here's an example of how to configure agents using YAML:
```yaml agents.yaml
# src/latest_ai_development/config/agents.yaml
researcher:
role: >
{topic} Senior Data Researcher
goal: >
Uncover cutting-edge developments in {topic}
backstory: >
You're a seasoned researcher with a knack for uncovering the latest
developments in {topic}. Known for your ability to find the most relevant
information and present it in a clear and concise manner.
reporting_analyst:
role: >
{topic} Reporting Analyst
goal: >
Create detailed reports based on {topic} data analysis and research findings
backstory: >
You're a meticulous analyst with a keen eye for detail. You're known for
your ability to turn complex data into clear and concise reports, making
it easy for others to understand and act on the information you provide.
```
To use this YAML configuration in your code, create a crew class that inherits from `CrewBase`:
```python Code
# src/latest_ai_development/crew.py
from crewai import Agent, Crew, Process
from crewai.project import CrewBase, agent, crew
from crewai_tools import SerperDevTool
@CrewBase
class LatestAiDevelopmentCrew():
"""LatestAiDevelopment crew"""
agents_config = "config/agents.yaml"
@agent
def researcher(self) -> Agent:
return Agent(
config=self.agents_config['researcher'], # type: ignore[index]
verbose=True,
tools=[SerperDevTool()]
)
@agent
def reporting_analyst(self) -> Agent:
return Agent(
config=self.agents_config['reporting_analyst'], # type: ignore[index]
verbose=True
)
```
The names you use in your YAML files (`agents.yaml`) should match the method names in your Python code.
### Direct Code Definition
You can create agents directly in code by instantiating the `Agent` class. Here's a comprehensive example showing all available parameters:
```python Code
from crewai import Agent
from crewai_tools import SerperDevTool
# Create an agent with all available parameters
agent = Agent(
role="Senior Data Scientist",
goal="Analyze and interpret complex datasets to provide actionable insights",
backstory="With over 10 years of experience in data science and machine learning, "
"you excel at finding patterns in complex datasets.",
llm="gpt-4", # Default: OPENAI_MODEL_NAME or "gpt-4"
function_calling_llm=None, # Optional: Separate LLM for tool calling
memory=True, # Default: True
verbose=False, # Default: False
allow_delegation=False, # Default: False
max_iter=20, # Default: 20 iterations
max_rpm=None, # Optional: Rate limit for API calls
max_execution_time=None, # Optional: Maximum execution time in seconds
max_retry_limit=2, # Default: 2 retries on error
allow_code_execution=False, # Default: False
code_execution_mode="safe", # Default: "safe" (options: "safe", "unsafe")
respect_context_window=True, # Default: True
use_system_prompt=True, # Default: True
tools=[SerperDevTool()], # Optional: List of tools
knowledge_sources=None, # Optional: List of knowledge sources
embedder=None, # Optional: Custom embedder configuration
system_template=None, # Optional: Custom system prompt template
prompt_template=None, # Optional: Custom prompt template
response_template=None, # Optional: Custom response template
step_callback=None, # Optional: Callback function for monitoring
)
```
Let's break down some key parameter combinations for common use cases:
#### Basic Research Agent
```python Code
research_agent = Agent(
role="Research Analyst",
goal="Find and summarize information about specific topics",
backstory="You are an experienced researcher with attention to detail",
tools=[SerperDevTool()],
verbose=True # Enable logging for debugging
)
```
#### Code Development Agent
```python Code
dev_agent = Agent(
role="Senior Python Developer",
goal="Write and debug Python code",
backstory="Expert Python developer with 10 years of experience",
allow_code_execution=True,
code_execution_mode="safe", # Uses Docker for safety
max_execution_time=300, # 5-minute timeout
max_retry_limit=3 # More retries for complex code tasks
)
```
#### Long-Running Analysis Agent
```python Code
analysis_agent = Agent(
role="Data Analyst",
goal="Perform deep analysis of large datasets",
backstory="Specialized in big data analysis and pattern recognition",
memory=True,
respect_context_window=True,
max_rpm=10, # Limit API calls
function_calling_llm="gpt-4o-mini" # Cheaper model for tool calls
)
```
#### Custom Template Agent
```python Code
custom_agent = Agent(
role="Customer Service Representative",
goal="Assist customers with their inquiries",
backstory="Experienced in customer support with a focus on satisfaction",
system_template="""<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>""",
prompt_template="""<|start_header_id|>user<|end_header_id|>
{{ .Prompt }}<|eot_id|>""",
response_template="""<|start_header_id|>assistant<|end_header_id|>
{{ .Response }}<|eot_id|>""",
)
```
### Parameter Details
#### Critical Parameters
* `role`, `goal`, and `backstory` are required and shape the agent's behavior
* `llm` determines the language model used (default: OpenAI's GPT-4)
#### Memory and Context
* `memory`: Enable to maintain conversation history
* `respect_context_window`: Prevents token limit issues
* `knowledge_sources`: Add domain-specific knowledge bases
#### Execution Control
* `max_iter`: Maximum attempts before giving best answer
* `max_execution_time`: Timeout in seconds
* `max_rpm`: Rate limiting for API calls
* `max_retry_limit`: Retries on error
#### Code Execution
* `allow_code_execution`: Must be True to run code
* `code_execution_mode`:
* `"safe"`: Uses Docker (recommended for production)
* `"unsafe"`: Direct execution (use only in trusted environments)
#### Templates
* `system_template`: Defines agent's core behavior
* `prompt_template`: Structures input format
* `response_template`: Formats agent responses
When using custom templates, you can use variables like `{role}`, `{goal}`, and `{input}` in your templates. These will be automatically populated during execution.
## Agent Tools
Agents can be equipped with various tools to enhance their capabilities. CrewAI supports tools from:
* [CrewAI Toolkit](https://github.com/joaomdmoura/crewai-tools)
* [LangChain Tools](https://python.langchain.com/docs/integrations/tools)
Here's how to add tools to an agent:
```python Code
from crewai import Agent
from crewai_tools import SerperDevTool, WikipediaTools
# Create tools
search_tool = SerperDevTool()
wiki_tool = WikipediaTools()
# Add tools to agent
researcher = Agent(
role="AI Technology Researcher",
goal="Research the latest AI developments",
tools=[search_tool, wiki_tool],
verbose=True
)
```
## Agent Memory and Context
Agents can maintain memory of their interactions and use context from previous tasks. This is particularly useful for complex workflows where information needs to be retained across multiple tasks.
```python Code
from crewai import Agent
analyst = Agent(
role="Data Analyst",
goal="Analyze and remember complex data patterns",
memory=True, # Enable memory
verbose=True
)
```
When `memory` is enabled, the agent will maintain context across multiple interactions, improving its ability to handle complex, multi-step tasks.
## Important Considerations and Best Practices
### Security and Code Execution
* When using `allow_code_execution`, be cautious with user input and always validate it
* Use `code_execution_mode: "safe"` (Docker) in production environments
* Consider setting appropriate `max_execution_time` limits to prevent infinite loops
### Performance Optimization
* Use `respect_context_window: true` to prevent token limit issues
* Set appropriate `max_rpm` to avoid rate limiting
* Enable `cache: true` to improve performance for repetitive tasks
* Adjust `max_iter` and `max_retry_limit` based on task complexity
### Memory and Context Management
* Use `memory: true` for tasks requiring historical context
* Leverage `knowledge_sources` for domain-specific information
* Configure `embedder_config` when using custom embedding models
* Use custom templates (`system_template`, `prompt_template`, `response_template`) for fine-grained control over agent behavior
### Agent Collaboration
* Enable `allow_delegation: true` when agents need to work together
* Use `step_callback` to monitor and log agent interactions
* Consider using different LLMs for different purposes:
* Main `llm` for complex reasoning
* `function_calling_llm` for efficient tool usage
### Model Compatibility
* Set `use_system_prompt: false` for older models that don't support system messages
* Ensure your chosen `llm` supports the features you need (like function calling)
## Troubleshooting Common Issues
1. **Rate Limiting**: If you're hitting API rate limits:
* Implement appropriate `max_rpm`
* Use caching for repetitive operations
* Consider batching requests
2. **Context Window Errors**: If you're exceeding context limits:
* Enable `respect_context_window`
* Use more efficient prompts
* Clear agent memory periodically
3. **Code Execution Issues**: If code execution fails:
* Verify Docker is installed for safe mode
* Check execution permissions
* Review code sandbox settings
4. **Memory Issues**: If agent responses seem inconsistent:
* Verify memory is enabled
* Check knowledge source configuration
* Review conversation history management
Remember that agents are most effective when configured according to their specific use case. Take time to understand your requirements and adjust these parameters accordingly.
# CLI
Source: https://docs.crewai.com/concepts/cli
Learn how to use the CrewAI CLI to interact with CrewAI.
# CrewAI CLI Documentation
The CrewAI CLI provides a set of commands to interact with CrewAI, allowing you to create, train, run, and manage crews & flows.
## Installation
To use the CrewAI CLI, make sure you have CrewAI installed:
```shell Terminal
pip install crewai
```
## Basic Usage
The basic structure of a CrewAI CLI command is:
```shell Terminal
crewai [COMMAND] [OPTIONS] [ARGUMENTS]
```
## Available Commands
### 1. Create
Create a new crew or flow.
```shell Terminal
crewai create [OPTIONS] TYPE NAME
```
* `TYPE`: Choose between "crew" or "flow"
* `NAME`: Name of the crew or flow
Example:
```shell Terminal
crewai create crew my_new_crew
crewai create flow my_new_flow
```
### 2. Version
Show the installed version of CrewAI.
```shell Terminal
crewai version [OPTIONS]
```
* `--tools`: (Optional) Show the installed version of CrewAI tools
Example:
```shell Terminal
crewai version
crewai version --tools
```
### 3. Train
Train the crew for a specified number of iterations.
```shell Terminal
crewai train [OPTIONS]
```
* `-n, --n_iterations INTEGER`: Number of iterations to train the crew (default: 5)
* `-f, --filename TEXT`: Path to a custom file for training (default: "trained\_agents\_data.pkl")
Example:
```shell Terminal
crewai train -n 10 -f my_training_data.pkl
```
### 4. Replay
Replay the crew execution from a specific task.
```shell Terminal
crewai replay [OPTIONS]
```
* `-t, --task_id TEXT`: Replay the crew from this task ID, including all subsequent tasks
Example:
```shell Terminal
crewai replay -t task_123456
```
### 5. Log-tasks-outputs
Retrieve your latest crew\.kickoff() task outputs.
```shell Terminal
crewai log-tasks-outputs
```
### 6. Reset-memories
Reset the crew memories (long, short, entity, latest\_crew\_kickoff\_outputs).
```shell Terminal
crewai reset-memories [OPTIONS]
```
* `-l, --long`: Reset LONG TERM memory
* `-s, --short`: Reset SHORT TERM memory
* `-e, --entities`: Reset ENTITIES memory
* `-k, --kickoff-outputs`: Reset LATEST KICKOFF TASK OUTPUTS
* `-a, --all`: Reset ALL memories
Example:
```shell Terminal
crewai reset-memories --long --short
crewai reset-memories --all
```
### 7. Test
Test the crew and evaluate the results.
```shell Terminal
crewai test [OPTIONS]
```
* `-n, --n_iterations INTEGER`: Number of iterations to test the crew (default: 3)
* `-m, --model TEXT`: LLM Model to run the tests on the Crew (default: "gpt-4o-mini")
Example:
```shell Terminal
crewai test -n 5 -m gpt-3.5-turbo
```
### 8. Run
Run the crew or flow.
```shell Terminal
crewai run
```
Starting from version 0.103.0, the `crewai run` command can be used to run both standard crews and flows. For flows, it automatically detects the type from pyproject.toml and runs the appropriate command. This is now the recommended way to run both crews and flows.
Make sure to run these commands from the directory where your CrewAI project is set up.
Some commands may require additional configuration or setup within your project structure.
### 9. Chat
Starting in version `0.98.0`, when you run the `crewai chat` command, you start an interactive session with your crew. The AI assistant will guide you by asking for necessary inputs to execute the crew. Once all inputs are provided, the crew will execute its tasks.
After receiving the results, you can continue interacting with the assistant for further instructions or questions.
```shell Terminal
crewai chat
```
Ensure you execute these commands from your CrewAI project's root directory.
IMPORTANT: Set the `chat_llm` property in your `crew.py` file to enable this command.
```python
@crew
def crew(self) -> Crew:
return Crew(
agents=self.agents,
tasks=self.tasks,
process=Process.sequential,
verbose=True,
chat_llm="gpt-4o", # LLM for chat orchestration
)
```
### 10. API Keys
When running `crewai create crew` command, the CLI will first show you the top 5 most common LLM providers and ask you to select one.
Once you've selected an LLM provider, you will be prompted for API keys.
#### Initial API key providers
The CLI will initially prompt for API keys for the following services:
* OpenAI
* Groq
* Anthropic
* Google Gemini
* SambaNova
When you select a provider, the CLI will prompt you to enter your API key.
#### Other Options
If you select option 6, you will be able to select from a list of LiteLLM supported providers.
When you select a provider, the CLI will prompt you to enter the Key name and the API key.
See the following link for each provider's key name:
* [LiteLLM Providers](https://docs.litellm.ai/docs/providers)
# Collaboration
Source: https://docs.crewai.com/concepts/collaboration
Exploring the dynamics of agent collaboration within the CrewAI framework, focusing on the newly integrated features for enhanced functionality.
## Collaboration Fundamentals
Collaboration in CrewAI is fundamental, enabling agents to combine their skills, share information, and assist each other in task execution, embodying a truly cooperative ecosystem.
* **Information Sharing**: Ensures all agents are well-informed and can contribute effectively by sharing data and findings.
* **Task Assistance**: Allows agents to seek help from peers with the required expertise for specific tasks.
* **Resource Allocation**: Optimizes task execution through the efficient distribution and sharing of resources among agents.
## Enhanced Attributes for Improved Collaboration
The `Crew` class has been enriched with several attributes to support advanced functionalities:
| Feature | Description |
| :-------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Language Model Management** (`manager_llm`, `function_calling_llm`) | Manages language models for executing tasks and tools. `manager_llm` is required for hierarchical processes, while `function_calling_llm` is optional with a default value for streamlined interactions. |
| **Custom Manager Agent** (`manager_agent`) | Specifies a custom agent as the manager, replacing the default CrewAI manager. |
| **Process Flow** (`process`) | Defines execution logic (e.g., sequential, hierarchical) for task distribution. |
| **Verbose Logging** (`verbose`) | Provides detailed logging for monitoring and debugging. Accepts integer and boolean values to control verbosity level. |
| **Rate Limiting** (`max_rpm`) | Limits requests per minute to optimize resource usage. Setting guidelines depend on task complexity and load. |
| **Internationalization / Customization** (`prompt_file`) | Supports prompt customization for global usability. [Example of file](https://github.com/joaomdmoura/crewAI/blob/main/src/crewai/translations/en.json) |
| **Callback and Telemetry** (`step_callback`, `task_callback`) | Enables step-wise and task-level execution monitoring and telemetry for performance analytics. |
| **Crew Sharing** (`share_crew`) | Allows sharing crew data with CrewAI for model improvement. Privacy implications and benefits should be considered. |
| **Usage Metrics** (`usage_metrics`) | Logs all LLM usage metrics during task execution for performance insights. |
| **Memory Usage** (`memory`) | Enables memory for storing execution history, aiding in agent learning and task efficiency. |
| **Embedder Configuration** (`embedder`) | Configures the embedder for language understanding and generation, with support for provider customization. |
| **Cache Management** (`cache`) | Specifies whether to cache tool execution results, enhancing performance. |
| **Output Logging** (`output_log_file`) | Defines the file path for logging crew execution output. |
| **Planning Mode** (`planning`) | Enables action planning before task execution. Set `planning=True` to activate. |
| **Replay Feature** (`replay`) | Provides CLI for listing tasks from the last run and replaying from specific tasks, aiding in task management and troubleshooting. |
## Delegation (Dividing to Conquer)
Delegation enhances functionality by allowing agents to intelligently assign tasks or seek help, thereby amplifying the crew's overall capability.
## Implementing Collaboration and Delegation
Setting up a crew involves defining the roles and capabilities of each agent. CrewAI seamlessly manages their interactions, ensuring efficient collaboration and delegation, with enhanced customization and monitoring features to adapt to various operational needs.
## Example Scenario
Consider a crew with a researcher agent tasked with data gathering and a writer agent responsible for compiling reports. The integration of advanced language model management and process flow attributes allows for more sophisticated interactions, such as the writer delegating complex research tasks to the researcher or querying specific information, thereby facilitating a seamless workflow.
## Conclusion
The integration of advanced attributes and functionalities into the CrewAI framework significantly enriches the agent collaboration ecosystem. These enhancements not only simplify interactions but also offer unprecedented flexibility and control, paving the way for sophisticated AI-driven solutions capable of tackling complex tasks through intelligent collaboration and delegation.
# Crews
Source: https://docs.crewai.com/concepts/crews
Understanding and utilizing crews in the crewAI framework with comprehensive attributes and functionalities.
## What is a Crew?
A crew in crewAI represents a collaborative group of agents working together to achieve a set of tasks. Each crew defines the strategy for task execution, agent collaboration, and the overall workflow.
## Crew Attributes
| Attribute | Parameters | Description |
| :------------------------------------ | :--------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Tasks** | `tasks` | A list of tasks assigned to the crew. |
| **Agents** | `agents` | A list of agents that are part of the crew. |
| **Process** *(optional)* | `process` | The process flow (e.g., sequential, hierarchical) the crew follows. Default is `sequential`. |
| **Verbose** *(optional)* | `verbose` | The verbosity level for logging during execution. Defaults to `False`. |
| **Manager LLM** *(optional)* | `manager_llm` | The language model used by the manager agent in a hierarchical process. **Required when using a hierarchical process.** |
| **Function Calling LLM** *(optional)* | `function_calling_llm` | If passed, the crew will use this LLM to do function calling for tools for all agents in the crew. Each agent can have its own LLM, which overrides the crew's LLM for function calling. |
| **Config** *(optional)* | `config` | Optional configuration settings for the crew, in `Json` or `Dict[str, Any]` format. |
| **Max RPM** *(optional)* | `max_rpm` | Maximum requests per minute the crew adheres to during execution. Defaults to `None`. |
| **Memory** *(optional)* | `memory` | Utilized for storing execution memories (short-term, long-term, entity memory). |
| **Memory Config** *(optional)* | `memory_config` | Configuration for the memory provider to be used by the crew. |
| **Cache** *(optional)* | `cache` | Specifies whether to use a cache for storing the results of tools' execution. Defaults to `True`. |
| **Embedder** *(optional)* | `embedder` | Configuration for the embedder to be used by the crew. Mostly used by memory for now. Default is `{"provider": "openai"}`. |
| **Step Callback** *(optional)* | `step_callback` | A function that is called after each step of every agent. This can be used to log the agent's actions or to perform other operations; it won't override the agent-specific `step_callback`. |
| **Task Callback** *(optional)* | `task_callback` | A function that is called after the completion of each task. Useful for monitoring or additional operations post-task execution. |
| **Share Crew** *(optional)* | `share_crew` | Whether you want to share the complete crew information and execution with the crewAI team to make the library better, and allow us to train models. |
| **Output Log File** *(optional)* | `output_log_file` | Set to True to save logs as logs.txt in the current directory or provide a file path. Logs will be in JSON format if the filename ends in .json, otherwise .txt. Defautls to `None`. |
| **Manager Agent** *(optional)* | `manager_agent` | `manager` sets a custom agent that will be used as a manager. |
| **Prompt File** *(optional)* | `prompt_file` | Path to the prompt JSON file to be used for the crew. |
| **Planning** *(optional)* | `planning` | Adds planning ability to the Crew. When activated before each Crew iteration, all Crew data is sent to an AgentPlanner that will plan the tasks and this plan will be added to each task description. |
| **Planning LLM** *(optional)* | `planning_llm` | The language model used by the AgentPlanner in a planning process. |
**Crew Max RPM**: The `max_rpm` attribute sets the maximum number of requests per minute the crew can perform to avoid rate limits and will override individual agents' `max_rpm` settings if you set it.
## Creating Crews
There are two ways to create crews in CrewAI: using **YAML configuration (recommended)** or defining them **directly in code**.
### YAML Configuration (Recommended)
Using YAML configuration provides a cleaner, more maintainable way to define crews and is consistent with how agents and tasks are defined in CrewAI projects.
After creating your CrewAI project as outlined in the [Installation](/installation) section, you can define your crew in a class that inherits from `CrewBase` and uses decorators to define agents, tasks, and the crew itself.
#### Example Crew Class with Decorators
```python code
from crewai import Agent, Crew, Task, Process
from crewai.project import CrewBase, agent, task, crew, before_kickoff, after_kickoff
from crewai.agents.agent_builder.base_agent import BaseAgent
from typing import List
@CrewBase
class YourCrewName:
"""Description of your crew"""
agents: List[BaseAgent]
tasks: List[Task]
# Paths to your YAML configuration files
# To see an example agent and task defined in YAML, checkout the following:
# - Task: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
# - Agents: https://docs.crewai.com/concepts/agents#yaml-configuration-recommended
agents_config = 'config/agents.yaml'
tasks_config = 'config/tasks.yaml'
@before_kickoff
def prepare_inputs(self, inputs):
# Modify inputs before the crew starts
inputs['additional_data'] = "Some extra information"
return inputs
@after_kickoff
def process_output(self, output):
# Modify output after the crew finishes
output.raw += "\nProcessed after kickoff."
return output
@agent
def agent_one(self) -> Agent:
return Agent(
config=self.agents_config['agent_one'], # type: ignore[index]
verbose=True
)
@agent
def agent_two(self) -> Agent:
return Agent(
config=self.agents_config['agent_two'], # type: ignore[index]
verbose=True
)
@task
def task_one(self) -> Task:
return Task(
config=self.tasks_config['task_one'] # type: ignore[index]
)
@task
def task_two(self) -> Task:
return Task(
config=self.tasks_config['task_two'] # type: ignore[index]
)
@crew
def crew(self) -> Crew:
return Crew(
agents=self.agents, # Automatically collected by the @agent decorator
tasks=self.tasks, # Automatically collected by the @task decorator.
process=Process.sequential,
verbose=True,
)
```
Tasks will be executed in the order they are defined.
The `CrewBase` class, along with these decorators, automates the collection of agents and tasks, reducing the need for manual management.
#### Decorators overview from `annotations.py`
CrewAI provides several decorators in the `annotations.py` file that are used to mark methods within your crew class for special handling:
* `@CrewBase`: Marks the class as a crew base class.
* `@agent`: Denotes a method that returns an `Agent` object.
* `@task`: Denotes a method that returns a `Task` object.
* `@crew`: Denotes the method that returns the `Crew` object.
* `@before_kickoff`: (Optional) Marks a method to be executed before the crew starts.
* `@after_kickoff`: (Optional) Marks a method to be executed after the crew finishes.
These decorators help in organizing your crew's structure and automatically collecting agents and tasks without manually listing them.
### Direct Code Definition (Alternative)
Alternatively, you can define the crew directly in code without using YAML configuration files.
```python code
from crewai import Agent, Crew, Task, Process
from crewai_tools import YourCustomTool
class YourCrewName:
def agent_one(self) -> Agent:
return Agent(
role="Data Analyst",
goal="Analyze data trends in the market",
backstory="An experienced data analyst with a background in economics",
verbose=True,
tools=[YourCustomTool()]
)
def agent_two(self) -> Agent:
return Agent(
role="Market Researcher",
goal="Gather information on market dynamics",
backstory="A diligent researcher with a keen eye for detail",
verbose=True
)
def task_one(self) -> Task:
return Task(
description="Collect recent market data and identify trends.",
expected_output="A report summarizing key trends in the market.",
agent=self.agent_one()
)
def task_two(self) -> Task:
return Task(
description="Research factors affecting market dynamics.",
expected_output="An analysis of factors influencing the market.",
agent=self.agent_two()
)
def crew(self) -> Crew:
return Crew(
agents=[self.agent_one(), self.agent_two()],
tasks=[self.task_one(), self.task_two()],
process=Process.sequential,
verbose=True
)
```
In this example:
* Agents and tasks are defined directly within the class without decorators.
* We manually create and manage the list of agents and tasks.
* This approach provides more control but can be less maintainable for larger projects.
## Crew Output
The output of a crew in the CrewAI framework is encapsulated within the `CrewOutput` class.
This class provides a structured way to access results of the crew's execution, including various formats such as raw strings, JSON, and Pydantic models.
The `CrewOutput` includes the results from the final task output, token usage, and individual task outputs.
### Crew Output Attributes
| Attribute | Parameters | Type | Description |
| :--------------- | :------------- | :------------------------- | :--------------------------------------------------------------------------------------------------- |
| **Raw** | `raw` | `str` | The raw output of the crew. This is the default format for the output. |
| **Pydantic** | `pydantic` | `Optional[BaseModel]` | A Pydantic model object representing the structured output of the crew. |
| **JSON Dict** | `json_dict` | `Optional[Dict[str, Any]]` | A dictionary representing the JSON output of the crew. |
| **Tasks Output** | `tasks_output` | `List[TaskOutput]` | A list of `TaskOutput` objects, each representing the output of a task in the crew. |
| **Token Usage** | `token_usage` | `Dict[str, Any]` | A summary of token usage, providing insights into the language model's performance during execution. |
### Crew Output Methods and Properties
| Method/Property | Description |
| :-------------- | :------------------------------------------------------------------------------------------------ |
| **json** | Returns the JSON string representation of the crew output if the output format is JSON. |
| **to\_dict** | Converts the JSON and Pydantic outputs to a dictionary. |
| \***\*str\*\*** | Returns the string representation of the crew output, prioritizing Pydantic, then JSON, then raw. |
### Accessing Crew Outputs
Once a crew has been executed, its output can be accessed through the `output` attribute of the `Crew` object. The `CrewOutput` class provides various ways to interact with and present this output.
#### Example
```python Code
# Example crew execution
crew = Crew(
agents=[research_agent, writer_agent],
tasks=[research_task, write_article_task],
verbose=True
)
crew_output = crew.kickoff()
# Accessing the crew output
print(f"Raw Output: {crew_output.raw}")
if crew_output.json_dict:
print(f"JSON Output: {json.dumps(crew_output.json_dict, indent=2)}")
if crew_output.pydantic:
print(f"Pydantic Output: {crew_output.pydantic}")
print(f"Tasks Output: {crew_output.tasks_output}")
print(f"Token Usage: {crew_output.token_usage}")
```
## Accessing Crew Logs
You can see real time log of the crew execution, by setting `output_log_file` as a `True(Boolean)` or a `file_name(str)`. Supports logging of events as both `file_name.txt` and `file_name.json`.
In case of `True(Boolean)` will save as `logs.txt`.
In case of `output_log_file` is set as `False(Booelan)` or `None`, the logs will not be populated.
```python Code
# Save crew logs
crew = Crew(output_log_file = True) # Logs will be saved as logs.txt
crew = Crew(output_log_file = file_name) # Logs will be saved as file_name.txt
crew = Crew(output_log_file = file_name.txt) # Logs will be saved as file_name.txt
crew = Crew(output_log_file = file_name.json) # Logs will be saved as file_name.json
```
## Memory Utilization
Crews can utilize memory (short-term, long-term, and entity memory) to enhance their execution and learning over time. This feature allows crews to store and recall execution memories, aiding in decision-making and task execution strategies.
## Cache Utilization
Caches can be employed to store the results of tools' execution, making the process more efficient by reducing the need to re-execute identical tasks.
## Crew Usage Metrics
After the crew execution, you can access the `usage_metrics` attribute to view the language model (LLM) usage metrics for all tasks executed by the crew. This provides insights into operational efficiency and areas for improvement.
```python Code
# Access the crew's usage metrics
crew = Crew(agents=[agent1, agent2], tasks=[task1, task2])
crew.kickoff()
print(crew.usage_metrics)
```
## Crew Execution Process
* **Sequential Process**: Tasks are executed one after another, allowing for a linear flow of work.
* **Hierarchical Process**: A manager agent coordinates the crew, delegating tasks and validating outcomes before proceeding. **Note**: A `manager_llm` or `manager_agent` is required for this process and it's essential for validating the process flow.
### Kicking Off a Crew
Once your crew is assembled, initiate the workflow with the `kickoff()` method. This starts the execution process according to the defined process flow.
```python Code
# Start the crew's task execution
result = my_crew.kickoff()
print(result)
```
### Different Ways to Kick Off a Crew
Once your crew is assembled, initiate the workflow with the appropriate kickoff method. CrewAI provides several methods for better control over the kickoff process: `kickoff()`, `kickoff_for_each()`, `kickoff_async()`, and `kickoff_for_each_async()`.
* `kickoff()`: Starts the execution process according to the defined process flow.
* `kickoff_for_each()`: Executes tasks sequentially for each provided input event or item in the collection.
* `kickoff_async()`: Initiates the workflow asynchronously.
* `kickoff_for_each_async()`: Executes tasks concurrently for each provided input event or item, leveraging asynchronous processing.
```python Code
# Start the crew's task execution
result = my_crew.kickoff()
print(result)
# Example of using kickoff_for_each
inputs_array = [{'topic': 'AI in healthcare'}, {'topic': 'AI in finance'}]
results = my_crew.kickoff_for_each(inputs=inputs_array)
for result in results:
print(result)
# Example of using kickoff_async
inputs = {'topic': 'AI in healthcare'}
async_result = my_crew.kickoff_async(inputs=inputs)
print(async_result)
# Example of using kickoff_for_each_async
inputs_array = [{'topic': 'AI in healthcare'}, {'topic': 'AI in finance'}]
async_results = my_crew.kickoff_for_each_async(inputs=inputs_array)
for async_result in async_results:
print(async_result)
```
These methods provide flexibility in how you manage and execute tasks within your crew, allowing for both synchronous and asynchronous workflows tailored to your needs.
### Replaying from a Specific Task
You can now replay from a specific task using our CLI command `replay`.
The replay feature in CrewAI allows you to replay from a specific task using the command-line interface (CLI). By running the command `crewai replay -t `, you can specify the `task_id` for the replay process.
Kickoffs will now save the latest kickoffs returned task outputs locally for you to be able to replay from.
### Replaying from a Specific Task Using the CLI
To use the replay feature, follow these steps:
1. Open your terminal or command prompt.
2. Navigate to the directory where your CrewAI project is located.
3. Run the following command:
To view the latest kickoff task IDs, use:
```shell
crewai log-tasks-outputs
```
Then, to replay from a specific task, use:
```shell
crewai replay -t
```
These commands let you replay from your latest kickoff tasks, still retaining context from previously executed tasks.
# Event Listeners
Source: https://docs.crewai.com/concepts/event-listener
Tap into CrewAI events to build custom integrations and monitoring
# Event Listeners
CrewAI provides a powerful event system that allows you to listen for and react to various events that occur during the execution of your Crew. This feature enables you to build custom integrations, monitoring solutions, logging systems, or any other functionality that needs to be triggered based on CrewAI's internal events.
## How It Works
CrewAI uses an event bus architecture to emit events throughout the execution lifecycle. The event system is built on the following components:
1. **CrewAIEventsBus**: A singleton event bus that manages event registration and emission
2. **BaseEvent**: Base class for all events in the system
3. **BaseEventListener**: Abstract base class for creating custom event listeners
When specific actions occur in CrewAI (like a Crew starting execution, an Agent completing a task, or a tool being used), the system emits corresponding events. You can register handlers for these events to execute custom code when they occur.
CrewAI Enterprise provides a built-in Prompt Tracing feature that leverages the event system to track, store, and visualize all prompts, completions, and associated metadata. This provides powerful debugging capabilities and transparency into your agent operations.
With Prompt Tracing you can:
* View the complete history of all prompts sent to your LLM
* Track token usage and costs
* Debug agent reasoning failures
* Share prompt sequences with your team
* Compare different prompt strategies
* Export traces for compliance and auditing
## Creating a Custom Event Listener
To create a custom event listener, you need to:
1. Create a class that inherits from `BaseEventListener`
2. Implement the `setup_listeners` method
3. Register handlers for the events you're interested in
4. Create an instance of your listener in the appropriate file
Here's a simple example of a custom event listener class:
```python
from crewai.utilities.events import (
CrewKickoffStartedEvent,
CrewKickoffCompletedEvent,
AgentExecutionCompletedEvent,
)
from crewai.utilities.events.base_event_listener import BaseEventListener
class MyCustomListener(BaseEventListener):
def __init__(self):
super().__init__()
def setup_listeners(self, crewai_event_bus):
@crewai_event_bus.on(CrewKickoffStartedEvent)
def on_crew_started(source, event):
print(f"Crew '{event.crew_name}' has started execution!")
@crewai_event_bus.on(CrewKickoffCompletedEvent)
def on_crew_completed(source, event):
print(f"Crew '{event.crew_name}' has completed execution!")
print(f"Output: {event.output}")
@crewai_event_bus.on(AgentExecutionCompletedEvent)
def on_agent_execution_completed(source, event):
print(f"Agent '{event.agent.role}' completed task")
print(f"Output: {event.output}")
```
## Properly Registering Your Listener
Simply defining your listener class isn't enough. You need to create an instance of it and ensure it's imported in your application. This ensures that:
1. The event handlers are registered with the event bus
2. The listener instance remains in memory (not garbage collected)
3. The listener is active when events are emitted
### Option 1: Import and Instantiate in Your Crew or Flow Implementation
The most important thing is to create an instance of your listener in the file where your Crew or Flow is defined and executed:
#### For Crew-based Applications
Create and import your listener at the top of your Crew implementation file:
```python
# In your crew.py file
from crewai import Agent, Crew, Task
from my_listeners import MyCustomListener
# Create an instance of your listener
my_listener = MyCustomListener()
class MyCustomCrew:
# Your crew implementation...
def crew(self):
return Crew(
agents=[...],
tasks=[...],
# ...
)
```
#### For Flow-based Applications
Create and import your listener at the top of your Flow implementation file:
```python
# In your main.py or flow.py file
from crewai.flow import Flow, listen, start
from my_listeners import MyCustomListener
# Create an instance of your listener
my_listener = MyCustomListener()
class MyCustomFlow(Flow):
# Your flow implementation...
@start()
def first_step(self):
# ...
```
This ensures that your listener is loaded and active when your Crew or Flow is executed.
### Option 2: Create a Package for Your Listeners
For a more structured approach, especially if you have multiple listeners:
1. Create a package for your listeners:
```
my_project/
├── listeners/
│ ├── __init__.py
│ ├── my_custom_listener.py
│ └── another_listener.py
```
2. In `my_custom_listener.py`, define your listener class and create an instance:
```python
# my_custom_listener.py
from crewai.utilities.events.base_event_listener import BaseEventListener
# ... import events ...
class MyCustomListener(BaseEventListener):
# ... implementation ...
# Create an instance of your listener
my_custom_listener = MyCustomListener()
```
3. In `__init__.py`, import the listener instances to ensure they're loaded:
```python
# __init__.py
from .my_custom_listener import my_custom_listener
from .another_listener import another_listener
# Optionally export them if you need to access them elsewhere
__all__ = ['my_custom_listener', 'another_listener']
```
4. Import your listeners package in your Crew or Flow file:
```python
# In your crew.py or flow.py file
import my_project.listeners # This loads all your listeners
class MyCustomCrew:
# Your crew implementation...
```
This is exactly how CrewAI's built-in `agentops_listener` is registered. In the CrewAI codebase, you'll find:
```python
# src/crewai/utilities/events/third_party/__init__.py
from .agentops_listener import agentops_listener
```
This ensures the `agentops_listener` is loaded when the `crewai.utilities.events` package is imported.
## Available Event Types
CrewAI provides a wide range of events that you can listen for:
### Crew Events
* **CrewKickoffStartedEvent**: Emitted when a Crew starts execution
* **CrewKickoffCompletedEvent**: Emitted when a Crew completes execution
* **CrewKickoffFailedEvent**: Emitted when a Crew fails to complete execution
* **CrewTestStartedEvent**: Emitted when a Crew starts testing
* **CrewTestCompletedEvent**: Emitted when a Crew completes testing
* **CrewTestFailedEvent**: Emitted when a Crew fails to complete testing
* **CrewTrainStartedEvent**: Emitted when a Crew starts training
* **CrewTrainCompletedEvent**: Emitted when a Crew completes training
* **CrewTrainFailedEvent**: Emitted when a Crew fails to complete training
### Agent Events
* **AgentExecutionStartedEvent**: Emitted when an Agent starts executing a task
* **AgentExecutionCompletedEvent**: Emitted when an Agent completes executing a task
* **AgentExecutionErrorEvent**: Emitted when an Agent encounters an error during execution
### Task Events
* **TaskStartedEvent**: Emitted when a Task starts execution
* **TaskCompletedEvent**: Emitted when a Task completes execution
* **TaskFailedEvent**: Emitted when a Task fails to complete execution
* **TaskEvaluationEvent**: Emitted when a Task is evaluated
### Tool Usage Events
* **ToolUsageStartedEvent**: Emitted when a tool execution is started
* **ToolUsageFinishedEvent**: Emitted when a tool execution is completed
* **ToolUsageErrorEvent**: Emitted when a tool execution encounters an error
* **ToolValidateInputErrorEvent**: Emitted when a tool input validation encounters an error
* **ToolExecutionErrorEvent**: Emitted when a tool execution encounters an error
* **ToolSelectionErrorEvent**: Emitted when there's an error selecting a tool
### Flow Events
* **FlowCreatedEvent**: Emitted when a Flow is created
* **FlowStartedEvent**: Emitted when a Flow starts execution
* **FlowFinishedEvent**: Emitted when a Flow completes execution
* **FlowPlotEvent**: Emitted when a Flow is plotted
* **MethodExecutionStartedEvent**: Emitted when a Flow method starts execution
* **MethodExecutionFinishedEvent**: Emitted when a Flow method completes execution
* **MethodExecutionFailedEvent**: Emitted when a Flow method fails to complete execution
### LLM Events
* **LLMCallStartedEvent**: Emitted when an LLM call starts
* **LLMCallCompletedEvent**: Emitted when an LLM call completes
* **LLMCallFailedEvent**: Emitted when an LLM call fails
* **LLMStreamChunkEvent**: Emitted for each chunk received during streaming LLM responses
## Event Handler Structure
Each event handler receives two parameters:
1. **source**: The object that emitted the event
2. **event**: The event instance, containing event-specific data
The structure of the event object depends on the event type, but all events inherit from `BaseEvent` and include:
* **timestamp**: The time when the event was emitted
* **type**: A string identifier for the event type
Additional fields vary by event type. For example, `CrewKickoffCompletedEvent` includes `crew_name` and `output` fields.
## Real-World Example: Integration with AgentOps
CrewAI includes an example of a third-party integration with [AgentOps](https://github.com/AgentOps-AI/agentops), a monitoring and observability platform for AI agents. Here's how it's implemented:
```python
from typing import Optional
from crewai.utilities.events import (
CrewKickoffCompletedEvent,
ToolUsageErrorEvent,
ToolUsageStartedEvent,
)
from crewai.utilities.events.base_event_listener import BaseEventListener
from crewai.utilities.events.crew_events import CrewKickoffStartedEvent
from crewai.utilities.events.task_events import TaskEvaluationEvent
try:
import agentops
AGENTOPS_INSTALLED = True
except ImportError:
AGENTOPS_INSTALLED = False
class AgentOpsListener(BaseEventListener):
tool_event: Optional["agentops.ToolEvent"] = None
session: Optional["agentops.Session"] = None
def __init__(self):
super().__init__()
def setup_listeners(self, crewai_event_bus):
if not AGENTOPS_INSTALLED:
return
@crewai_event_bus.on(CrewKickoffStartedEvent)
def on_crew_kickoff_started(source, event: CrewKickoffStartedEvent):
self.session = agentops.init()
for agent in source.agents:
if self.session:
self.session.create_agent(
name=agent.role,
agent_id=str(agent.id),
)
@crewai_event_bus.on(CrewKickoffCompletedEvent)
def on_crew_kickoff_completed(source, event: CrewKickoffCompletedEvent):
if self.session:
self.session.end_session(
end_state="Success",
end_state_reason="Finished Execution",
)
@crewai_event_bus.on(ToolUsageStartedEvent)
def on_tool_usage_started(source, event: ToolUsageStartedEvent):
self.tool_event = agentops.ToolEvent(name=event.tool_name)
if self.session:
self.session.record(self.tool_event)
@crewai_event_bus.on(ToolUsageErrorEvent)
def on_tool_usage_error(source, event: ToolUsageErrorEvent):
agentops.ErrorEvent(exception=event.error, trigger_event=self.tool_event)
```
This listener initializes an AgentOps session when a Crew starts, registers agents with AgentOps, tracks tool usage, and ends the session when the Crew completes.
The AgentOps listener is registered in CrewAI's event system through the import in `src/crewai/utilities/events/third_party/__init__.py`:
```python
from .agentops_listener import agentops_listener
```
This ensures the `agentops_listener` is loaded when the `crewai.utilities.events` package is imported.
## Advanced Usage: Scoped Handlers
For temporary event handling (useful for testing or specific operations), you can use the `scoped_handlers` context manager:
```python
from crewai.utilities.events import crewai_event_bus, CrewKickoffStartedEvent
with crewai_event_bus.scoped_handlers():
@crewai_event_bus.on(CrewKickoffStartedEvent)
def temp_handler(source, event):
print("This handler only exists within this context")
# Do something that emits events
# Outside the context, the temporary handler is removed
```
## Use Cases
Event listeners can be used for a variety of purposes:
1. **Logging and Monitoring**: Track the execution of your Crew and log important events
2. **Analytics**: Collect data about your Crew's performance and behavior
3. **Debugging**: Set up temporary listeners to debug specific issues
4. **Integration**: Connect CrewAI with external systems like monitoring platforms, databases, or notification services
5. **Custom Behavior**: Trigger custom actions based on specific events
## Best Practices
1. **Keep Handlers Light**: Event handlers should be lightweight and avoid blocking operations
2. **Error Handling**: Include proper error handling in your event handlers to prevent exceptions from affecting the main execution
3. **Cleanup**: If your listener allocates resources, ensure they're properly cleaned up
4. **Selective Listening**: Only listen for events you actually need to handle
5. **Testing**: Test your event listeners in isolation to ensure they behave as expected
By leveraging CrewAI's event system, you can extend its functionality and integrate it seamlessly with your existing infrastructure.
# Flows
Source: https://docs.crewai.com/concepts/flows
Learn how to create and manage AI workflows using CrewAI Flows.
## Introduction
CrewAI Flows is a powerful feature designed to streamline the creation and management of AI workflows. Flows allow developers to combine and coordinate coding tasks and Crews efficiently, providing a robust framework for building sophisticated AI automations.
Flows allow you to create structured, event-driven workflows. They provide a seamless way to connect multiple tasks, manage state, and control the flow of execution in your AI applications. With Flows, you can easily design and implement multi-step processes that leverage the full potential of CrewAI's capabilities.
1. **Simplified Workflow Creation**: Easily chain together multiple Crews and tasks to create complex AI workflows.
2. **State Management**: Flows make it super easy to manage and share state between different tasks in your workflow.
3. **Event-Driven Architecture**: Built on an event-driven model, allowing for dynamic and responsive workflows.
4. **Flexible Control Flow**: Implement conditional logic, loops, and branching within your workflows.
## Getting Started
Let's create a simple Flow where you will use OpenAI to generate a random city in one task and then use that city to generate a fun fact in another task.
```python Code
from crewai.flow.flow import Flow, listen, start
from dotenv import load_dotenv
from litellm import completion
class ExampleFlow(Flow):
model = "gpt-4o-mini"
@start()
def generate_city(self):
print("Starting flow")
# Each flow state automatically gets a unique ID
print(f"Flow State ID: {self.state['id']}")
response = completion(
model=self.model,
messages=[
{
"role": "user",
"content": "Return the name of a random city in the world.",
},
],
)
random_city = response["choices"][0]["message"]["content"]
# Store the city in our state
self.state["city"] = random_city
print(f"Random City: {random_city}")
return random_city
@listen(generate_city)
def generate_fun_fact(self, random_city):
response = completion(
model=self.model,
messages=[
{
"role": "user",
"content": f"Tell me a fun fact about {random_city}",
},
],
)
fun_fact = response["choices"][0]["message"]["content"]
# Store the fun fact in our state
self.state["fun_fact"] = fun_fact
return fun_fact
flow = ExampleFlow()
result = flow.kickoff()
print(f"Generated fun fact: {result}")
```
In the above example, we have created a simple Flow that generates a random city using OpenAI and then generates a fun fact about that city. The Flow consists of two tasks: `generate_city` and `generate_fun_fact`. The `generate_city` task is the starting point of the Flow, and the `generate_fun_fact` task listens for the output of the `generate_city` task.
Each Flow instance automatically receives a unique identifier (UUID) in its state, which helps track and manage flow executions. The state can also store additional data (like the generated city and fun fact) that persists throughout the flow's execution.
When you run the Flow, it will:
1. Generate a unique ID for the flow state
2. Generate a random city and store it in the state
3. Generate a fun fact about that city and store it in the state
4. Print the results to the console
The state's unique ID and stored data can be useful for tracking flow executions and maintaining context between tasks.
**Note:** Ensure you have set up your `.env` file to store your `OPENAI_API_KEY`. This key is necessary for authenticating requests to the OpenAI API.
### @start()
The `@start()` decorator is used to mark a method as the starting point of a Flow. When a Flow is started, all the methods decorated with `@start()` are executed in parallel. You can have multiple start methods in a Flow, and they will all be executed when the Flow is started.
### @listen()
The `@listen()` decorator is used to mark a method as a listener for the output of another task in the Flow. The method decorated with `@listen()` will be executed when the specified task emits an output. The method can access the output of the task it is listening to as an argument.
#### Usage
The `@listen()` decorator can be used in several ways:
1. **Listening to a Method by Name**: You can pass the name of the method you want to listen to as a string. When that method completes, the listener method will be triggered.
```python Code
@listen("generate_city")
def generate_fun_fact(self, random_city):
# Implementation
```
2. **Listening to a Method Directly**: You can pass the method itself. When that method completes, the listener method will be triggered.
```python Code
@listen(generate_city)
def generate_fun_fact(self, random_city):
# Implementation
```
### Flow Output
Accessing and handling the output of a Flow is essential for integrating your AI workflows into larger applications or systems. CrewAI Flows provide straightforward mechanisms to retrieve the final output, access intermediate results, and manage the overall state of your Flow.
#### Retrieving the Final Output
When you run a Flow, the final output is determined by the last method that completes. The `kickoff()` method returns the output of this final method.
Here's how you can access the final output:
```python Code
from crewai.flow.flow import Flow, listen, start
class OutputExampleFlow(Flow):
@start()
def first_method(self):
return "Output from first_method"
@listen(first_method)
def second_method(self, first_output):
return f"Second method received: {first_output}"
flow = OutputExampleFlow()
final_output = flow.kickoff()
print("---- Final Output ----")
print(final_output)
```
```text Output
---- Final Output ----
Second method received: Output from first_method
```
In this example, the `second_method` is the last method to complete, so its output will be the final output of the Flow.
The `kickoff()` method will return the final output, which is then printed to the console.
#### Accessing and Updating State
In addition to retrieving the final output, you can also access and update the state within your Flow. The state can be used to store and share data between different methods in the Flow. After the Flow has run, you can access the state to retrieve any information that was added or updated during the execution.
Here's an example of how to update and access the state:
```python Code
from crewai.flow.flow import Flow, listen, start
from pydantic import BaseModel
class ExampleState(BaseModel):
counter: int = 0
message: str = ""
class StateExampleFlow(Flow[ExampleState]):
@start()
def first_method(self):
self.state.message = "Hello from first_method"
self.state.counter += 1
@listen(first_method)
def second_method(self):
self.state.message += " - updated by second_method"
self.state.counter += 1
return self.state.message
flow = StateExampleFlow()
final_output = flow.kickoff()
print(f"Final Output: {final_output}")
print("Final State:")
print(flow.state)
```
```text Output
Final Output: Hello from first_method - updated by second_method
Final State:
counter=2 message='Hello from first_method - updated by second_method'
```
In this example, the state is updated by both `first_method` and `second_method`.
After the Flow has run, you can access the final state to see the updates made by these methods.
By ensuring that the final method's output is returned and providing access to the state, CrewAI Flows make it easy to integrate the results of your AI workflows into larger applications or systems,
while also maintaining and accessing the state throughout the Flow's execution.
## Flow State Management
Managing state effectively is crucial for building reliable and maintainable AI workflows. CrewAI Flows provides robust mechanisms for both unstructured and structured state management,
allowing developers to choose the approach that best fits their application's needs.
### Unstructured State Management
In unstructured state management, all state is stored in the `state` attribute of the `Flow` class.
This approach offers flexibility, enabling developers to add or modify state attributes on the fly without defining a strict schema.
Even with unstructured states, CrewAI Flows automatically generates and maintains a unique identifier (UUID) for each state instance.
```python Code
from crewai.flow.flow import Flow, listen, start
class UnstructuredExampleFlow(Flow):
@start()
def first_method(self):
# The state automatically includes an 'id' field
print(f"State ID: {self.state['id']}")
self.state['counter'] = 0
self.state['message'] = "Hello from structured flow"
@listen(first_method)
def second_method(self):
self.state['counter'] += 1
self.state['message'] += " - updated"
@listen(second_method)
def third_method(self):
self.state['counter'] += 1
self.state['message'] += " - updated again"
print(f"State after third_method: {self.state}")
flow = UnstructuredExampleFlow()
flow.kickoff()
```
**Note:** The `id` field is automatically generated and preserved throughout the flow's execution. You don't need to manage or set it manually, and it will be maintained even when updating the state with new data.
**Key Points:**
* **Flexibility:** You can dynamically add attributes to `self.state` without predefined constraints.
* **Simplicity:** Ideal for straightforward workflows where state structure is minimal or varies significantly.
### Structured State Management
Structured state management leverages predefined schemas to ensure consistency and type safety across the workflow.
By using models like Pydantic's `BaseModel`, developers can define the exact shape of the state, enabling better validation and auto-completion in development environments.
Each state in CrewAI Flows automatically receives a unique identifier (UUID) to help track and manage state instances. This ID is automatically generated and managed by the Flow system.
```python Code
from crewai.flow.flow import Flow, listen, start
from pydantic import BaseModel
class ExampleState(BaseModel):
# Note: 'id' field is automatically added to all states
counter: int = 0
message: str = ""
class StructuredExampleFlow(Flow[ExampleState]):
@start()
def first_method(self):
# Access the auto-generated ID if needed
print(f"State ID: {self.state.id}")
self.state.message = "Hello from structured flow"
@listen(first_method)
def second_method(self):
self.state.counter += 1
self.state.message += " - updated"
@listen(second_method)
def third_method(self):
self.state.counter += 1
self.state.message += " - updated again"
print(f"State after third_method: {self.state}")
flow = StructuredExampleFlow()
flow.kickoff()
```
**Key Points:**
* **Defined Schema:** `ExampleState` clearly outlines the state structure, enhancing code readability and maintainability.
* **Type Safety:** Leveraging Pydantic ensures that state attributes adhere to the specified types, reducing runtime errors.
* **Auto-Completion:** IDEs can provide better auto-completion and error checking based on the defined state model.
### Choosing Between Unstructured and Structured State Management
* **Use Unstructured State Management when:**
* The workflow's state is simple or highly dynamic.
* Flexibility is prioritized over strict state definitions.
* Rapid prototyping is required without the overhead of defining schemas.
* **Use Structured State Management when:**
* The workflow requires a well-defined and consistent state structure.
* Type safety and validation are important for your application's reliability.
* You want to leverage IDE features like auto-completion and type checking for better developer experience.
By providing both unstructured and structured state management options, CrewAI Flows empowers developers to build AI workflows that are both flexible and robust, catering to a wide range of application requirements.
## Flow Persistence
The @persist decorator enables automatic state persistence in CrewAI Flows, allowing you to maintain flow state across restarts or different workflow executions. This decorator can be applied at either the class level or method level, providing flexibility in how you manage state persistence.
### Class-Level Persistence
When applied at the class level, the @persist decorator automatically persists all flow method states:
```python
@persist # Using SQLiteFlowPersistence by default
class MyFlow(Flow[MyState]):
@start()
def initialize_flow(self):
# This method will automatically have its state persisted
self.state.counter = 1
print("Initialized flow. State ID:", self.state.id)
@listen(initialize_flow)
def next_step(self):
# The state (including self.state.id) is automatically reloaded
self.state.counter += 1
print("Flow state is persisted. Counter:", self.state.counter)
```
### Method-Level Persistence
For more granular control, you can apply @persist to specific methods:
```python
class AnotherFlow(Flow[dict]):
@persist # Persists only this method's state
@start()
def begin(self):
if "runs" not in self.state:
self.state["runs"] = 0
self.state["runs"] += 1
print("Method-level persisted runs:", self.state["runs"])
```
### How It Works
1. **Unique State Identification**
* Each flow state automatically receives a unique UUID
* The ID is preserved across state updates and method calls
* Supports both structured (Pydantic BaseModel) and unstructured (dictionary) states
2. **Default SQLite Backend**
* SQLiteFlowPersistence is the default storage backend
* States are automatically saved to a local SQLite database
* Robust error handling ensures clear messages if database operations fail
3. **Error Handling**
* Comprehensive error messages for database operations
* Automatic state validation during save and load
* Clear feedback when persistence operations encounter issues
### Important Considerations
* **State Types**: Both structured (Pydantic BaseModel) and unstructured (dictionary) states are supported
* **Automatic ID**: The `id` field is automatically added if not present
* **State Recovery**: Failed or restarted flows can automatically reload their previous state
* **Custom Implementation**: You can provide your own FlowPersistence implementation for specialized storage needs
### Technical Advantages
1. **Precise Control Through Low-Level Access**
* Direct access to persistence operations for advanced use cases
* Fine-grained control via method-level persistence decorators
* Built-in state inspection and debugging capabilities
* Full visibility into state changes and persistence operations
2. **Enhanced Reliability**
* Automatic state recovery after system failures or restarts
* Transaction-based state updates for data integrity
* Comprehensive error handling with clear error messages
* Robust validation during state save and load operations
3. **Extensible Architecture**
* Customizable persistence backend through FlowPersistence interface
* Support for specialized storage solutions beyond SQLite
* Compatible with both structured (Pydantic) and unstructured (dict) states
* Seamless integration with existing CrewAI flow patterns
The persistence system's architecture emphasizes technical precision and customization options, allowing developers to maintain full control over state management while benefiting from built-in reliability features.
## Flow Control
### Conditional Logic: `or`
The `or_` function in Flows allows you to listen to multiple methods and trigger the listener method when any of the specified methods emit an output.
```python Code
from crewai.flow.flow import Flow, listen, or_, start
class OrExampleFlow(Flow):
@start()
def start_method(self):
return "Hello from the start method"
@listen(start_method)
def second_method(self):
return "Hello from the second method"
@listen(or_(start_method, second_method))
def logger(self, result):
print(f"Logger: {result}")
flow = OrExampleFlow()
flow.kickoff()
```
```text Output
Logger: Hello from the start method
Logger: Hello from the second method
```
When you run this Flow, the `logger` method will be triggered by the output of either the `start_method` or the `second_method`.
The `or_` function is used to listen to multiple methods and trigger the listener method when any of the specified methods emit an output.
### Conditional Logic: `and`
The `and_` function in Flows allows you to listen to multiple methods and trigger the listener method only when all the specified methods emit an output.
```python Code
from crewai.flow.flow import Flow, and_, listen, start
class AndExampleFlow(Flow):
@start()
def start_method(self):
self.state["greeting"] = "Hello from the start method"
@listen(start_method)
def second_method(self):
self.state["joke"] = "What do computers eat? Microchips."
@listen(and_(start_method, second_method))
def logger(self):
print("---- Logger ----")
print(self.state)
flow = AndExampleFlow()
flow.kickoff()
```
```text Output
---- Logger ----
{'greeting': 'Hello from the start method', 'joke': 'What do computers eat? Microchips.'}
```
When you run this Flow, the `logger` method will be triggered only when both the `start_method` and the `second_method` emit an output.
The `and_` function is used to listen to multiple methods and trigger the listener method only when all the specified methods emit an output.
### Router
The `@router()` decorator in Flows allows you to define conditional routing logic based on the output of a method.
You can specify different routes based on the output of the method, allowing you to control the flow of execution dynamically.
```python Code
import random
from crewai.flow.flow import Flow, listen, router, start
from pydantic import BaseModel
class ExampleState(BaseModel):
success_flag: bool = False
class RouterFlow(Flow[ExampleState]):
@start()
def start_method(self):
print("Starting the structured flow")
random_boolean = random.choice([True, False])
self.state.success_flag = random_boolean
@router(start_method)
def second_method(self):
if self.state.success_flag:
return "success"
else:
return "failed"
@listen("success")
def third_method(self):
print("Third method running")
@listen("failed")
def fourth_method(self):
print("Fourth method running")
flow = RouterFlow()
flow.kickoff()
```
```text Output
Starting the structured flow
Third method running
Fourth method running
```
In the above example, the `start_method` generates a random boolean value and sets it in the state.
The `second_method` uses the `@router()` decorator to define conditional routing logic based on the value of the boolean.
If the boolean is `True`, the method returns `"success"`, and if it is `False`, the method returns `"failed"`.
The `third_method` and `fourth_method` listen to the output of the `second_method` and execute based on the returned value.
When you run this Flow, the output will change based on the random boolean value generated by the `start_method`.
## Adding Agents to Flows
Agents can be seamlessly integrated into your flows, providing a lightweight alternative to full Crews when you need simpler, focused task execution. Here's an example of how to use an Agent within a flow to perform market research:
```python
import asyncio
from typing import Any, Dict, List
from crewai_tools import SerperDevTool
from pydantic import BaseModel, Field
from crewai.agent import Agent
from crewai.flow.flow import Flow, listen, start
# Define a structured output format
class MarketAnalysis(BaseModel):
key_trends: List[str] = Field(description="List of identified market trends")
market_size: str = Field(description="Estimated market size")
competitors: List[str] = Field(description="Major competitors in the space")
# Define flow state
class MarketResearchState(BaseModel):
product: str = ""
analysis: MarketAnalysis | None = None
# Create a flow class
class MarketResearchFlow(Flow[MarketResearchState]):
@start()
def initialize_research(self) -> Dict[str, Any]:
print(f"Starting market research for {self.state.product}")
return {"product": self.state.product}
@listen(initialize_research)
async def analyze_market(self) -> Dict[str, Any]:
# Create an Agent for market research
analyst = Agent(
role="Market Research Analyst",
goal=f"Analyze the market for {self.state.product}",
backstory="You are an experienced market analyst with expertise in "
"identifying market trends and opportunities.",
tools=[SerperDevTool()],
verbose=True,
)
# Define the research query
query = f"""
Research the market for {self.state.product}. Include:
1. Key market trends
2. Market size
3. Major competitors
Format your response according to the specified structure.
"""
# Execute the analysis with structured output format
result = await analyst.kickoff_async(query, response_format=MarketAnalysis)
if result.pydantic:
print("result", result.pydantic)
else:
print("result", result)
# Return the analysis to update the state
return {"analysis": result.pydantic}
@listen(analyze_market)
def present_results(self, analysis) -> None:
print("\nMarket Analysis Results")
print("=====================")
if isinstance(analysis, dict):
# If we got a dict with 'analysis' key, extract the actual analysis object
market_analysis = analysis.get("analysis")
else:
market_analysis = analysis
if market_analysis and isinstance(market_analysis, MarketAnalysis):
print("\nKey Market Trends:")
for trend in market_analysis.key_trends:
print(f"- {trend}")
print(f"\nMarket Size: {market_analysis.market_size}")
print("\nMajor Competitors:")
for competitor in market_analysis.competitors:
print(f"- {competitor}")
else:
print("No structured analysis data available.")
print("Raw analysis:", analysis)
# Usage example
async def run_flow():
flow = MarketResearchFlow()
result = await flow.kickoff_async(inputs={"product": "AI-powered chatbots"})
return result
# Run the flow
if __name__ == "__main__":
asyncio.run(run_flow())
```
This example demonstrates several key features of using Agents in flows:
1. **Structured Output**: Using Pydantic models to define the expected output format (`MarketAnalysis`) ensures type safety and structured data throughout the flow.
2. **State Management**: The flow state (`MarketResearchState`) maintains context between steps and stores both inputs and outputs.
3. **Tool Integration**: Agents can use tools (like `WebsiteSearchTool`) to enhance their capabilities.
## Adding Crews to Flows
Creating a flow with multiple crews in CrewAI is straightforward.
You can generate a new CrewAI project that includes all the scaffolding needed to create a flow with multiple crews by running the following command:
```bash
crewai create flow name_of_flow
```
This command will generate a new CrewAI project with the necessary folder structure. The generated project includes a prebuilt crew called `poem_crew` that is already working. You can use this crew as a template by copying, pasting, and editing it to create other crews.
### Folder Structure
After running the `crewai create flow name_of_flow` command, you will see a folder structure similar to the following:
| Directory/File | Description |
| :--------------------- | :------------------------------------------------------------------ |
| `name_of_flow/` | Root directory for the flow. |
| ├── `crews/` | Contains directories for specific crews. |
| │ └── `poem_crew/` | Directory for the "poem\_crew" with its configurations and scripts. |
| │ ├── `config/` | Configuration files directory for the "poem\_crew". |
| │ │ ├── `agents.yaml` | YAML file defining the agents for "poem\_crew". |
| │ │ └── `tasks.yaml` | YAML file defining the tasks for "poem\_crew". |
| │ ├── `poem_crew.py` | Script for "poem\_crew" functionality. |
| ├── `tools/` | Directory for additional tools used in the flow. |
| │ └── `custom_tool.py` | Custom tool implementation. |
| ├── `main.py` | Main script for running the flow. |
| ├── `README.md` | Project description and instructions. |
| ├── `pyproject.toml` | Configuration file for project dependencies and settings. |
| └── `.gitignore` | Specifies files and directories to ignore in version control. |
### Building Your Crews
In the `crews` folder, you can define multiple crews. Each crew will have its own folder containing configuration files and the crew definition file. For example, the `poem_crew` folder contains:
* `config/agents.yaml`: Defines the agents for the crew.
* `config/tasks.yaml`: Defines the tasks for the crew.
* `poem_crew.py`: Contains the crew definition, including agents, tasks, and the crew itself.
You can copy, paste, and edit the `poem_crew` to create other crews.
### Connecting Crews in `main.py`
The `main.py` file is where you create your flow and connect the crews together. You can define your flow by using the `Flow` class and the decorators `@start` and `@listen` to specify the flow of execution.
Here's an example of how you can connect the `poem_crew` in the `main.py` file:
```python Code
#!/usr/bin/env python
from random import randint
from pydantic import BaseModel
from crewai.flow.flow import Flow, listen, start
from .crews.poem_crew.poem_crew import PoemCrew
class PoemState(BaseModel):
sentence_count: int = 1
poem: str = ""
class PoemFlow(Flow[PoemState]):
@start()
def generate_sentence_count(self):
print("Generating sentence count")
self.state.sentence_count = randint(1, 5)
@listen(generate_sentence_count)
def generate_poem(self):
print("Generating poem")
result = PoemCrew().crew().kickoff(inputs={"sentence_count": self.state.sentence_count})
print("Poem generated", result.raw)
self.state.poem = result.raw
@listen(generate_poem)
def save_poem(self):
print("Saving poem")
with open("poem.txt", "w") as f:
f.write(self.state.poem)
def kickoff():
poem_flow = PoemFlow()
poem_flow.kickoff()
def plot():
poem_flow = PoemFlow()
poem_flow.plot()
if __name__ == "__main__":
kickoff()
```
In this example, the `PoemFlow` class defines a flow that generates a sentence count, uses the `PoemCrew` to generate a poem, and then saves the poem to a file. The flow is kicked off by calling the `kickoff()` method.
### Running the Flow
(Optional) Before running the flow, you can install the dependencies by running:
```bash
crewai install
```
Once all of the dependencies are installed, you need to activate the virtual environment by running:
```bash
source .venv/bin/activate
```
After activating the virtual environment, you can run the flow by executing one of the following commands:
```bash
crewai flow kickoff
```
or
```bash
uv run kickoff
```
The flow will execute, and you should see the output in the console.
## Plot Flows
Visualizing your AI workflows can provide valuable insights into the structure and execution paths of your flows. CrewAI offers a powerful visualization tool that allows you to generate interactive plots of your flows, making it easier to understand and optimize your AI workflows.
### What are Plots?
Plots in CrewAI are graphical representations of your AI workflows. They display the various tasks, their connections, and the flow of data between them. This visualization helps in understanding the sequence of operations, identifying bottlenecks, and ensuring that the workflow logic aligns with your expectations.
### How to Generate a Plot
CrewAI provides two convenient methods to generate plots of your flows:
#### Option 1: Using the `plot()` Method
If you are working directly with a flow instance, you can generate a plot by calling the `plot()` method on your flow object. This method will create an HTML file containing the interactive plot of your flow.
```python Code
# Assuming you have a flow instance
flow.plot("my_flow_plot")
```
This will generate a file named `my_flow_plot.html` in your current directory. You can open this file in a web browser to view the interactive plot.
#### Option 2: Using the Command Line
If you are working within a structured CrewAI project, you can generate a plot using the command line. This is particularly useful for larger projects where you want to visualize the entire flow setup.
```bash
crewai flow plot
```
This command will generate an HTML file with the plot of your flow, similar to the `plot()` method. The file will be saved in your project directory, and you can open it in a web browser to explore the flow.
### Understanding the Plot
The generated plot will display nodes representing the tasks in your flow, with directed edges indicating the flow of execution. The plot is interactive, allowing you to zoom in and out, and hover over nodes to see additional details.
By visualizing your flows, you can gain a clearer understanding of the workflow's structure, making it easier to debug, optimize, and communicate your AI processes to others.
### Conclusion
Plotting your flows is a powerful feature of CrewAI that enhances your ability to design and manage complex AI workflows. Whether you choose to use the `plot()` method or the command line, generating plots will provide you with a visual representation of your workflows, aiding in both development and presentation.
## Next Steps
If you're interested in exploring additional examples of flows, we have a variety of recommendations in our examples repository. Here are four specific flow examples, each showcasing unique use cases to help you match your current problem type to a specific example:
1. **Email Auto Responder Flow**: This example demonstrates an infinite loop where a background job continually runs to automate email responses. It's a great use case for tasks that need to be performed repeatedly without manual intervention. [View Example](https://github.com/crewAIInc/crewAI-examples/tree/main/email_auto_responder_flow)
2. **Lead Score Flow**: This flow showcases adding human-in-the-loop feedback and handling different conditional branches using the router. It's an excellent example of how to incorporate dynamic decision-making and human oversight into your workflows. [View Example](https://github.com/crewAIInc/crewAI-examples/tree/main/lead-score-flow)
3. **Write a Book Flow**: This example excels at chaining multiple crews together, where the output of one crew is used by another. Specifically, one crew outlines an entire book, and another crew generates chapters based on the outline. Eventually, everything is connected to produce a complete book. This flow is perfect for complex, multi-step processes that require coordination between different tasks. [View Example](https://github.com/crewAIInc/crewAI-examples/tree/main/write_a_book_with_flows)
4. **Meeting Assistant Flow**: This flow demonstrates how to broadcast one event to trigger multiple follow-up actions. For instance, after a meeting is completed, the flow can update a Trello board, send a Slack message, and save the results. It's a great example of handling multiple outcomes from a single event, making it ideal for comprehensive task management and notification systems. [View Example](https://github.com/crewAIInc/crewAI-examples/tree/main/meeting_assistant_flow)
By exploring these examples, you can gain insights into how to leverage CrewAI Flows for various use cases, from automating repetitive tasks to managing complex, multi-step processes with dynamic decision-making and human feedback.
Also, check out our YouTube video on how to use flows in CrewAI below!
## Running Flows
There are two ways to run a flow:
### Using the Flow API
You can run a flow programmatically by creating an instance of your flow class and calling the `kickoff()` method:
```python
flow = ExampleFlow()
result = flow.kickoff()
```
### Using the CLI
Starting from version 0.103.0, you can run flows using the `crewai run` command:
```shell
crewai run
```
This command automatically detects if your project is a flow (based on the `type = "flow"` setting in your pyproject.toml) and runs it accordingly. This is the recommended way to run flows from the command line.
For backward compatibility, you can also use:
```shell
crewai flow kickoff
```
However, the `crewai run` command is now the preferred method as it works for both crews and flows.
# Knowledge
Source: https://docs.crewai.com/concepts/knowledge
What is knowledge in CrewAI and how to use it.
## What is Knowledge?
Knowledge in CrewAI is a powerful system that allows AI agents to access and utilize external information sources during their tasks.
Think of it as giving your agents a reference library they can consult while working.
Key benefits of using Knowledge:
* Enhance agents with domain-specific information
* Support decisions with real-world data
* Maintain context across conversations
* Ground responses in factual information
## Supported Knowledge Sources
CrewAI supports various types of knowledge sources out of the box:
* Raw strings
* Text files (.txt)
* PDF documents
* CSV files
* Excel spreadsheets
* JSON documents
## Supported Knowledge Parameters
| Parameter | Type | Required | Description |
| :---------------- | :------------------------------ | :------- | :------------------------------------------------------------------------------------------------------------------------------------------------ |
| `sources` | **List\[BaseKnowledgeSource]** | Yes | List of knowledge sources that provide content to be stored and queried. Can include PDF, CSV, Excel, JSON, text files, or string content. |
| `collection_name` | **str** | No | Name of the collection where the knowledge will be stored. Used to identify different sets of knowledge. Defaults to "knowledge" if not provided. |
| `storage` | **Optional\[KnowledgeStorage]** | No | Custom storage configuration for managing how the knowledge is stored and retrieved. If not provided, a default storage will be created. |
## Quickstart Example
For file-Based Knowledge Sources, make sure to place your files in a `knowledge` directory at the root of your project.
Also, use relative paths from the `knowledge` directory when creating the source.
Here's an example using string-based knowledge:
```python Code
from crewai import Agent, Task, Crew, Process, LLM
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
# Create a knowledge source
content = "Users name is John. He is 30 years old and lives in San Francisco."
string_source = StringKnowledgeSource(
content=content,
)
# Create an LLM with a temperature of 0 to ensure deterministic outputs
llm = LLM(model="gpt-4o-mini", temperature=0)
# Create an agent with the knowledge store
agent = Agent(
role="About User",
goal="You know everything about the user.",
backstory="""You are a master at understanding people and their preferences.""",
verbose=True,
allow_delegation=False,
llm=llm,
)
task = Task(
description="Answer the following questions about the user: {question}",
expected_output="An answer to the question.",
agent=agent,
)
crew = Crew(
agents=[agent],
tasks=[task],
verbose=True,
process=Process.sequential,
knowledge_sources=[string_source], # Enable knowledge by adding the sources here. You can also add more sources to the sources list.
)
result = crew.kickoff(inputs={"question": "What city does John live in and how old is he?"})
```
Here's another example with the `CrewDoclingSource`. The CrewDoclingSource is actually quite versatile and can handle multiple file formats including MD, PDF, DOCX, HTML, and more.
You need to install `docling` for the following example to work: `uv add docling`
```python Code
from crewai import LLM, Agent, Crew, Process, Task
from crewai.knowledge.source.crew_docling_source import CrewDoclingSource
# Create a knowledge source
content_source = CrewDoclingSource(
file_paths=[
"https://lilianweng.github.io/posts/2024-11-28-reward-hacking",
"https://lilianweng.github.io/posts/2024-07-07-hallucination",
],
)
# Create an LLM with a temperature of 0 to ensure deterministic outputs
llm = LLM(model="gpt-4o-mini", temperature=0)
# Create an agent with the knowledge store
agent = Agent(
role="About papers",
goal="You know everything about the papers.",
backstory="""You are a master at understanding papers and their content.""",
verbose=True,
allow_delegation=False,
llm=llm,
)
task = Task(
description="Answer the following questions about the papers: {question}",
expected_output="An answer to the question.",
agent=agent,
)
crew = Crew(
agents=[agent],
tasks=[task],
verbose=True,
process=Process.sequential,
knowledge_sources=[
content_source
], # Enable knowledge by adding the sources here. You can also add more sources to the sources list.
)
result = crew.kickoff(
inputs={
"question": "What is the reward hacking paper about? Be sure to provide sources."
}
)
```
## More Examples
Here are examples of how to use different types of knowledge sources:
Note: Please ensure that you create the ./knowldge folder. All source files (e.g., .txt, .pdf, .xlsx, .json) should be placed in this folder for centralized management.
### Text File Knowledge Source
```python
from crewai.knowledge.source.text_file_knowledge_source import TextFileKnowledgeSource
# Create a text file knowledge source
text_source = TextFileKnowledgeSource(
file_paths=["document.txt", "another.txt"]
)
# Create crew with text file source on agents or crew level
agent = Agent(
...
knowledge_sources=[text_source]
)
crew = Crew(
...
knowledge_sources=[text_source]
)
```
### PDF Knowledge Source
```python
from crewai.knowledge.source.pdf_knowledge_source import PDFKnowledgeSource
# Create a PDF knowledge source
pdf_source = PDFKnowledgeSource(
file_paths=["document.pdf", "another.pdf"]
)
# Create crew with PDF knowledge source on agents or crew level
agent = Agent(
...
knowledge_sources=[pdf_source]
)
crew = Crew(
...
knowledge_sources=[pdf_source]
)
```
### CSV Knowledge Source
```python
from crewai.knowledge.source.csv_knowledge_source import CSVKnowledgeSource
# Create a CSV knowledge source
csv_source = CSVKnowledgeSource(
file_paths=["data.csv"]
)
# Create crew with CSV knowledge source or on agent level
agent = Agent(
...
knowledge_sources=[csv_source]
)
crew = Crew(
...
knowledge_sources=[csv_source]
)
```
### Excel Knowledge Source
```python
from crewai.knowledge.source.excel_knowledge_source import ExcelKnowledgeSource
# Create an Excel knowledge source
excel_source = ExcelKnowledgeSource(
file_paths=["spreadsheet.xlsx"]
)
# Create crew with Excel knowledge source on agents or crew level
agent = Agent(
...
knowledge_sources=[excel_source]
)
crew = Crew(
...
knowledge_sources=[excel_source]
)
```
### JSON Knowledge Source
```python
from crewai.knowledge.source.json_knowledge_source import JSONKnowledgeSource
# Create a JSON knowledge source
json_source = JSONKnowledgeSource(
file_paths=["data.json"]
)
# Create crew with JSON knowledge source on agents or crew level
agent = Agent(
...
knowledge_sources=[json_source]
)
crew = Crew(
...
knowledge_sources=[json_source]
)
```
## Knowledge Configuration
### Chunking Configuration
Knowledge sources automatically chunk content for better processing.
You can configure chunking behavior in your knowledge sources:
```python
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
source = StringKnowledgeSource(
content="Your content here",
chunk_size=4000, # Maximum size of each chunk (default: 4000)
chunk_overlap=200 # Overlap between chunks (default: 200)
)
```
The chunking configuration helps in:
* Breaking down large documents into manageable pieces
* Maintaining context through chunk overlap
* Optimizing retrieval accuracy
### Embeddings Configuration
You can also configure the embedder for the knowledge store.
This is useful if you want to use a different embedder for the knowledge store than the one used for the agents.
The `embedder` parameter supports various embedding model providers that include:
* `openai`: OpenAI's embedding models
* `google`: Google's text embedding models
* `azure`: Azure OpenAI embeddings
* `ollama`: Local embeddings with Ollama
* `vertexai`: Google Cloud VertexAI embeddings
* `cohere`: Cohere's embedding models
* `voyageai`: VoyageAI's embedding models
* `bedrock`: AWS Bedrock embeddings
* `huggingface`: Hugging Face models
* `watson`: IBM Watson embeddings
Here's an example of how to configure the embedder for the knowledge store using Google's `text-embedding-004` model:
```python Example
from crewai import Agent, Task, Crew, Process, LLM
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
import os
# Get the GEMINI API key
GEMINI_API_KEY = os.environ.get("GEMINI_API_KEY")
# Create a knowledge source
content = "Users name is John. He is 30 years old and lives in San Francisco."
string_source = StringKnowledgeSource(
content=content,
)
# Create an LLM with a temperature of 0 to ensure deterministic outputs
gemini_llm = LLM(
model="gemini/gemini-1.5-pro-002",
api_key=GEMINI_API_KEY,
temperature=0,
)
# Create an agent with the knowledge store
agent = Agent(
role="About User",
goal="You know everything about the user.",
backstory="""You are a master at understanding people and their preferences.""",
verbose=True,
allow_delegation=False,
llm=gemini_llm,
embedder={
"provider": "google",
"config": {
"model": "models/text-embedding-004",
"api_key": GEMINI_API_KEY,
}
}
)
task = Task(
description="Answer the following questions about the user: {question}",
expected_output="An answer to the question.",
agent=agent,
)
crew = Crew(
agents=[agent],
tasks=[task],
verbose=True,
process=Process.sequential,
knowledge_sources=[string_source],
embedder={
"provider": "google",
"config": {
"model": "models/text-embedding-004",
"api_key": GEMINI_API_KEY,
}
}
)
result = crew.kickoff(inputs={"question": "What city does John live in and how old is he?"})
```
```text Output
# Agent: About User
## Task: Answer the following questions about the user: What city does John live in and how old is he?
# Agent: About User
## Final Answer:
John is 30 years old and lives in San Francisco.
```
## Clearing Knowledge
If you need to clear the knowledge stored in CrewAI, you can use the `crewai reset-memories` command with the `--knowledge` option.
```bash Command
crewai reset-memories --knowledge
```
This is useful when you've updated your knowledge sources and want to ensure that the agents are using the most recent information.
## Agent-Specific Knowledge
While knowledge can be provided at the crew level using `crew.knowledge_sources`, individual agents can also have their own knowledge sources using the `knowledge_sources` parameter:
```python Code
from crewai import Agent, Task, Crew
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
# Create agent-specific knowledge about a product
product_specs = StringKnowledgeSource(
content="""The XPS 13 laptop features:
- 13.4-inch 4K display
- Intel Core i7 processor
- 16GB RAM
- 512GB SSD storage
- 12-hour battery life""",
metadata={"category": "product_specs"}
)
# Create a support agent with product knowledge
support_agent = Agent(
role="Technical Support Specialist",
goal="Provide accurate product information and support.",
backstory="You are an expert on our laptop products and specifications.",
knowledge_sources=[product_specs] # Agent-specific knowledge
)
# Create a task that requires product knowledge
support_task = Task(
description="Answer this customer question: {question}",
agent=support_agent
)
# Create and run the crew
crew = Crew(
agents=[support_agent],
tasks=[support_task]
)
# Get answer about the laptop's specifications
result = crew.kickoff(
inputs={"question": "What is the storage capacity of the XPS 13?"}
)
```
Benefits of agent-specific knowledge:
* Give agents specialized information for their roles
* Maintain separation of concerns between agents
* Combine with crew-level knowledge for layered information access
## Custom Knowledge Sources
CrewAI allows you to create custom knowledge sources for any type of data by extending the `BaseKnowledgeSource` class. Let's create a practical example that fetches and processes space news articles.
#### Space News Knowledge Source Example
```python Code
from crewai import Agent, Task, Crew, Process, LLM
from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
import requests
from datetime import datetime
from typing import Dict, Any
from pydantic import BaseModel, Field
class SpaceNewsKnowledgeSource(BaseKnowledgeSource):
"""Knowledge source that fetches data from Space News API."""
api_endpoint: str = Field(description="API endpoint URL")
limit: int = Field(default=10, description="Number of articles to fetch")
def load_content(self) -> Dict[Any, str]:
"""Fetch and format space news articles."""
try:
response = requests.get(
f"{self.api_endpoint}?limit={self.limit}"
)
response.raise_for_status()
data = response.json()
articles = data.get('results', [])
formatted_data = self.validate_content(articles)
return {self.api_endpoint: formatted_data}
except Exception as e:
raise ValueError(f"Failed to fetch space news: {str(e)}")
def validate_content(self, articles: list) -> str:
"""Format articles into readable text."""
formatted = "Space News Articles:\n\n"
for article in articles:
formatted += f"""
Title: {article['title']}
Published: {article['published_at']}
Summary: {article['summary']}
News Site: {article['news_site']}
URL: {article['url']}
-------------------"""
return formatted
def add(self) -> None:
"""Process and store the articles."""
content = self.load_content()
for _, text in content.items():
chunks = self._chunk_text(text)
self.chunks.extend(chunks)
self._save_documents()
# Create knowledge source
recent_news = SpaceNewsKnowledgeSource(
api_endpoint="https://api.spaceflightnewsapi.net/v4/articles",
limit=10,
)
# Create specialized agent
space_analyst = Agent(
role="Space News Analyst",
goal="Answer questions about space news accurately and comprehensively",
backstory="""You are a space industry analyst with expertise in space exploration,
satellite technology, and space industry trends. You excel at answering questions
about space news and providing detailed, accurate information.""",
knowledge_sources=[recent_news],
llm=LLM(model="gpt-4", temperature=0.0)
)
# Create task that handles user questions
analysis_task = Task(
description="Answer this question about space news: {user_question}",
expected_output="A detailed answer based on the recent space news articles",
agent=space_analyst
)
# Create and run the crew
crew = Crew(
agents=[space_analyst],
tasks=[analysis_task],
verbose=True,
process=Process.sequential
)
# Example usage
result = crew.kickoff(
inputs={"user_question": "What are the latest developments in space exploration?"}
)
```
```output Output
# Agent: Space News Analyst
## Task: Answer this question about space news: What are the latest developments in space exploration?
# Agent: Space News Analyst
## Final Answer:
The latest developments in space exploration, based on recent space news articles, include the following:
1. SpaceX has received the final regulatory approvals to proceed with the second integrated Starship/Super Heavy launch, scheduled for as soon as the morning of Nov. 17, 2023. This is a significant step in SpaceX's ambitious plans for space exploration and colonization. [Source: SpaceNews](https://spacenews.com/starship-cleared-for-nov-17-launch/)
2. SpaceX has also informed the US Federal Communications Commission (FCC) that it plans to begin launching its first next-generation Starlink Gen2 satellites. This represents a major upgrade to the Starlink satellite internet service, which aims to provide high-speed internet access worldwide. [Source: Teslarati](https://www.teslarati.com/spacex-first-starlink-gen2-satellite-launch-2022/)
3. AI startup Synthetaic has raised $15 million in Series B funding. The company uses artificial intelligence to analyze data from space and air sensors, which could have significant applications in space exploration and satellite technology. [Source: SpaceNews](https://spacenews.com/ai-startup-synthetaic-raises-15-million-in-series-b-funding/)
4. The Space Force has formally established a unit within the U.S. Indo-Pacific Command, marking a permanent presence in the Indo-Pacific region. This could have significant implications for space security and geopolitics. [Source: SpaceNews](https://spacenews.com/space-force-establishes-permanent-presence-in-indo-pacific-region/)
5. Slingshot Aerospace, a space tracking and data analytics company, is expanding its network of ground-based optical telescopes to increase coverage of low Earth orbit. This could improve our ability to track and analyze objects in low Earth orbit, including satellites and space debris. [Source: SpaceNews](https://spacenews.com/slingshots-space-tracking-network-to-extend-coverage-of-low-earth-orbit/)
6. The National Natural Science Foundation of China has outlined a five-year project for researchers to study the assembly of ultra-large spacecraft. This could lead to significant advancements in spacecraft technology and space exploration capabilities. [Source: SpaceNews](https://spacenews.com/china-researching-challenges-of-kilometer-scale-ultra-large-spacecraft/)
7. The Center for AEroSpace Autonomy Research (CAESAR) at Stanford University is focusing on spacecraft autonomy. The center held a kickoff event on May 22, 2024, to highlight the industry, academia, and government collaboration it seeks to foster. This could lead to significant advancements in autonomous spacecraft technology. [Source: SpaceNews](https://spacenews.com/stanford-center-focuses-on-spacecraft-autonomy/)
```
#### Key Components Explained
1. **Custom Knowledge Source (`SpaceNewsKnowledgeSource`)**:
* Extends `BaseKnowledgeSource` for integration with CrewAI
* Configurable API endpoint and article limit
* Implements three key methods:
* `load_content()`: Fetches articles from the API
* `_format_articles()`: Structures the articles into readable text
* `add()`: Processes and stores the content
2. **Agent Configuration**:
* Specialized role as a Space News Analyst
* Uses the knowledge source to access space news
3. **Task Setup**:
* Takes a user question as input through `{user_question}`
* Designed to provide detailed answers based on the knowledge source
4. **Crew Orchestration**:
* Manages the workflow between agent and task
* Handles input/output through the kickoff method
This example demonstrates how to:
* Create a custom knowledge source that fetches real-time data
* Process and format external data for AI consumption
* Use the knowledge source to answer specific user questions
* Integrate everything seamlessly with CrewAI's agent system
#### About the Spaceflight News API
The example uses the [Spaceflight News API](https://api.spaceflightnewsapi.net/v4/docs/), which:
* Provides free access to space-related news articles
* Requires no authentication
* Returns structured data about space news
* Supports pagination and filtering
You can customize the API query by modifying the endpoint URL:
```python
# Fetch more articles
recent_news = SpaceNewsKnowledgeSource(
api_endpoint="https://api.spaceflightnewsapi.net/v4/articles",
limit=20, # Increase the number of articles
)
# Add search parameters
recent_news = SpaceNewsKnowledgeSource(
api_endpoint="https://api.spaceflightnewsapi.net/v4/articles?search=NASA", # Search for NASA news
limit=10,
)
```
## Best Practices
* Keep chunk sizes appropriate for your content type
* Consider content overlap for context preservation
* Organize related information into separate knowledge sources
* Adjust chunk sizes based on content complexity
* Configure appropriate embedding models
* Consider using local embedding providers for faster processing
# LLMs
Source: https://docs.crewai.com/concepts/llms
A comprehensive guide to configuring and using Large Language Models (LLMs) in your CrewAI projects
CrewAI integrates with multiple LLM providers through LiteLLM, giving you the flexibility to choose the right model for your specific use case. This guide will help you understand how to configure and use different LLM providers in your CrewAI projects.
## What are LLMs?
Large Language Models (LLMs) are the core intelligence behind CrewAI agents. They enable agents to understand context, make decisions, and generate human-like responses. Here's what you need to know:
Large Language Models are AI systems trained on vast amounts of text data. They power the intelligence of your CrewAI agents, enabling them to understand and generate human-like text.
The context window determines how much text an LLM can process at once. Larger windows (e.g., 128K tokens) allow for more context but may be more expensive and slower.
Temperature (0.0 to 1.0) controls response randomness. Lower values (e.g., 0.2) produce more focused, deterministic outputs, while higher values (e.g., 0.8) increase creativity and variability.
Each LLM provider (e.g., OpenAI, Anthropic, Google) offers different models with varying capabilities, pricing, and features. Choose based on your needs for accuracy, speed, and cost.
## Setting Up Your LLM
There are three ways to configure LLMs in CrewAI. Choose the method that best fits your workflow:
The simplest way to get started. Set these variables in your environment:
```bash
# Required: Your API key for authentication
OPENAI_API_KEY=
# Optional: Default model selection
OPENAI_MODEL_NAME=gpt-4o-mini # Default if not set
# Optional: Organization ID (if applicable)
OPENAI_ORGANIZATION_ID=
```
Never commit API keys to version control. Use environment files (.env) or your system's secret management.
Create a YAML file to define your agent configurations. This method is great for version control and team collaboration:
```yaml
researcher:
role: Research Specialist
goal: Conduct comprehensive research and analysis
backstory: A dedicated research professional with years of experience
verbose: true
llm: openai/gpt-4o-mini # your model here
# (see provider configuration examples below for more)
```
The YAML configuration allows you to:
* Version control your agent settings
* Easily switch between different models
* Share configurations across team members
* Document model choices and their purposes
For maximum flexibility, configure LLMs directly in your Python code:
```python
from crewai import LLM
# Basic configuration
llm = LLM(model="gpt-4")
# Advanced configuration with detailed parameters
llm = LLM(
model="gpt-4o-mini",
temperature=0.7, # Higher for more creative outputs
timeout=120, # Seconds to wait for response
max_tokens=4000, # Maximum length of response
top_p=0.9, # Nucleus sampling parameter
frequency_penalty=0.1, # Reduce repetition
presence_penalty=0.1, # Encourage topic diversity
response_format={"type": "json"}, # For structured outputs
seed=42 # For reproducible results
)
```
Parameter explanations:
* `temperature`: Controls randomness (0.0-1.0)
* `timeout`: Maximum wait time for response
* `max_tokens`: Limits response length
* `top_p`: Alternative to temperature for sampling
* `frequency_penalty`: Reduces word repetition
* `presence_penalty`: Encourages new topics
* `response_format`: Specifies output structure
* `seed`: Ensures consistent outputs
## Provider Configuration Examples
CrewAI supports a multitude of LLM providers, each offering unique features, authentication methods, and model capabilities.
In this section, you'll find detailed examples that help you select, configure, and optimize the LLM that best fits your project's needs.
Set the following environment variables in your `.env` file:
```toml Code
# Required
OPENAI_API_KEY=sk-...
# Optional
OPENAI_API_BASE=
OPENAI_ORGANIZATION=
```
Example usage in your CrewAI project:
```python Code
from crewai import LLM
llm = LLM(
model="openai/gpt-4", # call model by provider/model_name
temperature=0.8,
max_tokens=150,
top_p=0.9,
frequency_penalty=0.1,
presence_penalty=0.1,
stop=["END"],
seed=42
)
```
OpenAI is one of the leading providers of LLMs with a wide range of models and features.
| Model | Context Window | Best For |
| -------------------- | -------------- | --------------------------------------- |
| GPT-4 | 8,192 tokens | High-accuracy tasks, complex reasoning |
| GPT-4 Turbo | 128,000 tokens | Long-form content, document analysis |
| GPT-4o & GPT-4o-mini | 128,000 tokens | Cost-effective large context processing |
| o3-mini | 200,000 tokens | Fast reasoning, complex reasoning |
| o1-mini | 128,000 tokens | Fast reasoning, complex reasoning |
| o1-preview | 128,000 tokens | Fast reasoning, complex reasoning |
| o1 | 200,000 tokens | Fast reasoning, complex reasoning |
```toml Code
# Required
ANTHROPIC_API_KEY=sk-ant-...
# Optional
ANTHROPIC_API_BASE=
```
Example usage in your CrewAI project:
```python Code
llm = LLM(
model="anthropic/claude-3-sonnet-20240229-v1:0",
temperature=0.7
)
```
Set the following environment variables in your `.env` file:
```toml Code
# Option 1: Gemini accessed with an API key.
# https://ai.google.dev/gemini-api/docs/api-key
GEMINI_API_KEY=
# Option 2: Vertex AI IAM credentials for Gemini, Anthropic, and Model Garden.
# https://cloud.google.com/vertex-ai/generative-ai/docs/overview
```
Get credentials from your Google Cloud Console and save it to a JSON file with the following code:
```python Code
import json
file_path = 'path/to/vertex_ai_service_account.json'
# Load the JSON file
with open(file_path, 'r') as file:
vertex_credentials = json.load(file)
# Convert the credentials to a JSON string
vertex_credentials_json = json.dumps(vertex_credentials)
```
Example usage in your CrewAI project:
```python Code
from crewai import LLM
llm = LLM(
model="gemini/gemini-1.5-pro-latest",
temperature=0.7,
vertex_credentials=vertex_credentials_json
)
```
Google offers a range of powerful models optimized for different use cases:
| Model | Context Window | Best For |
| -------------------- | -------------- | ---------------------------------------------------------------------------------------------------------------- |
| gemini-2.0-flash-exp | 1M tokens | Higher quality at faster speed, multimodal model, good for most tasks |
| gemini-1.5-flash | 1M tokens | Balanced multimodal model, good for most tasks |
| gemini-1.5-flash-8B | 1M tokens | Fastest, most cost-efficient, good for high-frequency tasks |
| gemini-1.5-pro | 2M tokens | Best performing, wide variety of reasoning tasks including logical reasoning, coding, and creative collaboration |
```toml Code
# Required
AZURE_API_KEY=
AZURE_API_BASE=
AZURE_API_VERSION=
# Optional
AZURE_AD_TOKEN=
AZURE_API_TYPE=
```
Example usage in your CrewAI project:
```python Code
llm = LLM(
model="azure/gpt-4",
api_version="2023-05-15"
)
```
```toml Code
AWS_ACCESS_KEY_ID=
AWS_SECRET_ACCESS_KEY=
AWS_DEFAULT_REGION=
```
Example usage in your CrewAI project:
```python Code
llm = LLM(
model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
)
```
Before using Amazon Bedrock, make sure you have boto3 installed in your environment
[Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-regions.html) is a managed service that provides access to multiple foundation models from top AI companies through a unified API, enabling secure and responsible AI application development.
| Model | Context Window | Best For |
| ----------------------- | ------------------ | ------------------------------------------------------------------------------------------------------------------------------------- |
| Amazon Nova Pro | Up to 300k tokens | High-performance, model balancing accuracy, speed, and cost-effectiveness across diverse tasks. |
| Amazon Nova Micro | Up to 128k tokens | High-performance, cost-effective text-only model optimized for lowest latency responses. |
| Amazon Nova Lite | Up to 300k tokens | High-performance, affordable multimodal processing for images, video, and text with real-time capabilities. |
| Claude 3.7 Sonnet | Up to 128k tokens | High-performance, best for complex reasoning, coding & AI agents |
| Claude 3.5 Sonnet v2 | Up to 200k tokens | State-of-the-art model specialized in software engineering, agentic capabilities, and computer interaction at optimized cost. |
| Claude 3.5 Sonnet | Up to 200k tokens | High-performance model delivering superior intelligence and reasoning across diverse tasks with optimal speed-cost balance. |
| Claude 3.5 Haiku | Up to 200k tokens | Fast, compact multimodal model optimized for quick responses and seamless human-like interactions |
| Claude 3 Sonnet | Up to 200k tokens | Multimodal model balancing intelligence and speed for high-volume deployments. |
| Claude 3 Haiku | Up to 200k tokens | Compact, high-speed multimodal model optimized for quick responses and natural conversational interactions |
| Claude 3 Opus | Up to 200k tokens | Most advanced multimodal model exceling at complex tasks with human-like reasoning and superior contextual understanding. |
| Claude 2.1 | Up to 200k tokens | Enhanced version with expanded context window, improved reliability, and reduced hallucinations for long-form and RAG applications |
| Claude | Up to 100k tokens | Versatile model excelling in sophisticated dialogue, creative content, and precise instruction following. |
| Claude Instant | Up to 100k tokens | Fast, cost-effective model for everyday tasks like dialogue, analysis, summarization, and document Q\&A |
| Llama 3.1 405B Instruct | Up to 128k tokens | Advanced LLM for synthetic data generation, distillation, and inference for chatbots, coding, and domain-specific tasks. |
| Llama 3.1 70B Instruct | Up to 128k tokens | Powers complex conversations with superior contextual understanding, reasoning and text generation. |
| Llama 3.1 8B Instruct | Up to 128k tokens | Advanced state-of-the-art model with language understanding, superior reasoning, and text generation. |
| Llama 3 70B Instruct | Up to 8k tokens | Powers complex conversations with superior contextual understanding, reasoning and text generation. |
| Llama 3 8B Instruct | Up to 8k tokens | Advanced state-of-the-art LLM with language understanding, superior reasoning, and text generation. |
| Titan Text G1 - Lite | Up to 4k tokens | Lightweight, cost-effective model optimized for English tasks and fine-tuning with focus on summarization and content generation. |
| Titan Text G1 - Express | Up to 8k tokens | Versatile model for general language tasks, chat, and RAG applications with support for English and 100+ languages. |
| Cohere Command | Up to 4k tokens | Model specialized in following user commands and delivering practical enterprise solutions. |
| Jurassic-2 Mid | Up to 8,191 tokens | Cost-effective model balancing quality and affordability for diverse language tasks like Q\&A, summarization, and content generation. |
| Jurassic-2 Ultra | Up to 8,191 tokens | Model for advanced text generation and comprehension, excelling in complex tasks like analysis and content creation. |
| Jamba-Instruct | Up to 256k tokens | Model with extended context window optimized for cost-effective text generation, summarization, and Q\&A. |
| Mistral 7B Instruct | Up to 32k tokens | This LLM follows instructions, completes requests, and generates creative text. |
| Mistral 8x7B Instruct | Up to 32k tokens | An MOE LLM that follows instructions, completes requests, and generates creative text. |
```toml Code
AWS_ACCESS_KEY_ID=
AWS_SECRET_ACCESS_KEY=
AWS_DEFAULT_REGION=
```
Example usage in your CrewAI project:
```python Code
llm = LLM(
model="sagemaker/"
)
```
Set the following environment variables in your `.env` file:
```toml Code
MISTRAL_API_KEY=
```
Example usage in your CrewAI project:
```python Code
llm = LLM(
model="mistral/mistral-large-latest",
temperature=0.7
)
```
Set the following environment variables in your `.env` file:
```toml Code
NVIDIA_API_KEY=
```
Example usage in your CrewAI project:
```python Code
llm = LLM(
model="nvidia_nim/meta/llama3-70b-instruct",
temperature=0.7
)
```
Nvidia NIM provides a comprehensive suite of models for various use cases, from general-purpose tasks to specialized applications.
| Model | Context Window | Best For |
| ------------------------------------------- | -------------- | --------------------------------------------------------------------------------------------------------------------------- |
| nvidia/mistral-nemo-minitron-8b-8k-instruct | 8,192 tokens | State-of-the-art small language model delivering superior accuracy for chatbot, virtual assistants, and content generation. |
| nvidia/nemotron-4-mini-hindi-4b-instruct | 4,096 tokens | A bilingual Hindi-English SLM for on-device inference, tailored specifically for Hindi Language. |
| nvidia/llama-3.1-nemotron-70b-instruct | 128k tokens | Customized for enhanced helpfulness in responses |
| nvidia/llama3-chatqa-1.5-8b | 128k tokens | Advanced LLM to generate high-quality, context-aware responses for chatbots and search engines. |
| nvidia/llama3-chatqa-1.5-70b | 128k tokens | Advanced LLM to generate high-quality, context-aware responses for chatbots and search engines. |
| nvidia/vila | 128k tokens | Multi-modal vision-language model that understands text/img/video and creates informative responses |
| nvidia/neva-22 | 4,096 tokens | Multi-modal vision-language model that understands text/images and generates informative responses |
| nvidia/nemotron-mini-4b-instruct | 8,192 tokens | General-purpose tasks |
| nvidia/usdcode-llama3-70b-instruct | 128k tokens | State-of-the-art LLM that answers OpenUSD knowledge queries and generates USD-Python code. |
| nvidia/nemotron-4-340b-instruct | 4,096 tokens | Creates diverse synthetic data that mimics the characteristics of real-world data. |
| meta/codellama-70b | 100k tokens | LLM capable of generating code from natural language and vice versa. |
| meta/llama2-70b | 4,096 tokens | Cutting-edge large language AI model capable of generating text and code in response to prompts. |
| meta/llama3-8b-instruct | 8,192 tokens | Advanced state-of-the-art LLM with language understanding, superior reasoning, and text generation. |
| meta/llama3-70b-instruct | 8,192 tokens | Powers complex conversations with superior contextual understanding, reasoning and text generation. |
| meta/llama-3.1-8b-instruct | 128k tokens | Advanced state-of-the-art model with language understanding, superior reasoning, and text generation. |
| meta/llama-3.1-70b-instruct | 128k tokens | Powers complex conversations with superior contextual understanding, reasoning and text generation. |
| meta/llama-3.1-405b-instruct | 128k tokens | Advanced LLM for synthetic data generation, distillation, and inference for chatbots, coding, and domain-specific tasks. |
| meta/llama-3.2-1b-instruct | 128k tokens | Advanced state-of-the-art small language model with language understanding, superior reasoning, and text generation. |
| meta/llama-3.2-3b-instruct | 128k tokens | Advanced state-of-the-art small language model with language understanding, superior reasoning, and text generation. |
| meta/llama-3.2-11b-vision-instruct | 128k tokens | Advanced state-of-the-art small language model with language understanding, superior reasoning, and text generation. |
| meta/llama-3.2-90b-vision-instruct | 128k tokens | Advanced state-of-the-art small language model with language understanding, superior reasoning, and text generation. |
| google/gemma-7b | 8,192 tokens | Cutting-edge text generation model text understanding, transformation, and code generation. |
| google/gemma-2b | 8,192 tokens | Cutting-edge text generation model text understanding, transformation, and code generation. |
| google/codegemma-7b | 8,192 tokens | Cutting-edge model built on Google's Gemma-7B specialized for code generation and code completion. |
| google/codegemma-1.1-7b | 8,192 tokens | Advanced programming model for code generation, completion, reasoning, and instruction following. |
| google/recurrentgemma-2b | 8,192 tokens | Novel recurrent architecture based language model for faster inference when generating long sequences. |
| google/gemma-2-9b-it | 8,192 tokens | Cutting-edge text generation model text understanding, transformation, and code generation. |
| google/gemma-2-27b-it | 8,192 tokens | Cutting-edge text generation model text understanding, transformation, and code generation. |
| google/gemma-2-2b-it | 8,192 tokens | Cutting-edge text generation model text understanding, transformation, and code generation. |
| google/deplot | 512 tokens | One-shot visual language understanding model that translates images of plots into tables. |
| google/paligemma | 8,192 tokens | Vision language model adept at comprehending text and visual inputs to produce informative responses. |
| mistralai/mistral-7b-instruct-v0.2 | 32k tokens | This LLM follows instructions, completes requests, and generates creative text. |
| mistralai/mixtral-8x7b-instruct-v0.1 | 8,192 tokens | An MOE LLM that follows instructions, completes requests, and generates creative text. |
| mistralai/mistral-large | 4,096 tokens | Creates diverse synthetic data that mimics the characteristics of real-world data. |
| mistralai/mixtral-8x22b-instruct-v0.1 | 8,192 tokens | Creates diverse synthetic data that mimics the characteristics of real-world data. |
| mistralai/mistral-7b-instruct-v0.3 | 32k tokens | This LLM follows instructions, completes requests, and generates creative text. |
| nv-mistralai/mistral-nemo-12b-instruct | 128k tokens | Most advanced language model for reasoning, code, multilingual tasks; runs on a single GPU. |
| mistralai/mamba-codestral-7b-v0.1 | 256k tokens | Model for writing and interacting with code across a wide range of programming languages and tasks. |
| microsoft/phi-3-mini-128k-instruct | 128K tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. |
| microsoft/phi-3-mini-4k-instruct | 4,096 tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. |
| microsoft/phi-3-small-8k-instruct | 8,192 tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. |
| microsoft/phi-3-small-128k-instruct | 128K tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. |
| microsoft/phi-3-medium-4k-instruct | 4,096 tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. |
| microsoft/phi-3-medium-128k-instruct | 128K tokens | Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills. |
| microsoft/phi-3.5-mini-instruct | 128K tokens | Lightweight multilingual LLM powering AI applications in latency bound, memory/compute constrained environments |
| microsoft/phi-3.5-moe-instruct | 128K tokens | Advanced LLM based on Mixture of Experts architecure to deliver compute efficient content generation |
| microsoft/kosmos-2 | 1,024 tokens | Groundbreaking multimodal model designed to understand and reason about visual elements in images. |
| microsoft/phi-3-vision-128k-instruct | 128k tokens | Cutting-edge open multimodal model exceling in high-quality reasoning from images. |
| microsoft/phi-3.5-vision-instruct | 128k tokens | Cutting-edge open multimodal model exceling in high-quality reasoning from images. |
| databricks/dbrx-instruct | 12k tokens | A general-purpose LLM with state-of-the-art performance in language understanding, coding, and RAG. |
| snowflake/arctic | 1,024 tokens | Delivers high efficiency inference for enterprise applications focused on SQL generation and coding. |
| aisingapore/sea-lion-7b-instruct | 4,096 tokens | LLM to represent and serve the linguistic and cultural diversity of Southeast Asia |
| ibm/granite-8b-code-instruct | 4,096 tokens | Software programming LLM for code generation, completion, explanation, and multi-turn conversion. |
| ibm/granite-34b-code-instruct | 8,192 tokens | Software programming LLM for code generation, completion, explanation, and multi-turn conversion. |
| ibm/granite-3.0-8b-instruct | 4,096 tokens | Advanced Small Language Model supporting RAG, summarization, classification, code, and agentic AI |
| ibm/granite-3.0-3b-a800m-instruct | 4,096 tokens | Highly efficient Mixture of Experts model for RAG, summarization, entity extraction, and classification |
| mediatek/breeze-7b-instruct | 4,096 tokens | Creates diverse synthetic data that mimics the characteristics of real-world data. |
| upstage/solar-10.7b-instruct | 4,096 tokens | Excels in NLP tasks, particularly in instruction-following, reasoning, and mathematics. |
| writer/palmyra-med-70b-32k | 32k tokens | Leading LLM for accurate, contextually relevant responses in the medical domain. |
| writer/palmyra-med-70b | 32k tokens | Leading LLM for accurate, contextually relevant responses in the medical domain. |
| writer/palmyra-fin-70b-32k | 32k tokens | Specialized LLM for financial analysis, reporting, and data processing |
| 01-ai/yi-large | 32k tokens | Powerful model trained on English and Chinese for diverse tasks including chatbot and creative writing. |
| deepseek-ai/deepseek-coder-6.7b-instruct | 2k tokens | Powerful coding model offering advanced capabilities in code generation, completion, and infilling |
| rakuten/rakutenai-7b-instruct | 1,024 tokens | Advanced state-of-the-art LLM with language understanding, superior reasoning, and text generation. |
| rakuten/rakutenai-7b-chat | 1,024 tokens | Advanced state-of-the-art LLM with language understanding, superior reasoning, and text generation. |
| baichuan-inc/baichuan2-13b-chat | 4,096 tokens | Support Chinese and English chat, coding, math, instruction following, solving quizzes |
NVIDIA NIM enables you to run powerful LLMs locally on your Windows machine using WSL2 (Windows Subsystem for Linux).
This approach allows you to leverage your NVIDIA GPU for private, secure, and cost-effective AI inference without relying on cloud services.
Perfect for development, testing, or production scenarios where data privacy or offline capabilities are required.
Here is a step-by-step guide to setting up a local NVIDIA NIM model:
1. Follow installation instructions from [NVIDIA Website](https://docs.nvidia.com/nim/wsl2/latest/getting-started.html)
2. Install the local model. For Llama 3.1-8b follow [instructions](https://build.nvidia.com/meta/llama-3_1-8b-instruct/deploy)
3. Configure your crewai local models:
```python Code
from crewai.llm import LLM
local_nvidia_nim_llm = LLM(
model="openai/meta/llama-3.1-8b-instruct", # it's an openai-api compatible model
base_url="http://localhost:8000/v1",
api_key="", # api_key is required, but you can use any text
)
# Then you can use it in your crew:
@CrewBase
class MyCrew():
# ...
@agent
def researcher(self) -> Agent:
return Agent(
config=self.agents_config['researcher'], # type: ignore[index]
llm=local_nvidia_nim_llm
)
# ...
```
Set the following environment variables in your `.env` file:
```toml Code
GROQ_API_KEY=
```
Example usage in your CrewAI project:
```python Code
llm = LLM(
model="groq/llama-3.2-90b-text-preview",
temperature=0.7
)
```
| Model | Context Window | Best For |
| ---------------- | -------------- | ------------------------------------- |
| Llama 3.1 70B/8B | 131,072 tokens | High-performance, large context tasks |
| Llama 3.2 Series | 8,192 tokens | General-purpose tasks |
| Mixtral 8x7B | 32,768 tokens | Balanced performance and context |
Set the following environment variables in your `.env` file:
```toml Code
# Required
WATSONX_URL=
WATSONX_APIKEY=
WATSONX_PROJECT_ID=
# Optional
WATSONX_TOKEN=
WATSONX_DEPLOYMENT_SPACE_ID=
```
Example usage in your CrewAI project:
```python Code
llm = LLM(
model="watsonx/meta-llama/llama-3-1-70b-instruct",
base_url="https://api.watsonx.ai/v1"
)
```
1. Install Ollama: [ollama.ai](https://ollama.ai/)
2. Run a model: `ollama run llama3`
3. Configure:
```python Code
llm = LLM(
model="ollama/llama3:70b",
base_url="http://localhost:11434"
)
```
Set the following environment variables in your `.env` file:
```toml Code
FIREWORKS_API_KEY=
```
Example usage in your CrewAI project:
```python Code
llm = LLM(
model="fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct",
temperature=0.7
)
```
Set the following environment variables in your `.env` file:
```toml Code
PERPLEXITY_API_KEY=
```
Example usage in your CrewAI project:
```python Code
llm = LLM(
model="llama-3.1-sonar-large-128k-online",
base_url="https://api.perplexity.ai/"
)
```
Set the following environment variables in your `.env` file:
```toml Code
HF_TOKEN=
```
Example usage in your CrewAI project:
```python Code
llm = LLM(
model="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct"
)
```
Set the following environment variables in your `.env` file:
```toml Code
SAMBANOVA_API_KEY=
```
Example usage in your CrewAI project:
```python Code
llm = LLM(
model="sambanova/Meta-Llama-3.1-8B-Instruct",
temperature=0.7
)
```
| Model | Context Window | Best For |
| ---------------- | -------------------- | ------------------------------------- |
| Llama 3.1 70B/8B | Up to 131,072 tokens | High-performance, large context tasks |
| Llama 3.1 405B | 8,192 tokens | High-performance and output quality |
| Llama 3.2 Series | 8,192 tokens | General-purpose, multimodal tasks |
| Llama 3.3 70B | Up to 131,072 tokens | High-performance and output quality |
| Qwen2 familly | 8,192 tokens | High-performance and output quality |
Set the following environment variables in your `.env` file:
```toml Code
# Required
CEREBRAS_API_KEY=
```
Example usage in your CrewAI project:
```python Code
llm = LLM(
model="cerebras/llama3.1-70b",
temperature=0.7,
max_tokens=8192
)
```
Cerebras features:
* Fast inference speeds
* Competitive pricing
* Good balance of speed and quality
* Support for long context windows
Set the following environment variables in your `.env` file:
```toml Code
OPENROUTER_API_KEY=
```
Example usage in your CrewAI project:
```python Code
llm = LLM(
model="openrouter/deepseek/deepseek-r1",
base_url="https://openrouter.ai/api/v1",
api_key=OPENROUTER_API_KEY
)
```
Open Router models:
* openrouter/deepseek/deepseek-r1
* openrouter/deepseek/deepseek-chat
## Streaming Responses
CrewAI supports streaming responses from LLMs, allowing your application to receive and process outputs in real-time as they're generated.
Enable streaming by setting the `stream` parameter to `True` when initializing your LLM:
```python
from crewai import LLM
# Create an LLM with streaming enabled
llm = LLM(
model="openai/gpt-4o",
stream=True # Enable streaming
)
```
When streaming is enabled, responses are delivered in chunks as they're generated, creating a more responsive user experience.
CrewAI emits events for each chunk received during streaming:
```python
from crewai import LLM
from crewai.utilities.events import EventHandler, LLMStreamChunkEvent
class MyEventHandler(EventHandler):
def on_llm_stream_chunk(self, event: LLMStreamChunkEvent):
# Process each chunk as it arrives
print(f"Received chunk: {event.chunk}")
# Register the event handler
from crewai.utilities.events import crewai_event_bus
crewai_event_bus.register_handler(MyEventHandler())
```
## Structured LLM Calls
CrewAI supports structured responses from LLM calls by allowing you to define a `response_format` using a Pydantic model. This enables the framework to automatically parse and validate the output, making it easier to integrate the response into your application without manual post-processing.
For example, you can define a Pydantic model to represent the expected response structure and pass it as the `response_format` when instantiating the LLM. The model will then be used to convert the LLM output into a structured Python object.
```python Code
from crewai import LLM
class Dog(BaseModel):
name: str
age: int
breed: str
llm = LLM(model="gpt-4o", response_format=Dog)
response = llm.call(
"Analyze the following messages and return the name, age, and breed. "
"Meet Kona! She is 3 years old and is a black german shepherd."
)
print(response)
# Output:
# Dog(name='Kona', age=3, breed='black german shepherd')
```
## Advanced Features and Optimization
Learn how to get the most out of your LLM configuration:
CrewAI includes smart context management features:
```python
from crewai import LLM
# CrewAI automatically handles:
# 1. Token counting and tracking
# 2. Content summarization when needed
# 3. Task splitting for large contexts
llm = LLM(
model="gpt-4",
max_tokens=4000, # Limit response length
)
```
Best practices for context management:
1. Choose models with appropriate context windows
2. Pre-process long inputs when possible
3. Use chunking for large documents
4. Monitor token usage to optimize costs
Choose the right context window for your task:
* Small tasks (up to 4K tokens): Standard models
* Medium tasks (between 4K-32K): Enhanced models
* Large tasks (over 32K): Large context models
```python
# Configure model with appropriate settings
llm = LLM(
model="openai/gpt-4-turbo-preview",
temperature=0.7, # Adjust based on task
max_tokens=4096, # Set based on output needs
timeout=300 # Longer timeout for complex tasks
)
```
* Lower temperature (0.1 to 0.3) for factual responses
* Higher temperature (0.7 to 0.9) for creative tasks
1. Monitor token usage
2. Implement rate limiting
3. Use caching when possible
4. Set appropriate max\_tokens limits
Remember to regularly monitor your token usage and adjust your configuration as needed to optimize costs and performance.
## Common Issues and Solutions
Most authentication issues can be resolved by checking API key format and environment variable names.
```bash
# OpenAI
OPENAI_API_KEY=sk-...
# Anthropic
ANTHROPIC_API_KEY=sk-ant-...
```
Always include the provider prefix in model names
```python
# Correct
llm = LLM(model="openai/gpt-4")
# Incorrect
llm = LLM(model="gpt-4")
```
Use larger context models for extensive tasks
```python
# Large context model
llm = LLM(model="openai/gpt-4o") # 128K tokens
```
# Memory
Source: https://docs.crewai.com/concepts/memory
Leveraging memory systems in the CrewAI framework to enhance agent capabilities.
## Introduction to Memory Systems in CrewAI
The crewAI framework introduces a sophisticated memory system designed to significantly enhance the capabilities of AI agents.
This system comprises `short-term memory`, `long-term memory`, `entity memory`, and `contextual memory`, each serving a unique purpose in aiding agents to remember,
reason, and learn from past interactions.
## Memory System Components
| Component | Description |
| :-------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Short-Term Memory** | Temporarily stores recent interactions and outcomes using `RAG`, enabling agents to recall and utilize information relevant to their current context during the current executions. |
| **Long-Term Memory** | Preserves valuable insights and learnings from past executions, allowing agents to build and refine their knowledge over time. |
| **Entity Memory** | Captures and organizes information about entities (people, places, concepts) encountered during tasks, facilitating deeper understanding and relationship mapping. Uses `RAG` for storing entity information. |
| **Contextual Memory** | Maintains the context of interactions by combining `ShortTermMemory`, `LongTermMemory`, and `EntityMemory`, aiding in the coherence and relevance of agent responses over a sequence of tasks or a conversation. |
| **External Memory** | Enables integration with external memory systems and providers (like Mem0), allowing for specialized memory storage and retrieval across different applications. Supports custom storage implementations for flexible memory management. |
| **User Memory** | ⚠️ **DEPRECATED**: This component is deprecated and will be removed in a future version. Please use [External Memory](#using-external-memory) instead. |
## How Memory Systems Empower Agents
1. **Contextual Awareness**: With short-term and contextual memory, agents gain the ability to maintain context over a conversation or task sequence, leading to more coherent and relevant responses.
2. **Experience Accumulation**: Long-term memory allows agents to accumulate experiences, learning from past actions to improve future decision-making and problem-solving.
3. **Entity Understanding**: By maintaining entity memory, agents can recognize and remember key entities, enhancing their ability to process and interact with complex information.
## Implementing Memory in Your Crew
When configuring a crew, you can enable and customize each memory component to suit the crew's objectives and the nature of tasks it will perform.
By default, the memory system is disabled, and you can ensure it is active by setting `memory=True` in the crew configuration.
The memory will use OpenAI embeddings by default, but you can change it by setting `embedder` to a different model.
It's also possible to initialize the memory instance with your own instance.
The 'embedder' only applies to **Short-Term Memory** which uses Chroma for RAG.
The **Long-Term Memory** uses SQLite3 to store task results. Currently, there is no way to override these storage implementations.
The data storage files are saved into a platform-specific location found using the appdirs package,
and the name of the project can be overridden using the **CREWAI\_STORAGE\_DIR** environment variable.
### Example: Configuring Memory for a Crew
```python Code
from crewai import Crew, Agent, Task, Process
# Assemble your crew with memory capabilities
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
verbose=True
)
```
### Example: Use Custom Memory Instances e.g FAISS as the VectorDB
```python Code
from crewai import Crew, Process
from crewai.memory import LongTermMemory, ShortTermMemory, EntityMemory
from crewai.memory.storage.rag_storage import RAGStorage
from crewai.memory.storage.ltm_sqlite_storage import LTMSQLiteStorage
from typing import List, Optional
# Assemble your crew with memory capabilities
my_crew: Crew = Crew(
agents = [...],
tasks = [...],
process = Process.sequential,
memory = True,
# Long-term memory for persistent storage across sessions
long_term_memory = LongTermMemory(
storage=LTMSQLiteStorage(
db_path="/my_crew1/long_term_memory_storage.db"
)
),
# Short-term memory for current context using RAG
short_term_memory = ShortTermMemory(
storage = RAGStorage(
embedder_config={
"provider": "openai",
"config": {
"model": 'text-embedding-3-small'
}
},
type="short_term",
path="/my_crew1/"
)
),
),
# Entity memory for tracking key information about entities
entity_memory = EntityMemory(
storage=RAGStorage(
embedder_config={
"provider": "openai",
"config": {
"model": 'text-embedding-3-small'
}
},
type="short_term",
path="/my_crew1/"
)
),
verbose=True,
)
```
## Security Considerations
When configuring memory storage:
* Use environment variables for storage paths (e.g., `CREWAI_STORAGE_DIR`)
* Never hardcode sensitive information like database credentials
* Consider access permissions for storage directories
* Use relative paths when possible to maintain portability
Example using environment variables:
```python
import os
from crewai import Crew
from crewai.memory import LongTermMemory
from crewai.memory.storage.ltm_sqlite_storage import LTMSQLiteStorage
# Configure storage path using environment variable
storage_path = os.getenv("CREWAI_STORAGE_DIR", "./storage")
crew = Crew(
memory=True,
long_term_memory=LongTermMemory(
storage=LTMSQLiteStorage(
db_path="{storage_path}/memory.db".format(storage_path=storage_path)
)
)
)
```
## Configuration Examples
### Basic Memory Configuration
```python
from crewai import Crew
from crewai.memory import LongTermMemory
# Simple memory configuration
crew = Crew(memory=True) # Uses default storage locations
```
Note that External Memory won’t be defined when `memory=True` is set, as we can’t infer which external memory would be suitable for your case
### Custom Storage Configuration
```python
from crewai import Crew
from crewai.memory import LongTermMemory
from crewai.memory.storage.ltm_sqlite_storage import LTMSQLiteStorage
# Configure custom storage paths
crew = Crew(
memory=True,
long_term_memory=LongTermMemory(
storage=LTMSQLiteStorage(db_path="./memory.db")
)
)
```
## Integrating Mem0 for Enhanced User Memory
[Mem0](https://mem0.ai/) is a self-improving memory layer for LLM applications, enabling personalized AI experiences.
### Using Mem0 API platform
To include user-specific memory you can get your API key [here](https://app.mem0.ai/dashboard/api-keys) and refer the [docs](https://docs.mem0.ai/platform/quickstart#4-1-create-memories) for adding user preferences. In this case `user_memory` is set to `MemoryClient` from mem0.
```python Code
import os
from crewai import Crew, Process
from mem0 import MemoryClient
# Set environment variables for Mem0
os.environ["MEM0_API_KEY"] = "m0-xx"
# Step 1: Create a Crew with User Memory
crew = Crew(
agents=[...],
tasks=[...],
verbose=True,
process=Process.sequential,
memory=True,
memory_config={
"provider": "mem0",
"config": {"user_id": "john"},
"user_memory" : {} #Set user_memory explicitly to a dictionary, we are working on this issue.
},
)
```
#### Additional Memory Configuration Options
If you want to access a specific organization and project, you can set the `org_id` and `project_id` parameters in the memory configuration.
```python Code
from crewai import Crew
crew = Crew(
agents=[...],
tasks=[...],
verbose=True,
memory=True,
memory_config={
"provider": "mem0",
"config": {"user_id": "john", "org_id": "my_org_id", "project_id": "my_project_id"},
"user_memory" : {} #Set user_memory explicitly to a dictionary, we are working on this issue.
},
)
```
### Using Local Mem0 memory
If you want to use local mem0 memory, with a custom configuration, you can set a parameter `local_mem0_config` in the config itself.
If both os environment key is set and local\_mem0\_config is given, the API platform takes higher priority over the local configuration.
Check [this](https://docs.mem0.ai/open-source/python-quickstart#run-mem0-locally) mem0 local configuration docs for more understanding.
In this case `user_memory` is set to `Memory` from mem0.
```python Code
from crewai import Crew
#local mem0 config
config = {
"vector_store": {
"provider": "qdrant",
"config": {
"host": "localhost",
"port": 6333
}
},
"llm": {
"provider": "openai",
"config": {
"api_key": "your-api-key",
"model": "gpt-4"
}
},
"embedder": {
"provider": "openai",
"config": {
"api_key": "your-api-key",
"model": "text-embedding-3-small"
}
},
"graph_store": {
"provider": "neo4j",
"config": {
"url": "neo4j+s://your-instance",
"username": "neo4j",
"password": "password"
}
},
"history_db_path": "/path/to/history.db",
"version": "v1.1",
"custom_fact_extraction_prompt": "Optional custom prompt for fact extraction for memory",
"custom_update_memory_prompt": "Optional custom prompt for update memory"
}
crew = Crew(
agents=[...],
tasks=[...],
verbose=True,
memory=True,
memory_config={
"provider": "mem0",
"config": {"user_id": "john", 'local_mem0_config': config},
"user_memory" : {} #Set user_memory explicitly to a dictionary, we are working on this issue.
},
)
```
### Using External Memory
External Memory is a powerful feature that allows you to integrate external memory systems with your CrewAI applications. This is particularly useful when you want to use specialized memory providers or maintain memory across different applications.
Since it’s an external memory, we’re not able to add a default value to it - unlike with Long Term and Short Term memory.
#### Basic Usage with Mem0
The most common way to use External Memory is with Mem0 as the provider:
```python
import os
from crewai import Agent, Crew, Process, Task
from crewai.memory.external.external_memory import ExternalMemory
os.environ["MEM0_API_KEY"] = "YOUR-API-KEY"
agent = Agent(
role="You are a helpful assistant",
goal="Plan a vacation for the user",
backstory="You are a helpful assistant that can plan a vacation for the user",
verbose=True,
)
task = Task(
description="Give things related to the user's vacation",
expected_output="A plan for the vacation",
agent=agent,
)
crew = Crew(
agents=[agent],
tasks=[task],
verbose=True,
process=Process.sequential,
external_memory=ExternalMemory(
embedder_config={"provider": "mem0", "config": {"user_id": "U-123"}} # you can provide an entire Mem0 configuration
),
)
crew.kickoff(
inputs={"question": "which destination is better for a beach vacation?"}
)
```
#### Using External Memory with Custom Storage
You can also create custom storage implementations for External Memory. Here's an example of how to create a custom storage:
```python
from crewai import Agent, Crew, Process, Task
from crewai.memory.external.external_memory import ExternalMemory
from crewai.memory.storage.interface import Storage
class CustomStorage(Storage):
def __init__(self):
self.memories = []
def save(self, value, metadata=None, agent=None):
self.memories.append({"value": value, "metadata": metadata, "agent": agent})
def search(self, query, limit=10, score_threshold=0.5):
# Implement your search logic here
return []
def reset(self):
self.memories = []
# Create external memory with custom storage
external_memory = ExternalMemory(
storage=CustomStorage(),
embedder_config={"provider": "mem0", "config": {"user_id": "U-123"}},
)
agent = Agent(
role="You are a helpful assistant",
goal="Plan a vacation for the user",
backstory="You are a helpful assistant that can plan a vacation for the user",
verbose=True,
)
task = Task(
description="Give things related to the user's vacation",
expected_output="A plan for the vacation",
agent=agent,
)
crew = Crew(
agents=[agent],
tasks=[task],
verbose=True,
process=Process.sequential,
external_memory=external_memory,
)
crew.kickoff(
inputs={"question": "which destination is better for a beach vacation?"}
)
```
## Additional Embedding Providers
### Using OpenAI embeddings (already default)
```python Code
from crewai import Crew, Agent, Task, Process
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "openai",
"config": {
"model": 'text-embedding-3-small'
}
}
)
```
Alternatively, you can directly pass the OpenAIEmbeddingFunction to the embedder parameter.
Example:
```python Code
from crewai import Crew, Agent, Task, Process
from chromadb.utils.embedding_functions import OpenAIEmbeddingFunction
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "openai",
"config": {
"model": 'text-embedding-3-small'
}
}
)
```
### Using Ollama embeddings
```python Code
from crewai import Crew, Agent, Task, Process
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "ollama",
"config": {
"model": "mxbai-embed-large"
}
}
)
```
### Using Google AI embeddings
#### Prerequisites
Before using Google AI embeddings, ensure you have:
* Access to the Gemini API
* The necessary API keys and permissions
You will need to update your *pyproject.toml* dependencies:
```YAML
dependencies = [
"google-generativeai>=0.8.4", #main version in January/2025 - crewai v.0.100.0 and crewai-tools 0.33.0
"crewai[tools]>=0.100.0,<1.0.0"
]
```
```python Code
from crewai import Crew, Agent, Task, Process
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "google",
"config": {
"api_key": "",
"model": ""
}
}
)
```
### Using Azure OpenAI embeddings
```python Code
from chromadb.utils.embedding_functions import OpenAIEmbeddingFunction
from crewai import Crew, Agent, Task, Process
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "openai",
"config": {
"api_key": "YOUR_API_KEY",
"api_base": "YOUR_API_BASE_PATH",
"api_version": "YOUR_API_VERSION",
"model_name": 'text-embedding-3-small'
}
}
)
```
### Using Vertex AI embeddings
```python Code
from chromadb.utils.embedding_functions import GoogleVertexEmbeddingFunction
from crewai import Crew, Agent, Task, Process
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "vertexai",
"config": {
"project_id"="YOUR_PROJECT_ID",
"region"="YOUR_REGION",
"api_key"="YOUR_API_KEY",
"model_name"="textembedding-gecko"
}
}
)
```
### Using Cohere embeddings
```python Code
from crewai import Crew, Agent, Task, Process
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "cohere",
"config": {
"api_key": "YOUR_API_KEY",
"model": ""
}
}
)
```
### Using VoyageAI embeddings
```python Code
from crewai import Crew, Agent, Task, Process
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "voyageai",
"config": {
"api_key": "YOUR_API_KEY",
"model": ""
}
}
)
```
### Using HuggingFace embeddings
```python Code
from crewai import Crew, Agent, Task, Process
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "huggingface",
"config": {
"api_url": "",
}
}
)
```
### Using Watson embeddings
```python Code
from crewai import Crew, Agent, Task, Process
# Note: Ensure you have installed and imported `ibm_watsonx_ai` for Watson embeddings to work.
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "watson",
"config": {
"model": "",
"api_url": "",
"api_key": "",
"project_id": "",
}
}
)
```
### Using Amazon Bedrock embeddings
```python Code
# Note: Ensure you have installed `boto3` for Bedrock embeddings to work.
import os
import boto3
from crewai import Crew, Agent, Task, Process
boto3_session = boto3.Session(
region_name=os.environ.get("AWS_REGION_NAME"),
aws_access_key_id=os.environ.get("AWS_ACCESS_KEY_ID"),
aws_secret_access_key=os.environ.get("AWS_SECRET_ACCESS_KEY")
)
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
embedder={
"provider": "bedrock",
"config":{
"session": boto3_session,
"model": "amazon.titan-embed-text-v2:0",
"vector_dimension": 1024
}
}
verbose=True
)
```
### Adding Custom Embedding Function
```python Code
from crewai import Crew, Agent, Task, Process
from chromadb import Documents, EmbeddingFunction, Embeddings
# Create a custom embedding function
class CustomEmbedder(EmbeddingFunction):
def __call__(self, input: Documents) -> Embeddings:
# generate embeddings
return [1, 2, 3] # this is a dummy embedding
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "custom",
"config": {
"embedder": CustomEmbedder()
}
}
)
```
### Resetting Memory via cli
```shell
crewai reset-memories [OPTIONS]
```
#### Resetting Memory Options
| Option | Description | Type | Default |
| :------------------------ | :--------------------------------- | :------------- | :------ |
| `-l`, `--long` | Reset LONG TERM memory. | Flag (boolean) | False |
| `-s`, `--short` | Reset SHORT TERM memory. | Flag (boolean) | False |
| `-e`, `--entities` | Reset ENTITIES memory. | Flag (boolean) | False |
| `-k`, `--kickoff-outputs` | Reset LATEST KICKOFF TASK OUTPUTS. | Flag (boolean) | False |
| `-kn`, `--knowledge` | Reset KNOWLEDEGE storage | Flag (boolean) | False |
| `-a`, `--all` | Reset ALL memories. | Flag (boolean) | False |
Note: To use the cli command you need to have your crew in a file called crew\.py in the same directory.
### Resetting Memory via crew object
```python
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "custom",
"config": {
"embedder": CustomEmbedder()
}
}
)
my_crew.reset_memories(command_type = 'all') # Resets all the memory
```
#### Resetting Memory Options
| Command Type | Description |
| :---------------- | :--------------------------------- |
| `long` | Reset LONG TERM memory. |
| `short` | Reset SHORT TERM memory. |
| `entities` | Reset ENTITIES memory. |
| `kickoff_outputs` | Reset LATEST KICKOFF TASK OUTPUTS. |
| `knowledge` | Reset KNOWLEDGE memory. |
| `all` | Reset ALL memories. |
## Benefits of Using CrewAI's Memory System
* 🦾 **Adaptive Learning:** Crews become more efficient over time, adapting to new information and refining their approach to tasks.
* 🫡 **Enhanced Personalization:** Memory enables agents to remember user preferences and historical interactions, leading to personalized experiences.
* 🧠 **Improved Problem Solving:** Access to a rich memory store aids agents in making more informed decisions, drawing on past learnings and contextual insights.
## Conclusion
Integrating CrewAI's memory system into your projects is straightforward. By leveraging the provided memory components and configurations,
you can quickly empower your agents with the ability to remember, reason, and learn from their interactions, unlocking new levels of intelligence and capability.
# Planning
Source: https://docs.crewai.com/concepts/planning
Learn how to add planning to your CrewAI Crew and improve their performance.
## Introduction
The planning feature in CrewAI allows you to add planning capability to your crew. When enabled, before each Crew iteration,
all Crew information is sent to an AgentPlanner that will plan the tasks step by step, and this plan will be added to each task description.
### Using the Planning Feature
Getting started with the planning feature is very easy, the only step required is to add `planning=True` to your Crew:
```python Code
from crewai import Crew, Agent, Task, Process
# Assemble your crew with planning capabilities
my_crew = Crew(
agents=self.agents,
tasks=self.tasks,
process=Process.sequential,
planning=True,
)
```
From this point on, your crew will have planning enabled, and the tasks will be planned before each iteration.
#### Planning LLM
Now you can define the LLM that will be used to plan the tasks.
When running the base case example, you will see something like the output below, which represents the output of the `AgentPlanner`
responsible for creating the step-by-step logic to add to the Agents' tasks.
```python Code
from crewai import Crew, Agent, Task, Process
# Assemble your crew with planning capabilities and custom LLM
my_crew = Crew(
agents=self.agents,
tasks=self.tasks,
process=Process.sequential,
planning=True,
planning_llm="gpt-4o"
)
# Run the crew
my_crew.kickoff()
```
````markdown Result
[2024-07-15 16:49:11][INFO]: Planning the crew execution
**Step-by-Step Plan for Task Execution**
**Task Number 1: Conduct a thorough research about AI LLMs**
**Agent:** AI LLMs Senior Data Researcher
**Agent Goal:** Uncover cutting-edge developments in AI LLMs
**Task Expected Output:** A list with 10 bullet points of the most relevant information about AI LLMs
**Task Tools:** None specified
**Agent Tools:** None specified
**Step-by-Step Plan:**
1. **Define Research Scope:**
- Determine the specific areas of AI LLMs to focus on, such as advancements in architecture, use cases, ethical considerations, and performance metrics.
2. **Identify Reliable Sources:**
- List reputable sources for AI research, including academic journals, industry reports, conferences (e.g., NeurIPS, ACL), AI research labs (e.g., OpenAI, Google AI), and online databases (e.g., IEEE Xplore, arXiv).
3. **Collect Data:**
- Search for the latest papers, articles, and reports published in 2024 and early 2025.
- Use keywords like "Large Language Models 2025", "AI LLM advancements", "AI ethics 2025", etc.
4. **Analyze Findings:**
- Read and summarize the key points from each source.
- Highlight new techniques, models, and applications introduced in the past year.
5. **Organize Information:**
- Categorize the information into relevant topics (e.g., new architectures, ethical implications, real-world applications).
- Ensure each bullet point is concise but informative.
6. **Create the List:**
- Compile the 10 most relevant pieces of information into a bullet point list.
- Review the list to ensure clarity and relevance.
**Expected Output:**
A list with 10 bullet points of the most relevant information about AI LLMs.
---
**Task Number 2: Review the context you got and expand each topic into a full section for a report**
**Agent:** AI LLMs Reporting Analyst
**Agent Goal:** Create detailed reports based on AI LLMs data analysis and research findings
**Task Expected Output:** A fully fledged report with the main topics, each with a full section of information. Formatted as markdown without '```'
**Task Tools:** None specified
**Agent Tools:** None specified
**Step-by-Step Plan:**
1. **Review the Bullet Points:**
- Carefully read through the list of 10 bullet points provided by the AI LLMs Senior Data Researcher.
2. **Outline the Report:**
- Create an outline with each bullet point as a main section heading.
- Plan sub-sections under each main heading to cover different aspects of the topic.
3. **Research Further Details:**
- For each bullet point, conduct additional research if necessary to gather more detailed information.
- Look for case studies, examples, and statistical data to support each section.
4. **Write Detailed Sections:**
- Expand each bullet point into a comprehensive section.
- Ensure each section includes an introduction, detailed explanation, examples, and a conclusion.
- Use markdown formatting for headings, subheadings, lists, and emphasis.
5. **Review and Edit:**
- Proofread the report for clarity, coherence, and correctness.
- Make sure the report flows logically from one section to the next.
- Format the report according to markdown standards.
6. **Finalize the Report:**
- Ensure the report is complete with all sections expanded and detailed.
- Double-check formatting and make any necessary adjustments.
**Expected Output:**
A fully fledged report with the main topics, each with a full section of information. Formatted as markdown without '```'.
````
# Processes
Source: https://docs.crewai.com/concepts/processes
Detailed guide on workflow management through processes in CrewAI, with updated implementation details.
## Understanding Processes
Processes orchestrate the execution of tasks by agents, akin to project management in human teams.
These processes ensure tasks are distributed and executed efficiently, in alignment with a predefined strategy.
## Process Implementations
* **Sequential**: Executes tasks sequentially, ensuring tasks are completed in an orderly progression.
* **Hierarchical**: Organizes tasks in a managerial hierarchy, where tasks are delegated and executed based on a structured chain of command. A manager language model (`manager_llm`) or a custom manager agent (`manager_agent`) must be specified in the crew to enable the hierarchical process, facilitating the creation and management of tasks by the manager.
* **Consensual Process (Planned)**: Aiming for collaborative decision-making among agents on task execution, this process type introduces a democratic approach to task management within CrewAI. It is planned for future development and is not currently implemented in the codebase.
## The Role of Processes in Teamwork
Processes enable individual agents to operate as a cohesive unit, streamlining their efforts to achieve common objectives with efficiency and coherence.
## Assigning Processes to a Crew
To assign a process to a crew, specify the process type upon crew creation to set the execution strategy. For a hierarchical process, ensure to define `manager_llm` or `manager_agent` for the manager agent.
```python
from crewai import Crew, Process
# Example: Creating a crew with a sequential process
crew = Crew(
agents=my_agents,
tasks=my_tasks,
process=Process.sequential
)
# Example: Creating a crew with a hierarchical process
# Ensure to provide a manager_llm or manager_agent
crew = Crew(
agents=my_agents,
tasks=my_tasks,
process=Process.hierarchical,
manager_llm="gpt-4o"
# or
# manager_agent=my_manager_agent
)
```
**Note:** Ensure `my_agents` and `my_tasks` are defined prior to creating a `Crew` object, and for the hierarchical process, either `manager_llm` or `manager_agent` is also required.
## Sequential Process
This method mirrors dynamic team workflows, progressing through tasks in a thoughtful and systematic manner. Task execution follows the predefined order in the task list, with the output of one task serving as context for the next.
To customize task context, utilize the `context` parameter in the `Task` class to specify outputs that should be used as context for subsequent tasks.
## Hierarchical Process
Emulates a corporate hierarchy, CrewAI allows specifying a custom manager agent or automatically creates one, requiring the specification of a manager language model (`manager_llm`). This agent oversees task execution, including planning, delegation, and validation. Tasks are not pre-assigned; the manager allocates tasks to agents based on their capabilities, reviews outputs, and assesses task completion.
## Process Class: Detailed Overview
The `Process` class is implemented as an enumeration (`Enum`), ensuring type safety and restricting process values to the defined types (`sequential`, `hierarchical`). The consensual process is planned for future inclusion, emphasizing our commitment to continuous development and innovation.
## Conclusion
The structured collaboration facilitated by processes within CrewAI is crucial for enabling systematic teamwork among agents.
This documentation has been updated to reflect the latest features, enhancements, and the planned integration of the Consensual Process, ensuring users have access to the most current and comprehensive information.
# Tasks
Source: https://docs.crewai.com/concepts/tasks
Detailed guide on managing and creating tasks within the CrewAI framework.
## Overview of a Task
In the CrewAI framework, a `Task` is a specific assignment completed by an `Agent`.
Tasks provide all necessary details for execution, such as a description, the agent responsible, required tools, and more, facilitating a wide range of action complexities.
Tasks within CrewAI can be collaborative, requiring multiple agents to work together. This is managed through the task properties and orchestrated by the Crew's process, enhancing teamwork and efficiency.
CrewAI Enterprise includes a Visual Task Builder in Crew Studio that simplifies complex task creation and chaining. Design your task flows visually and test them in real-time without writing code.
The Visual Task Builder enables:
* Drag-and-drop task creation
* Visual task dependencies and flow
* Real-time testing and validation
* Easy sharing and collaboration
### Task Execution Flow
Tasks can be executed in two ways:
* **Sequential**: Tasks are executed in the order they are defined
* **Hierarchical**: Tasks are assigned to agents based on their roles and expertise
The execution flow is defined when creating the crew:
```python Code
crew = Crew(
agents=[agent1, agent2],
tasks=[task1, task2],
process=Process.sequential # or Process.hierarchical
)
```
## Task Attributes
| Attribute | Parameters | Type | Description |
| :------------------------------- | :---------------- | :-------------------------- | :-------------------------------------------------------------------------------------------- |
| **Description** | `description` | `str` | A clear, concise statement of what the task entails. |
| **Expected Output** | `expected_output` | `str` | A detailed description of what the task's completion looks like. |
| **Name** *(optional)* | `name` | `Optional[str]` | A name identifier for the task. |
| **Agent** *(optional)* | `agent` | `Optional[BaseAgent]` | The agent responsible for executing the task. |
| **Tools** *(optional)* | `tools` | `List[BaseTool]` | The tools/resources the agent is limited to use for this task. |
| **Context** *(optional)* | `context` | `Optional[List["Task"]]` | Other tasks whose outputs will be used as context for this task. |
| **Async Execution** *(optional)* | `async_execution` | `Optional[bool]` | Whether the task should be executed asynchronously. Defaults to False. |
| **Human Input** *(optional)* | `human_input` | `Optional[bool]` | Whether the task should have a human review the final answer of the agent. Defaults to False. |
| **Config** *(optional)* | `config` | `Optional[Dict[str, Any]]` | Task-specific configuration parameters. |
| **Output File** *(optional)* | `output_file` | `Optional[str]` | File path for storing the task output. |
| **Output JSON** *(optional)* | `output_json` | `Optional[Type[BaseModel]]` | A Pydantic model to structure the JSON output. |
| **Output Pydantic** *(optional)* | `output_pydantic` | `Optional[Type[BaseModel]]` | A Pydantic model for task output. |
| **Callback** *(optional)* | `callback` | `Optional[Any]` | Function/object to be executed after task completion. |
## Creating Tasks
There are two ways to create tasks in CrewAI: using **YAML configuration (recommended)** or defining them **directly in code**.
### YAML Configuration (Recommended)
Using YAML configuration provides a cleaner, more maintainable way to define tasks. We strongly recommend using this approach to define tasks in your CrewAI projects.
After creating your CrewAI project as outlined in the [Installation](/installation) section, navigate to the `src/latest_ai_development/config/tasks.yaml` file and modify the template to match your specific task requirements.
Variables in your YAML files (like `{topic}`) will be replaced with values from your inputs when running the crew:
```python Code
crew.kickoff(inputs={'topic': 'AI Agents'})
```
Here's an example of how to configure tasks using YAML:
````yaml tasks.yaml
research_task:
description: >
Conduct a thorough research about {topic}
Make sure you find any interesting and relevant information given
the current year is 2025.
expected_output: >
A list with 10 bullet points of the most relevant information about {topic}
agent: researcher
reporting_task:
description: >
Review the context you got and expand each topic into a full section for a report.
Make sure the report is detailed and contains any and all relevant information.
expected_output: >
A fully fledge reports with the mains topics, each with a full section of information.
Formatted as markdown without '```'
agent: reporting_analyst
output_file: report.md
````
To use this YAML configuration in your code, create a crew class that inherits from `CrewBase`:
```python crew.py
# src/latest_ai_development/crew.py
from crewai import Agent, Crew, Process, Task
from crewai.project import CrewBase, agent, crew, task
from crewai_tools import SerperDevTool
@CrewBase
class LatestAiDevelopmentCrew():
"""LatestAiDevelopment crew"""
@agent
def researcher(self) -> Agent:
return Agent(
config=self.agents_config['researcher'], # type: ignore[index]
verbose=True,
tools=[SerperDevTool()]
)
@agent
def reporting_analyst(self) -> Agent:
return Agent(
config=self.agents_config['reporting_analyst'], # type: ignore[index]
verbose=True
)
@task
def research_task(self) -> Task:
return Task(
config=self.tasks_config['research_task'] # type: ignore[index]
)
@task
def reporting_task(self) -> Task:
return Task(
config=self.tasks_config['reporting_task'] # type: ignore[index]
)
@crew
def crew(self) -> Crew:
return Crew(
agents=[
self.researcher(),
self.reporting_analyst()
],
tasks=[
self.research_task(),
self.reporting_task()
],
process=Process.sequential
)
```
The names you use in your YAML files (`agents.yaml` and `tasks.yaml`) should match the method names in your Python code.
### Direct Code Definition (Alternative)
Alternatively, you can define tasks directly in your code without using YAML configuration:
````python task.py
from crewai import Task
research_task = Task(
description="""
Conduct a thorough research about AI Agents.
Make sure you find any interesting and relevant information given
the current year is 2025.
""",
expected_output="""
A list with 10 bullet points of the most relevant information about AI Agents
""",
agent=researcher
)
reporting_task = Task(
description="""
Review the context you got and expand each topic into a full section for a report.
Make sure the report is detailed and contains any and all relevant information.
""",
expected_output="""
A fully fledge reports with the mains topics, each with a full section of information.
Formatted as markdown without '```'
""",
agent=reporting_analyst,
output_file="report.md"
)
````
Directly specify an `agent` for assignment or let the `hierarchical` CrewAI's process decide based on roles, availability, etc.
## Task Output
Understanding task outputs is crucial for building effective AI workflows. CrewAI provides a structured way to handle task results through the `TaskOutput` class, which supports multiple output formats and can be easily passed between tasks.
The output of a task in CrewAI framework is encapsulated within the `TaskOutput` class. This class provides a structured way to access results of a task, including various formats such as raw output, JSON, and Pydantic models.
By default, the `TaskOutput` will only include the `raw` output. A `TaskOutput` will only include the `pydantic` or `json_dict` output if the original `Task` object was configured with `output_pydantic` or `output_json`, respectively.
### Task Output Attributes
| Attribute | Parameters | Type | Description |
| :---------------- | :-------------- | :------------------------- | :------------------------------------------------------------------------------------------------- |
| **Description** | `description` | `str` | Description of the task. |
| **Summary** | `summary` | `Optional[str]` | Summary of the task, auto-generated from the first 10 words of the description. |
| **Raw** | `raw` | `str` | The raw output of the task. This is the default format for the output. |
| **Pydantic** | `pydantic` | `Optional[BaseModel]` | A Pydantic model object representing the structured output of the task. |
| **JSON Dict** | `json_dict` | `Optional[Dict[str, Any]]` | A dictionary representing the JSON output of the task. |
| **Agent** | `agent` | `str` | The agent that executed the task. |
| **Output Format** | `output_format` | `OutputFormat` | The format of the task output, with options including RAW, JSON, and Pydantic. The default is RAW. |
### Task Methods and Properties
| Method/Property | Description |
| :-------------- | :------------------------------------------------------------------------------------------------ |
| **json** | Returns the JSON string representation of the task output if the output format is JSON. |
| **to\_dict** | Converts the JSON and Pydantic outputs to a dictionary. |
| **str** | Returns the string representation of the task output, prioritizing Pydantic, then JSON, then raw. |
### Accessing Task Outputs
Once a task has been executed, its output can be accessed through the `output` attribute of the `Task` object. The `TaskOutput` class provides various ways to interact with and present this output.
#### Example
```python Code
# Example task
task = Task(
description='Find and summarize the latest AI news',
expected_output='A bullet list summary of the top 5 most important AI news',
agent=research_agent,
tools=[search_tool]
)
# Execute the crew
crew = Crew(
agents=[research_agent],
tasks=[task],
verbose=True
)
result = crew.kickoff()
# Accessing the task output
task_output = task.output
print(f"Task Description: {task_output.description}")
print(f"Task Summary: {task_output.summary}")
print(f"Raw Output: {task_output.raw}")
if task_output.json_dict:
print(f"JSON Output: {json.dumps(task_output.json_dict, indent=2)}")
if task_output.pydantic:
print(f"Pydantic Output: {task_output.pydantic}")
```
## Task Dependencies and Context
Tasks can depend on the output of other tasks using the `context` attribute. For example:
```python Code
research_task = Task(
description="Research the latest developments in AI",
expected_output="A list of recent AI developments",
agent=researcher
)
analysis_task = Task(
description="Analyze the research findings and identify key trends",
expected_output="Analysis report of AI trends",
agent=analyst,
context=[research_task] # This task will wait for research_task to complete
)
```
## Task Guardrails
Task guardrails provide a way to validate and transform task outputs before they
are passed to the next task. This feature helps ensure data quality and provides
feedback to agents when their output doesn't meet specific criteria.
### Using Task Guardrails
To add a guardrail to a task, provide a validation function through the `guardrail` parameter:
```python Code
from typing import Tuple, Union, Dict, Any
from crewai import TaskOutput
def validate_blog_content(result: TaskOutput) -> Tuple[bool, Any]:
"""Validate blog content meets requirements."""
try:
# Check word count
word_count = len(result.split())
if word_count > 200:
return (False, "Blog content exceeds 200 words")
# Additional validation logic here
return (True, result.strip())
except Exception as e:
return (False, "Unexpected error during validation")
blog_task = Task(
description="Write a blog post about AI",
expected_output="A blog post under 200 words",
agent=blog_agent,
guardrail=validate_blog_content # Add the guardrail function
)
```
### Guardrail Function Requirements
1. **Function Signature**:
* Must accept exactly one parameter (the task output)
* Should return a tuple of `(bool, Any)`
* Type hints are recommended but optional
2. **Return Values**:
* On success: it returns a tuple of `(bool, Any)`. For example: `(True, validated_result)`
* On Failure: it returns a tuple of `(bool, str)`. For example: `(False, "Error message explain the failure")`
### Error Handling Best Practices
1. **Structured Error Responses**:
```python Code
from crewai import TaskOutput
def validate_with_context(result: TaskOutput) -> Tuple[bool, Any]:
try:
# Main validation logic
validated_data = perform_validation(result)
return (True, validated_data)
except ValidationError as e:
return (False, f"VALIDATION_ERROR: {str(e)}")
except Exception as e:
return (False, str(e))
```
2. **Error Categories**:
* Use specific error codes
* Include relevant context
* Provide actionable feedback
3. **Validation Chain**:
```python Code
from typing import Any, Dict, List, Tuple, Union
from crewai import TaskOutput
def complex_validation(result: TaskOutput) -> Tuple[bool, Any]:
"""Chain multiple validation steps."""
# Step 1: Basic validation
if not result:
return (False, "Empty result")
# Step 2: Content validation
try:
validated = validate_content(result)
if not validated:
return (False, "Invalid content")
# Step 3: Format validation
formatted = format_output(validated)
return (True, formatted)
except Exception as e:
return (False, str(e))
```
### Handling Guardrail Results
When a guardrail returns `(False, error)`:
1. The error is sent back to the agent
2. The agent attempts to fix the issue
3. The process repeats until:
* The guardrail returns `(True, result)`
* Maximum retries are reached
Example with retry handling:
```python Code
from typing import Optional, Tuple, Union
from crewai import TaskOutput, Task
def validate_json_output(result: TaskOutput) -> Tuple[bool, Any]:
"""Validate and parse JSON output."""
try:
# Try to parse as JSON
data = json.loads(result)
return (True, data)
except json.JSONDecodeError as e:
return (False, "Invalid JSON format")
task = Task(
description="Generate a JSON report",
expected_output="A valid JSON object",
agent=analyst,
guardrail=validate_json_output,
max_retries=3 # Limit retry attempts
)
```
## Getting Structured Consistent Outputs from Tasks
It's also important to note that the output of the final task of a crew becomes the final output of the actual crew itself.
### Using `output_pydantic`
The `output_pydantic` property allows you to define a Pydantic model that the task output should conform to. This ensures that the output is not only structured but also validated according to the Pydantic model.
Here's an example demonstrating how to use output\_pydantic:
```python Code
import json
from crewai import Agent, Crew, Process, Task
from pydantic import BaseModel
class Blog(BaseModel):
title: str
content: str
blog_agent = Agent(
role="Blog Content Generator Agent",
goal="Generate a blog title and content",
backstory="""You are an expert content creator, skilled in crafting engaging and informative blog posts.""",
verbose=False,
allow_delegation=False,
llm="gpt-4o",
)
task1 = Task(
description="""Create a blog title and content on a given topic. Make sure the content is under 200 words.""",
expected_output="A compelling blog title and well-written content.",
agent=blog_agent,
output_pydantic=Blog,
)
# Instantiate your crew with a sequential process
crew = Crew(
agents=[blog_agent],
tasks=[task1],
verbose=True,
process=Process.sequential,
)
result = crew.kickoff()
# Option 1: Accessing Properties Using Dictionary-Style Indexing
print("Accessing Properties - Option 1")
title = result["title"]
content = result["content"]
print("Title:", title)
print("Content:", content)
# Option 2: Accessing Properties Directly from the Pydantic Model
print("Accessing Properties - Option 2")
title = result.pydantic.title
content = result.pydantic.content
print("Title:", title)
print("Content:", content)
# Option 3: Accessing Properties Using the to_dict() Method
print("Accessing Properties - Option 3")
output_dict = result.to_dict()
title = output_dict["title"]
content = output_dict["content"]
print("Title:", title)
print("Content:", content)
# Option 4: Printing the Entire Blog Object
print("Accessing Properties - Option 5")
print("Blog:", result)
```
In this example:
* A Pydantic model Blog is defined with title and content fields.
* The task task1 uses the output\_pydantic property to specify that its output should conform to the Blog model.
* After executing the crew, you can access the structured output in multiple ways as shown.
#### Explanation of Accessing the Output
1. Dictionary-Style Indexing: You can directly access the fields using result\["field\_name"]. This works because the CrewOutput class implements the **getitem** method.
2. Directly from Pydantic Model: Access the attributes directly from the result.pydantic object.
3. Using to\_dict() Method: Convert the output to a dictionary and access the fields.
4. Printing the Entire Object: Simply print the result object to see the structured output.
### Using `output_json`
The `output_json` property allows you to define the expected output in JSON format. This ensures that the task's output is a valid JSON structure that can be easily parsed and used in your application.
Here's an example demonstrating how to use `output_json`:
```python Code
import json
from crewai import Agent, Crew, Process, Task
from pydantic import BaseModel
# Define the Pydantic model for the blog
class Blog(BaseModel):
title: str
content: str
# Define the agent
blog_agent = Agent(
role="Blog Content Generator Agent",
goal="Generate a blog title and content",
backstory="""You are an expert content creator, skilled in crafting engaging and informative blog posts.""",
verbose=False,
allow_delegation=False,
llm="gpt-4o",
)
# Define the task with output_json set to the Blog model
task1 = Task(
description="""Create a blog title and content on a given topic. Make sure the content is under 200 words.""",
expected_output="A JSON object with 'title' and 'content' fields.",
agent=blog_agent,
output_json=Blog,
)
# Instantiate the crew with a sequential process
crew = Crew(
agents=[blog_agent],
tasks=[task1],
verbose=True,
process=Process.sequential,
)
# Kickoff the crew to execute the task
result = crew.kickoff()
# Option 1: Accessing Properties Using Dictionary-Style Indexing
print("Accessing Properties - Option 1")
title = result["title"]
content = result["content"]
print("Title:", title)
print("Content:", content)
# Option 2: Printing the Entire Blog Object
print("Accessing Properties - Option 2")
print("Blog:", result)
```
In this example:
* A Pydantic model Blog is defined with title and content fields, which is used to specify the structure of the JSON output.
* The task task1 uses the output\_json property to indicate that it expects a JSON output conforming to the Blog model.
* After executing the crew, you can access the structured JSON output in two ways as shown.
#### Explanation of Accessing the Output
1. Accessing Properties Using Dictionary-Style Indexing: You can access the fields directly using result\["field\_name"]. This is possible because the CrewOutput class implements the **getitem** method, allowing you to treat the output like a dictionary. In this option, we're retrieving the title and content from the result.
2. Printing the Entire Blog Object: By printing result, you get the string representation of the CrewOutput object. Since the **str** method is implemented to return the JSON output, this will display the entire output as a formatted string representing the Blog object.
***
By using output\_pydantic or output\_json, you ensure that your tasks produce outputs in a consistent and structured format, making it easier to process and utilize the data within your application or across multiple tasks.
## Integrating Tools with Tasks
Leverage tools from the [CrewAI Toolkit](https://github.com/joaomdmoura/crewai-tools) and [LangChain Tools](https://python.langchain.com/docs/integrations/tools) for enhanced task performance and agent interaction.
## Creating a Task with Tools
```python Code
import os
os.environ["OPENAI_API_KEY"] = "Your Key"
os.environ["SERPER_API_KEY"] = "Your Key" # serper.dev API key
from crewai import Agent, Task, Crew
from crewai_tools import SerperDevTool
research_agent = Agent(
role='Researcher',
goal='Find and summarize the latest AI news',
backstory="""You're a researcher at a large company.
You're responsible for analyzing data and providing insights
to the business.""",
verbose=True
)
# to perform a semantic search for a specified query from a text's content across the internet
search_tool = SerperDevTool()
task = Task(
description='Find and summarize the latest AI news',
expected_output='A bullet list summary of the top 5 most important AI news',
agent=research_agent,
tools=[search_tool]
)
crew = Crew(
agents=[research_agent],
tasks=[task],
verbose=True
)
result = crew.kickoff()
print(result)
```
This demonstrates how tasks with specific tools can override an agent's default set for tailored task execution.
## Referring to Other Tasks
In CrewAI, the output of one task is automatically relayed into the next one, but you can specifically define what tasks' output, including multiple, should be used as context for another task.
This is useful when you have a task that depends on the output of another task that is not performed immediately after it. This is done through the `context` attribute of the task:
```python Code
# ...
research_ai_task = Task(
description="Research the latest developments in AI",
expected_output="A list of recent AI developments",
async_execution=True,
agent=research_agent,
tools=[search_tool]
)
research_ops_task = Task(
description="Research the latest developments in AI Ops",
expected_output="A list of recent AI Ops developments",
async_execution=True,
agent=research_agent,
tools=[search_tool]
)
write_blog_task = Task(
description="Write a full blog post about the importance of AI and its latest news",
expected_output="Full blog post that is 4 paragraphs long",
agent=writer_agent,
context=[research_ai_task, research_ops_task]
)
#...
```
## Asynchronous Execution
You can define a task to be executed asynchronously. This means that the crew will not wait for it to be completed to continue with the next task. This is useful for tasks that take a long time to be completed, or that are not crucial for the next tasks to be performed.
You can then use the `context` attribute to define in a future task that it should wait for the output of the asynchronous task to be completed.
```python Code
#...
list_ideas = Task(
description="List of 5 interesting ideas to explore for an article about AI.",
expected_output="Bullet point list of 5 ideas for an article.",
agent=researcher,
async_execution=True # Will be executed asynchronously
)
list_important_history = Task(
description="Research the history of AI and give me the 5 most important events.",
expected_output="Bullet point list of 5 important events.",
agent=researcher,
async_execution=True # Will be executed asynchronously
)
write_article = Task(
description="Write an article about AI, its history, and interesting ideas.",
expected_output="A 4 paragraph article about AI.",
agent=writer,
context=[list_ideas, list_important_history] # Will wait for the output of the two tasks to be completed
)
#...
```
## Callback Mechanism
The callback function is executed after the task is completed, allowing for actions or notifications to be triggered based on the task's outcome.
```python Code
# ...
def callback_function(output: TaskOutput):
# Do something after the task is completed
# Example: Send an email to the manager
print(f"""
Task completed!
Task: {output.description}
Output: {output.raw}
""")
research_task = Task(
description='Find and summarize the latest AI news',
expected_output='A bullet list summary of the top 5 most important AI news',
agent=research_agent,
tools=[search_tool],
callback=callback_function
)
#...
```
## Accessing a Specific Task Output
Once a crew finishes running, you can access the output of a specific task by using the `output` attribute of the task object:
```python Code
# ...
task1 = Task(
description='Find and summarize the latest AI news',
expected_output='A bullet list summary of the top 5 most important AI news',
agent=research_agent,
tools=[search_tool]
)
#...
crew = Crew(
agents=[research_agent],
tasks=[task1, task2, task3],
verbose=True
)
result = crew.kickoff()
# Returns a TaskOutput object with the description and results of the task
print(f"""
Task completed!
Task: {task1.output.description}
Output: {task1.output.raw}
""")
```
## Tool Override Mechanism
Specifying tools in a task allows for dynamic adaptation of agent capabilities, emphasizing CrewAI's flexibility.
## Error Handling and Validation Mechanisms
While creating and executing tasks, certain validation mechanisms are in place to ensure the robustness and reliability of task attributes. These include but are not limited to:
* Ensuring only one output type is set per task to maintain clear output expectations.
* Preventing the manual assignment of the `id` attribute to uphold the integrity of the unique identifier system.
These validations help in maintaining the consistency and reliability of task executions within the crewAI framework.
## Task Guardrails
Task guardrails provide a powerful way to validate, transform, or filter task outputs before they are passed to the next task. Guardrails are optional functions that execute before the next task starts, allowing you to ensure that task outputs meet specific requirements or formats.
### Basic Usage
```python Code
from typing import Tuple, Union
from crewai import Task
def validate_json_output(result: str) -> Tuple[bool, Union[dict, str]]:
"""Validate that the output is valid JSON."""
try:
json_data = json.loads(result)
return (True, json_data)
except json.JSONDecodeError:
return (False, "Output must be valid JSON")
task = Task(
description="Generate JSON data",
expected_output="Valid JSON object",
guardrail=validate_json_output
)
```
### How Guardrails Work
1. **Optional Attribute**: Guardrails are an optional attribute at the task level, allowing you to add validation only where needed.
2. **Execution Timing**: The guardrail function is executed before the next task starts, ensuring valid data flow between tasks.
3. **Return Format**: Guardrails must return a tuple of `(success, data)`:
* If `success` is `True`, `data` is the validated/transformed result
* If `success` is `False`, `data` is the error message
4. **Result Routing**:
* On success (`True`), the result is automatically passed to the next task
* On failure (`False`), the error is sent back to the agent to generate a new answer
### Common Use Cases
#### Data Format Validation
```python Code
def validate_email_format(result: str) -> Tuple[bool, Union[str, str]]:
"""Ensure the output contains a valid email address."""
import re
email_pattern = r'^[\w\.-]+@[\w\.-]+\.\w+$'
if re.match(email_pattern, result.strip()):
return (True, result.strip())
return (False, "Output must be a valid email address")
```
#### Content Filtering
```python Code
def filter_sensitive_info(result: str) -> Tuple[bool, Union[str, str]]:
"""Remove or validate sensitive information."""
sensitive_patterns = ['SSN:', 'password:', 'secret:']
for pattern in sensitive_patterns:
if pattern.lower() in result.lower():
return (False, f"Output contains sensitive information ({pattern})")
return (True, result)
```
#### Data Transformation
```python Code
def normalize_phone_number(result: str) -> Tuple[bool, Union[str, str]]:
"""Ensure phone numbers are in a consistent format."""
import re
digits = re.sub(r'\D', '', result)
if len(digits) == 10:
formatted = f"({digits[:3]}) {digits[3:6]}-{digits[6:]}"
return (True, formatted)
return (False, "Output must be a 10-digit phone number")
```
### Advanced Features
#### Chaining Multiple Validations
```python Code
def chain_validations(*validators):
"""Chain multiple validators together."""
def combined_validator(result):
for validator in validators:
success, data = validator(result)
if not success:
return (False, data)
result = data
return (True, result)
return combined_validator
# Usage
task = Task(
description="Get user contact info",
expected_output="Email and phone",
guardrail=chain_validations(
validate_email_format,
filter_sensitive_info
)
)
```
#### Custom Retry Logic
```python Code
task = Task(
description="Generate data",
expected_output="Valid data",
guardrail=validate_data,
max_retries=5 # Override default retry limit
)
```
## Creating Directories when Saving Files
You can now specify if a task should create directories when saving its output to a file. This is particularly useful for organizing outputs and ensuring that file paths are correctly structured.
```python Code
# ...
save_output_task = Task(
description='Save the summarized AI news to a file',
expected_output='File saved successfully',
agent=research_agent,
tools=[file_save_tool],
output_file='outputs/ai_news_summary.txt',
create_directory=True
)
#...
```
Check out the video below to see how to use structured outputs in CrewAI:
## Conclusion
Tasks are the driving force behind the actions of agents in CrewAI.
By properly defining tasks and their outcomes, you set the stage for your AI agents to work effectively, either independently or as a collaborative unit.
Equipping tasks with appropriate tools, understanding the execution process, and following robust validation practices are crucial for maximizing CrewAI's potential,
ensuring agents are effectively prepared for their assignments and that tasks are executed as intended.
# Testing
Source: https://docs.crewai.com/concepts/testing
Learn how to test your CrewAI Crew and evaluate their performance.
## Introduction
Testing is a crucial part of the development process, and it is essential to ensure that your crew is performing as expected. With crewAI, you can easily test your crew and evaluate its performance using the built-in testing capabilities.
### Using the Testing Feature
We added the CLI command `crewai test` to make it easy to test your crew. This command will run your crew for a specified number of iterations and provide detailed performance metrics. The parameters are `n_iterations` and `model`, which are optional and default to 2 and `gpt-4o-mini` respectively. For now, the only provider available is OpenAI.
```bash
crewai test
```
If you want to run more iterations or use a different model, you can specify the parameters like this:
```bash
crewai test --n_iterations 5 --model gpt-4o
```
or using the short forms:
```bash
crewai test -n 5 -m gpt-4o
```
When you run the `crewai test` command, the crew will be executed for the specified number of iterations, and the performance metrics will be displayed at the end of the run.
A table of scores at the end will show the performance of the crew in terms of the following metrics:
**Tasks Scores (1-10 Higher is better)**
| Tasks/Crew/Agents | Run 1 | Run 2 | Avg. Total | Agents | Additional Info |
| :----------------- | :---: | :---: | :--------: | :--------------------------: | :----------------------------- |
| Task 1 | 9.0 | 9.5 | **9.2** | Professional Insights | |
| | | | | Researcher | |
| Task 2 | 9.0 | 10.0 | **9.5** | Company Profile Investigator | |
| Task 3 | 9.0 | 9.0 | **9.0** | Automation Insights | |
| | | | | Specialist | |
| Task 4 | 9.0 | 9.0 | **9.0** | Final Report Compiler | Automation Insights Specialist |
| Crew | 9.00 | 9.38 | **9.2** | | |
| Execution Time (s) | 126 | 145 | **135** | | |
The example above shows the test results for two runs of the crew with two tasks, with the average total score for each task and the crew as a whole.
# Tools
Source: https://docs.crewai.com/concepts/tools
Understanding and leveraging tools within the CrewAI framework for agent collaboration and task execution.
## Introduction
CrewAI tools empower agents with capabilities ranging from web searching and data analysis to collaboration and delegating tasks among coworkers.
This documentation outlines how to create, integrate, and leverage these tools within the CrewAI framework, including a new focus on collaboration tools.
## What is a Tool?
A tool in CrewAI is a skill or function that agents can utilize to perform various actions.
This includes tools from the [CrewAI Toolkit](https://github.com/joaomdmoura/crewai-tools) and [LangChain Tools](https://python.langchain.com/docs/integrations/tools),
enabling everything from simple searches to complex interactions and effective teamwork among agents.
CrewAI Enterprise provides a comprehensive Tools Repository with pre-built integrations for common business systems and APIs. Deploy agents with enterprise tools in minutes instead of days.
The Enterprise Tools Repository includes:
* Pre-built connectors for popular enterprise systems
* Custom tool creation interface
* Version control and sharing capabilities
* Security and compliance features
## Key Characteristics of Tools
* **Utility**: Crafted for tasks such as web searching, data analysis, content generation, and agent collaboration.
* **Integration**: Boosts agent capabilities by seamlessly integrating tools into their workflow.
* **Customizability**: Provides the flexibility to develop custom tools or utilize existing ones, catering to the specific needs of agents.
* **Error Handling**: Incorporates robust error handling mechanisms to ensure smooth operation.
* **Caching Mechanism**: Features intelligent caching to optimize performance and reduce redundant operations.
## Using CrewAI Tools
To enhance your agents' capabilities with crewAI tools, begin by installing our extra tools package:
```bash
pip install 'crewai[tools]'
```
Here's an example demonstrating their use:
```python Code
import os
from crewai import Agent, Task, Crew
# Importing crewAI tools
from crewai_tools import (
DirectoryReadTool,
FileReadTool,
SerperDevTool,
WebsiteSearchTool
)
# Set up API keys
os.environ["SERPER_API_KEY"] = "Your Key" # serper.dev API key
os.environ["OPENAI_API_KEY"] = "Your Key"
# Instantiate tools
docs_tool = DirectoryReadTool(directory='./blog-posts')
file_tool = FileReadTool()
search_tool = SerperDevTool()
web_rag_tool = WebsiteSearchTool()
# Create agents
researcher = Agent(
role='Market Research Analyst',
goal='Provide up-to-date market analysis of the AI industry',
backstory='An expert analyst with a keen eye for market trends.',
tools=[search_tool, web_rag_tool],
verbose=True
)
writer = Agent(
role='Content Writer',
goal='Craft engaging blog posts about the AI industry',
backstory='A skilled writer with a passion for technology.',
tools=[docs_tool, file_tool],
verbose=True
)
# Define tasks
research = Task(
description='Research the latest trends in the AI industry and provide a summary.',
expected_output='A summary of the top 3 trending developments in the AI industry with a unique perspective on their significance.',
agent=researcher
)
write = Task(
description='Write an engaging blog post about the AI industry, based on the research analyst's summary. Draw inspiration from the latest blog posts in the directory.',
expected_output='A 4-paragraph blog post formatted in markdown with engaging, informative, and accessible content, avoiding complex jargon.',
agent=writer,
output_file='blog-posts/new_post.md' # The final blog post will be saved here
)
# Assemble a crew with planning enabled
crew = Crew(
agents=[researcher, writer],
tasks=[research, write],
verbose=True,
planning=True, # Enable planning feature
)
# Execute tasks
crew.kickoff()
```
## Available CrewAI Tools
* **Error Handling**: All tools are built with error handling capabilities, allowing agents to gracefully manage exceptions and continue their tasks.
* **Caching Mechanism**: All tools support caching, enabling agents to efficiently reuse previously obtained results, reducing the load on external resources and speeding up the execution time. You can also define finer control over the caching mechanism using the `cache_function` attribute on the tool.
Here is a list of the available tools and their descriptions:
| Tool | Description |
| :------------------------------- | :--------------------------------------------------------------------------------------------- |
| **ApifyActorsTool** | A tool that integrates Apify Actors with your workflows for web scraping and automation tasks. |
| **BrowserbaseLoadTool** | A tool for interacting with and extracting data from web browsers. |
| **CodeDocsSearchTool** | A RAG tool optimized for searching through code documentation and related technical documents. |
| **CodeInterpreterTool** | A tool for interpreting python code. |
| **ComposioTool** | Enables use of Composio tools. |
| **CSVSearchTool** | A RAG tool designed for searching within CSV files, tailored to handle structured data. |
| **DALL-E Tool** | A tool for generating images using the DALL-E API. |
| **DirectorySearchTool** | A RAG tool for searching within directories, useful for navigating through file systems. |
| **DOCXSearchTool** | A RAG tool aimed at searching within DOCX documents, ideal for processing Word files. |
| **DirectoryReadTool** | Facilitates reading and processing of directory structures and their contents. |
| **EXASearchTool** | A tool designed for performing exhaustive searches across various data sources. |
| **FileReadTool** | Enables reading and extracting data from files, supporting various file formats. |
| **FirecrawlSearchTool** | A tool to search webpages using Firecrawl and return the results. |
| **FirecrawlCrawlWebsiteTool** | A tool for crawling webpages using Firecrawl. |
| **FirecrawlScrapeWebsiteTool** | A tool for scraping webpages URL using Firecrawl and returning its contents. |
| **GithubSearchTool** | A RAG tool for searching within GitHub repositories, useful for code and documentation search. |
| **SerperDevTool** | A specialized tool for development purposes, with specific functionalities under development. |
| **TXTSearchTool** | A RAG tool focused on searching within text (.txt) files, suitable for unstructured data. |
| **JSONSearchTool** | A RAG tool designed for searching within JSON files, catering to structured data handling. |
| **LlamaIndexTool** | Enables the use of LlamaIndex tools. |
| **MDXSearchTool** | A RAG tool tailored for searching within Markdown (MDX) files, useful for documentation. |
| **PDFSearchTool** | A RAG tool aimed at searching within PDF documents, ideal for processing scanned documents. |
| **PGSearchTool** | A RAG tool optimized for searching within PostgreSQL databases, suitable for database queries. |
| **Vision Tool** | A tool for generating images using the DALL-E API. |
| **RagTool** | A general-purpose RAG tool capable of handling various data sources and types. |
| **ScrapeElementFromWebsiteTool** | Enables scraping specific elements from websites, useful for targeted data extraction. |
| **ScrapeWebsiteTool** | Facilitates scraping entire websites, ideal for comprehensive data collection. |
| **WebsiteSearchTool** | A RAG tool for searching website content, optimized for web data extraction. |
| **XMLSearchTool** | A RAG tool designed for searching within XML files, suitable for structured data formats. |
| **YoutubeChannelSearchTool** | A RAG tool for searching within YouTube channels, useful for video content analysis. |
| **YoutubeVideoSearchTool** | A RAG tool aimed at searching within YouTube videos, ideal for video data extraction. |
## Creating your own Tools
Developers can craft `custom tools` tailored for their agent's needs or
utilize pre-built options.
There are two main ways for one to create a CrewAI tool:
### Subclassing `BaseTool`
```python Code
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
class MyToolInput(BaseModel):
"""Input schema for MyCustomTool."""
argument: str = Field(..., description="Description of the argument.")
class MyCustomTool(BaseTool):
name: str = "Name of my tool"
description: str = "What this tool does. It's vital for effective utilization."
args_schema: Type[BaseModel] = MyToolInput
def _run(self, argument: str) -> str:
# Your tool's logic here
return "Tool's result"
```
### Utilizing the `tool` Decorator
```python Code
from crewai.tools import tool
@tool("Name of my tool")
def my_tool(question: str) -> str:
"""Clear description for what this tool is useful for, your agent will need this information to use it."""
# Function logic here
return "Result from your custom tool"
```
### Structured Tools
The `StructuredTool` class wraps functions as tools, providing flexibility and validation while reducing boilerplate. It supports custom schemas and dynamic logic for seamless integration of complex functionalities.
#### Example:
Using `StructuredTool.from_function`, you can wrap a function that interacts with an external API or system, providing a structured interface. This enables robust validation and consistent execution, making it easier to integrate complex functionalities into your applications as demonstrated in the following example:
```python
from crewai.tools.structured_tool import CrewStructuredTool
from pydantic import BaseModel
# Define the schema for the tool's input using Pydantic
class APICallInput(BaseModel):
endpoint: str
parameters: dict
# Wrapper function to execute the API call
def tool_wrapper(*args, **kwargs):
# Here, you would typically call the API using the parameters
# For demonstration, we'll return a placeholder string
return f"Call the API at {kwargs['endpoint']} with parameters {kwargs['parameters']}"
# Create and return the structured tool
def create_structured_tool():
return CrewStructuredTool.from_function(
name='Wrapper API',
description="A tool to wrap API calls with structured input.",
args_schema=APICallInput,
func=tool_wrapper,
)
# Example usage
structured_tool = create_structured_tool()
# Execute the tool with structured input
result = structured_tool._run(**{
"endpoint": "https://example.com/api",
"parameters": {"key1": "value1", "key2": "value2"}
})
print(result) # Output: Call the API at https://example.com/api with parameters {'key1': 'value1', 'key2': 'value2'}
```
### Custom Caching Mechanism
Tools can optionally implement a `cache_function` to fine-tune caching
behavior. This function determines when to cache results based on specific
conditions, offering granular control over caching logic.
```python Code
from crewai.tools import tool
@tool
def multiplication_tool(first_number: int, second_number: int) -> str:
"""Useful for when you need to multiply two numbers together."""
return first_number * second_number
def cache_func(args, result):
# In this case, we only cache the result if it's a multiple of 2
cache = result % 2 == 0
return cache
multiplication_tool.cache_function = cache_func
writer1 = Agent(
role="Writer",
goal="You write lessons of math for kids.",
backstory="You're an expert in writing and you love to teach kids but you know nothing of math.",
tools=[multiplication_tool],
allow_delegation=False,
)
#...
```
## Conclusion
Tools are pivotal in extending the capabilities of CrewAI agents, enabling them to undertake a broad spectrum of tasks and collaborate effectively.
When building solutions with CrewAI, leverage both custom and existing tools to empower your agents and enhance the AI ecosystem. Consider utilizing error handling,
caching mechanisms, and the flexibility of tool arguments to optimize your agents' performance and capabilities.
# Training
Source: https://docs.crewai.com/concepts/training
Learn how to train your CrewAI agents by giving them feedback early on and get consistent results.
## Introduction
The training feature in CrewAI allows you to train your AI agents using the command-line interface (CLI).
By running the command `crewai train -n `, you can specify the number of iterations for the training process.
During training, CrewAI utilizes techniques to optimize the performance of your agents along with human feedback.
This helps the agents improve their understanding, decision-making, and problem-solving abilities.
### Training Your Crew Using the CLI
To use the training feature, follow these steps:
1. Open your terminal or command prompt.
2. Navigate to the directory where your CrewAI project is located.
3. Run the following command:
```shell
crewai train -n (optional)
```
Replace `` with the desired number of training iterations and `` with the appropriate filename ending with `.pkl`.
### Training Your Crew Programmatically
To train your crew programmatically, use the following steps:
1. Define the number of iterations for training.
2. Specify the input parameters for the training process.
3. Execute the training command within a try-except block to handle potential errors.
```python Code
n_iterations = 2
inputs = {"topic": "CrewAI Training"}
filename = "your_model.pkl"
try:
YourCrewName_Crew().crew().train(
n_iterations=n_iterations,
inputs=inputs,
filename=filename
)
except Exception as e:
raise Exception(f"An error occurred while training the crew: {e}")
```
### Key Points to Note
* **Positive Integer Requirement:** Ensure that the number of iterations (`n_iterations`) is a positive integer. The code will raise a `ValueError` if this condition is not met.
* **Filename Requirement:** Ensure that the filename ends with `.pkl`. The code will raise a `ValueError` if this condition is not met.
* **Error Handling:** The code handles subprocess errors and unexpected exceptions, providing error messages to the user.
It is important to note that the training process may take some time, depending on the complexity of your agents and will also require your feedback on each iteration.
Once the training is complete, your agents will be equipped with enhanced capabilities and knowledge, ready to tackle complex tasks and provide more consistent and valuable insights.
Remember to regularly update and retrain your agents to ensure they stay up-to-date with the latest information and advancements in the field.
Happy training with CrewAI! 🚀
# CrewAI Examples
Source: https://docs.crewai.com/examples/example
A collection of examples that show how to use CrewAI framework to automate workflows.
Automate marketing strategy creation with CrewAI.
Create a surprise trip itinerary with CrewAI.
Match a profile to jobpositions with CrewAI.
Create a job posting with CrewAI.
Create a game with CrewAI.
Find job candidates with CrewAI.
# Customizing Prompts
Source: https://docs.crewai.com/guides/advanced/customizing-prompts
Dive deeper into low-level prompt customization for CrewAI, enabling super custom and complex use cases for different models and languages.
# Customizing Prompts at a Low Level
## Why Customize Prompts?
Although CrewAI's default prompts work well for many scenarios, low-level customization opens the door to significantly more flexible and powerful agent behavior. Here’s why you might want to take advantage of this deeper control:
1. **Optimize for specific LLMs** – Different models (such as GPT-4, Claude, or Llama) thrive with prompt formats tailored to their unique architectures.
2. **Change the language** – Build agents that operate exclusively in languages beyond English, handling nuances with precision.
3. **Specialize for complex domains** – Adapt prompts for highly specialized industries like healthcare, finance, or legal.
4. **Adjust tone and style** – Make agents more formal, casual, creative, or analytical.
5. **Support super custom use cases** – Utilize advanced prompt structures and formatting to meet intricate, project-specific requirements.
This guide explores how to tap into CrewAI's prompts at a lower level, giving you fine-grained control over how agents think and interact.
## Understanding CrewAI's Prompt System
Under the hood, CrewAI employs a modular prompt system that you can customize extensively:
* **Agent templates** – Govern each agent’s approach to their assigned role.
* **Prompt slices** – Control specialized behaviors such as tasks, tool usage, and output structure.
* **Error handling** – Direct how agents respond to failures, exceptions, or timeouts.
* **Tool-specific prompts** – Define detailed instructions for how tools are invoked or utilized.
Check out the [original prompt templates in CrewAI's repository](https://github.com/crewAIInc/crewAI/blob/main/src/crewai/translations/en.json) to see how these elements are organized. From there, you can override or adapt them as needed to unlock advanced behaviors.
## Best Practices for Managing Prompt Files
When engaging in low-level prompt customization, follow these guidelines to keep things organized and maintainable:
1. **Keep files separate** – Store your customized prompts in dedicated JSON files outside your main codebase.
2. **Version control** – Track changes within your repository, ensuring clear documentation of prompt adjustments over time.
3. **Organize by model or language** – Use naming schemes like `prompts_llama.json` or `prompts_es.json` to quickly identify specialized configurations.
4. **Document changes** – Provide comments or maintain a README detailing the purpose and scope of your customizations.
5. **Minimize alterations** – Only override the specific slices you genuinely need to adjust, keeping default functionality intact for everything else.
## The Simplest Way to Customize Prompts
One straightforward approach is to create a JSON file for the prompts you want to override and then point your Crew at that file:
1. Craft a JSON file with your updated prompt slices.
2. Reference that file via the `prompt_file` parameter in your Crew.
CrewAI then merges your customizations with the defaults, so you don’t have to redefine every prompt. Here’s how:
### Example: Basic Prompt Customization
Create a `custom_prompts.json` file with the prompts you want to modify. Ensure you list all top-level prompts it should contain, not just your changes:
```json
{
"slices": {
"format": "When responding, follow this structure:\n\nTHOUGHTS: Your step-by-step thinking\nACTION: Any tool you're using\nRESULT: Your final answer or conclusion"
}
}
```
Then integrate it like so:
```python
from crewai import Agent, Crew, Task, Process
# Create agents and tasks as normal
researcher = Agent(
role="Research Specialist",
goal="Find information on quantum computing",
backstory="You are a quantum physics expert",
verbose=True
)
research_task = Task(
description="Research quantum computing applications",
expected_output="A summary of practical applications",
agent=researcher
)
# Create a crew with your custom prompt file
crew = Crew(
agents=[researcher],
tasks=[research_task],
prompt_file="path/to/custom_prompts.json",
verbose=True
)
# Run the crew
result = crew.kickoff()
```
With these few edits, you gain low-level control over how your agents communicate and solve tasks.
## Optimizing for Specific Models
Different models thrive on differently structured prompts. Making deeper adjustments can significantly boost performance by aligning your prompts with a model’s nuances.
### Example: Llama 3.3 Prompting Template
For instance, when dealing with Meta’s Llama 3.3, deeper-level customization may reflect the recommended structure described at:
[https://www.llama.com/docs/model-cards-and-prompt-formats/llama3\_1/#prompt-template](https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_1/#prompt-template)
Here’s an example to highlight how you might fine-tune an Agent to leverage Llama 3.3 in code:
```python
from crewai import Agent, Crew, Task, Process
from crewai_tools import DirectoryReadTool, FileReadTool
# Define templates for system, user (prompt), and assistant (response) messages
system_template = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>{{ .System }}<|eot_id|>"""
prompt_template = """<|start_header_id|>user<|end_header_id|>{{ .Prompt }}<|eot_id|>"""
response_template = """<|start_header_id|>assistant<|end_header_id|>{{ .Response }}<|eot_id|>"""
# Create an Agent using Llama-specific layouts
principal_engineer = Agent(
role="Principal Engineer",
goal="Oversee AI architecture and make high-level decisions",
backstory="You are the lead engineer responsible for critical AI systems",
verbose=True,
llm="groq/llama-3.3-70b-versatile", # Using the Llama 3 model
system_template=system_template,
prompt_template=prompt_template,
response_template=response_template,
tools=[DirectoryReadTool(), FileReadTool()]
)
# Define a sample task
engineering_task = Task(
description="Review AI implementation files for potential improvements",
expected_output="A summary of key findings and recommendations",
agent=principal_engineer
)
# Create a Crew for the task
llama_crew = Crew(
agents=[principal_engineer],
tasks=[engineering_task],
process=Process.sequential,
verbose=True
)
# Execute the crew
result = llama_crew.kickoff()
print(result.raw)
```
Through this deeper configuration, you can exercise comprehensive, low-level control over your Llama-based workflows without needing a separate JSON file.
## Conclusion
Low-level prompt customization in CrewAI opens the door to super custom, complex use cases. By establishing well-organized prompt files (or direct inline templates), you can accommodate various models, languages, and specialized domains. This level of flexibility ensures you can craft precisely the AI behavior you need, all while knowing CrewAI still provides reliable defaults when you don’t override them.
You now have the foundation for advanced prompt customizations in CrewAI. Whether you’re adapting for model-specific structures or domain-specific constraints, this low-level approach lets you shape agent interactions in highly specialized ways.
# Fingerprinting
Source: https://docs.crewai.com/guides/advanced/fingerprinting
Learn how to use CrewAI's fingerprinting system to uniquely identify and track components throughout their lifecycle.
# Fingerprinting in CrewAI
## Overview
Fingerprints in CrewAI provide a way to uniquely identify and track components throughout their lifecycle. Each `Agent`, `Crew`, and `Task` automatically receives a unique fingerprint when created, which cannot be manually overridden.
These fingerprints can be used for:
* Auditing and tracking component usage
* Ensuring component identity integrity
* Attaching metadata to components
* Creating a traceable chain of operations
## How Fingerprints Work
A fingerprint is an instance of the `Fingerprint` class from the `crewai.security` module. Each fingerprint contains:
* A UUID string: A unique identifier for the component that is automatically generated and cannot be manually set
* A creation timestamp: When the fingerprint was generated, automatically set and cannot be manually modified
* Metadata: A dictionary of additional information that can be customized
Fingerprints are automatically generated and assigned when a component is created. Each component exposes its fingerprint through a read-only property.
## Basic Usage
### Accessing Fingerprints
```python
from crewai import Agent, Crew, Task
# Create components - fingerprints are automatically generated
agent = Agent(
role="Data Scientist",
goal="Analyze data",
backstory="Expert in data analysis"
)
crew = Crew(
agents=[agent],
tasks=[]
)
task = Task(
description="Analyze customer data",
expected_output="Insights from data analysis",
agent=agent
)
# Access the fingerprints
agent_fingerprint = agent.fingerprint
crew_fingerprint = crew.fingerprint
task_fingerprint = task.fingerprint
# Print the UUID strings
print(f"Agent fingerprint: {agent_fingerprint.uuid_str}")
print(f"Crew fingerprint: {crew_fingerprint.uuid_str}")
print(f"Task fingerprint: {task_fingerprint.uuid_str}")
```
### Working with Fingerprint Metadata
You can add metadata to fingerprints for additional context:
```python
# Add metadata to the agent's fingerprint
agent.security_config.fingerprint.metadata = {
"version": "1.0",
"department": "Data Science",
"project": "Customer Analysis"
}
# Access the metadata
print(f"Agent metadata: {agent.fingerprint.metadata}")
```
## Fingerprint Persistence
Fingerprints are designed to persist and remain unchanged throughout a component's lifecycle. If you modify a component, the fingerprint remains the same:
```python
original_fingerprint = agent.fingerprint.uuid_str
# Modify the agent
agent.goal = "New goal for analysis"
# The fingerprint remains unchanged
assert agent.fingerprint.uuid_str == original_fingerprint
```
## Deterministic Fingerprints
While you cannot directly set the UUID and creation timestamp, you can create deterministic fingerprints using the `generate` method with a seed:
```python
from crewai.security import Fingerprint
# Create a deterministic fingerprint using a seed string
deterministic_fingerprint = Fingerprint.generate(seed="my-agent-id")
# The same seed always produces the same fingerprint
same_fingerprint = Fingerprint.generate(seed="my-agent-id")
assert deterministic_fingerprint.uuid_str == same_fingerprint.uuid_str
# You can also set metadata
custom_fingerprint = Fingerprint.generate(
seed="my-agent-id",
metadata={"version": "1.0"}
)
```
## Advanced Usage
### Fingerprint Structure
Each fingerprint has the following structure:
```python
from crewai.security import Fingerprint
fingerprint = agent.fingerprint
# UUID string - the unique identifier (auto-generated)
uuid_str = fingerprint.uuid_str # e.g., "123e4567-e89b-12d3-a456-426614174000"
# Creation timestamp (auto-generated)
created_at = fingerprint.created_at # A datetime object
# Metadata - for additional information (can be customized)
metadata = fingerprint.metadata # A dictionary, defaults to {}
```
# Crafting Effective Agents
Source: https://docs.crewai.com/guides/agents/crafting-effective-agents
Learn best practices for designing powerful, specialized AI agents that collaborate effectively to solve complex problems.
# Crafting Effective Agents
## The Art and Science of Agent Design
At the heart of CrewAI lies the agent - a specialized AI entity designed to perform specific roles within a collaborative framework. While creating basic agents is simple, crafting truly effective agents that produce exceptional results requires understanding key design principles and best practices.
This guide will help you master the art of agent design, enabling you to create specialized AI personas that collaborate effectively, think critically, and produce high-quality outputs tailored to your specific needs.
### Why Agent Design Matters
The way you define your agents significantly impacts:
1. **Output quality**: Well-designed agents produce more relevant, high-quality results
2. **Collaboration effectiveness**: Agents with complementary skills work together more efficiently
3. **Task performance**: Agents with clear roles and goals execute tasks more effectively
4. **System scalability**: Thoughtfully designed agents can be reused across multiple crews and contexts
Let's explore best practices for creating agents that excel in these dimensions.
## The 80/20 Rule: Focus on Tasks Over Agents
When building effective AI systems, remember this crucial principle: **80% of your effort should go into designing tasks, and only 20% into defining agents**.
Why? Because even the most perfectly defined agent will fail with poorly designed tasks, but well-designed tasks can elevate even a simple agent. This means:
* Spend most of your time writing clear task instructions
* Define detailed inputs and expected outputs
* Add examples and context to guide execution
* Dedicate the remaining time to agent role, goal, and backstory
This doesn't mean agent design isn't important - it absolutely is. But task design is where most execution failures occur, so prioritize accordingly.
## Core Principles of Effective Agent Design
### 1. The Role-Goal-Backstory Framework
The most powerful agents in CrewAI are built on a strong foundation of three key elements:
#### Role: The Agent's Specialized Function
The role defines what the agent does and their area of expertise. When crafting roles:
* **Be specific and specialized**: Instead of "Writer," use "Technical Documentation Specialist" or "Creative Storyteller"
* **Align with real-world professions**: Base roles on recognizable professional archetypes
* **Include domain expertise**: Specify the agent's field of knowledge (e.g., "Financial Analyst specializing in market trends")
**Examples of effective roles:**
```yaml
role: "Senior UX Researcher specializing in user interview analysis"
role: "Full-Stack Software Architect with expertise in distributed systems"
role: "Corporate Communications Director specializing in crisis management"
```
#### Goal: The Agent's Purpose and Motivation
The goal directs the agent's efforts and shapes their decision-making process. Effective goals should:
* **Be clear and outcome-focused**: Define what the agent is trying to achieve
* **Emphasize quality standards**: Include expectations about the quality of work
* **Incorporate success criteria**: Help the agent understand what "good" looks like
**Examples of effective goals:**
```yaml
goal: "Uncover actionable user insights by analyzing interview data and identifying recurring patterns, unmet needs, and improvement opportunities"
goal: "Design robust, scalable system architectures that balance performance, maintainability, and cost-effectiveness"
goal: "Craft clear, empathetic crisis communications that address stakeholder concerns while protecting organizational reputation"
```
#### Backstory: The Agent's Experience and Perspective
The backstory gives depth to the agent, influencing how they approach problems and interact with others. Good backstories:
* **Establish expertise and experience**: Explain how the agent gained their skills
* **Define working style and values**: Describe how the agent approaches their work
* **Create a cohesive persona**: Ensure all elements of the backstory align with the role and goal
**Examples of effective backstories:**
```yaml
backstory: "You have spent 15 years conducting and analyzing user research for top tech companies. You have a talent for reading between the lines and identifying patterns that others miss. You believe that good UX is invisible and that the best insights come from listening to what users don't say as much as what they do say."
backstory: "With 20+ years of experience building distributed systems at scale, you've developed a pragmatic approach to software architecture. You've seen both successful and failed systems and have learned valuable lessons from each. You balance theoretical best practices with practical constraints and always consider the maintenance and operational aspects of your designs."
backstory: "As a seasoned communications professional who has guided multiple organizations through high-profile crises, you understand the importance of transparency, speed, and empathy in crisis response. You have a methodical approach to crafting messages that address concerns while maintaining organizational credibility."
```
### 2. Specialists Over Generalists
Agents perform significantly better when given specialized roles rather than general ones. A highly focused agent delivers more precise, relevant outputs:
**Generic (Less Effective):**
```yaml
role: "Writer"
```
**Specialized (More Effective):**
```yaml
role: "Technical Blog Writer specializing in explaining complex AI concepts to non-technical audiences"
```
**Specialist Benefits:**
* Clearer understanding of expected output
* More consistent performance
* Better alignment with specific tasks
* Improved ability to make domain-specific judgments
### 3. Balancing Specialization and Versatility
Effective agents strike the right balance between specialization (doing one thing extremely well) and versatility (being adaptable to various situations):
* **Specialize in role, versatile in application**: Create agents with specialized skills that can be applied across multiple contexts
* **Avoid overly narrow definitions**: Ensure agents can handle variations within their domain of expertise
* **Consider the collaborative context**: Design agents whose specializations complement the other agents they'll work with
### 4. Setting Appropriate Expertise Levels
The expertise level you assign to your agent shapes how they approach tasks:
* **Novice agents**: Good for straightforward tasks, brainstorming, or initial drafts
* **Intermediate agents**: Suitable for most standard tasks with reliable execution
* **Expert agents**: Best for complex, specialized tasks requiring depth and nuance
* **World-class agents**: Reserved for critical tasks where exceptional quality is needed
Choose the appropriate expertise level based on task complexity and quality requirements. For most collaborative crews, a mix of expertise levels often works best, with higher expertise assigned to core specialized functions.
## Practical Examples: Before and After
Let's look at some examples of agent definitions before and after applying these best practices:
### Example 1: Content Creation Agent
**Before:**
```yaml
role: "Writer"
goal: "Write good content"
backstory: "You are a writer who creates content for websites."
```
**After:**
```yaml
role: "B2B Technology Content Strategist"
goal: "Create compelling, technically accurate content that explains complex topics in accessible language while driving reader engagement and supporting business objectives"
backstory: "You have spent a decade creating content for leading technology companies, specializing in translating technical concepts for business audiences. You excel at research, interviewing subject matter experts, and structuring information for maximum clarity and impact. You believe that the best B2B content educates first and sells second, building trust through genuine expertise rather than marketing hype."
```
### Example 2: Research Agent
**Before:**
```yaml
role: "Researcher"
goal: "Find information"
backstory: "You are good at finding information online."
```
**After:**
```yaml
role: "Academic Research Specialist in Emerging Technologies"
goal: "Discover and synthesize cutting-edge research, identifying key trends, methodologies, and findings while evaluating the quality and reliability of sources"
backstory: "With a background in both computer science and library science, you've mastered the art of digital research. You've worked with research teams at prestigious universities and know how to navigate academic databases, evaluate research quality, and synthesize findings across disciplines. You're methodical in your approach, always cross-referencing information and tracing claims to primary sources before drawing conclusions."
```
## Crafting Effective Tasks for Your Agents
While agent design is important, task design is critical for successful execution. Here are best practices for designing tasks that set your agents up for success:
### The Anatomy of an Effective Task
A well-designed task has two key components that serve different purposes:
#### Task Description: The Process
The description should focus on what to do and how to do it, including:
* Detailed instructions for execution
* Context and background information
* Scope and constraints
* Process steps to follow
#### Expected Output: The Deliverable
The expected output should define what the final result should look like:
* Format specifications (markdown, JSON, etc.)
* Structure requirements
* Quality criteria
* Examples of good outputs (when possible)
### Task Design Best Practices
#### 1. Single Purpose, Single Output
Tasks perform best when focused on one clear objective:
**Bad Example (Too Broad):**
```yaml
task_description: "Research market trends, analyze the data, and create a visualization."
```
**Good Example (Focused):**
```yaml
# Task 1
research_task:
description: "Research the top 5 market trends in the AI industry for 2024."
expected_output: "A markdown list of the 5 trends with supporting evidence."
# Task 2
analysis_task:
description: "Analyze the identified trends to determine potential business impacts."
expected_output: "A structured analysis with impact ratings (High/Medium/Low)."
# Task 3
visualization_task:
description: "Create a visual representation of the analyzed trends."
expected_output: "A description of a chart showing trends and their impact ratings."
```
#### 2. Be Explicit About Inputs and Outputs
Always clearly specify what inputs the task will use and what the output should look like:
**Example:**
```yaml
analysis_task:
description: >
Analyze the customer feedback data from the CSV file.
Focus on identifying recurring themes related to product usability.
Consider sentiment and frequency when determining importance.
expected_output: >
A markdown report with the following sections:
1. Executive summary (3-5 bullet points)
2. Top 3 usability issues with supporting data
3. Recommendations for improvement
```
#### 3. Include Purpose and Context
Explain why the task matters and how it fits into the larger workflow:
**Example:**
```yaml
competitor_analysis_task:
description: >
Analyze our three main competitors' pricing strategies.
This analysis will inform our upcoming pricing model revision.
Focus on identifying patterns in how they price premium features
and how they structure their tiered offerings.
```
#### 4. Use Structured Output Tools
For machine-readable outputs, specify the format clearly:
**Example:**
```yaml
data_extraction_task:
description: "Extract key metrics from the quarterly report."
expected_output: "JSON object with the following keys: revenue, growth_rate, customer_acquisition_cost, and retention_rate."
```
## Common Mistakes to Avoid
Based on lessons learned from real-world implementations, here are the most common pitfalls in agent and task design:
### 1. Unclear Task Instructions
**Problem:** Tasks lack sufficient detail, making it difficult for agents to execute effectively.
**Example of Poor Design:**
```yaml
research_task:
description: "Research AI trends."
expected_output: "A report on AI trends."
```
**Improved Version:**
```yaml
research_task:
description: >
Research the top emerging AI trends for 2024 with a focus on:
1. Enterprise adoption patterns
2. Technical breakthroughs in the past 6 months
3. Regulatory developments affecting implementation
For each trend, identify key companies, technologies, and potential business impacts.
expected_output: >
A comprehensive markdown report with:
- Executive summary (5 bullet points)
- 5-7 major trends with supporting evidence
- For each trend: definition, examples, and business implications
- References to authoritative sources
```
### 2. "God Tasks" That Try to Do Too Much
**Problem:** Tasks that combine multiple complex operations into one instruction set.
**Example of Poor Design:**
```yaml
comprehensive_task:
description: "Research market trends, analyze competitor strategies, create a marketing plan, and design a launch timeline."
```
**Improved Version:**
Break this into sequential, focused tasks:
```yaml
# Task 1: Research
market_research_task:
description: "Research current market trends in the SaaS project management space."
expected_output: "A markdown summary of key market trends."
# Task 2: Competitive Analysis
competitor_analysis_task:
description: "Analyze strategies of the top 3 competitors based on the market research."
expected_output: "A comparison table of competitor strategies."
context: [market_research_task]
# Continue with additional focused tasks...
```
### 3. Misaligned Description and Expected Output
**Problem:** The task description asks for one thing while the expected output specifies something different.
**Example of Poor Design:**
```yaml
analysis_task:
description: "Analyze customer feedback to find areas of improvement."
expected_output: "A marketing plan for the next quarter."
```
**Improved Version:**
```yaml
analysis_task:
description: "Analyze customer feedback to identify the top 3 areas for product improvement."
expected_output: "A report listing the 3 priority improvement areas with supporting customer quotes and data points."
```
### 4. Not Understanding the Process Yourself
**Problem:** Asking agents to execute tasks that you yourself don't fully understand.
**Solution:**
1. Try to perform the task manually first
2. Document your process, decision points, and information sources
3. Use this documentation as the basis for your task description
### 5. Premature Use of Hierarchical Structures
**Problem:** Creating unnecessarily complex agent hierarchies where sequential processes would work better.
**Solution:** Start with sequential processes and only move to hierarchical models when the workflow complexity truly requires it.
### 6. Vague or Generic Agent Definitions
**Problem:** Generic agent definitions lead to generic outputs.
**Example of Poor Design:**
```yaml
agent:
role: "Business Analyst"
goal: "Analyze business data"
backstory: "You are good at business analysis."
```
**Improved Version:**
```yaml
agent:
role: "SaaS Metrics Specialist focusing on growth-stage startups"
goal: "Identify actionable insights from business data that can directly impact customer retention and revenue growth"
backstory: "With 10+ years analyzing SaaS business models, you've developed a keen eye for the metrics that truly matter for sustainable growth. You've helped numerous companies identify the leverage points that turned around their business trajectory. You believe in connecting data to specific, actionable recommendations rather than general observations."
```
## Advanced Agent Design Strategies
### Designing for Collaboration
When creating agents that will work together in a crew, consider:
* **Complementary skills**: Design agents with distinct but complementary abilities
* **Handoff points**: Define clear interfaces for how work passes between agents
* **Constructive tension**: Sometimes, creating agents with slightly different perspectives can lead to better outcomes through productive dialogue
For example, a content creation crew might include:
```yaml
# Research Agent
role: "Research Specialist for technical topics"
goal: "Gather comprehensive, accurate information from authoritative sources"
backstory: "You are a meticulous researcher with a background in library science..."
# Writer Agent
role: "Technical Content Writer"
goal: "Transform research into engaging, clear content that educates and informs"
backstory: "You are an experienced writer who excels at explaining complex concepts..."
# Editor Agent
role: "Content Quality Editor"
goal: "Ensure content is accurate, well-structured, and polished while maintaining consistency"
backstory: "With years of experience in publishing, you have a keen eye for detail..."
```
### Creating Specialized Tool Users
Some agents can be designed specifically to leverage certain tools effectively:
```yaml
role: "Data Analysis Specialist"
goal: "Derive meaningful insights from complex datasets through statistical analysis"
backstory: "With a background in data science, you excel at working with structured and unstructured data..."
tools: [PythonREPLTool, DataVisualizationTool, CSVAnalysisTool]
```
### Tailoring Agents to LLM Capabilities
Different LLMs have different strengths. Design your agents with these capabilities in mind:
```yaml
# For complex reasoning tasks
analyst:
role: "Data Insights Analyst"
goal: "..."
backstory: "..."
llm: openai/gpt-4o
# For creative content
writer:
role: "Creative Content Writer"
goal: "..."
backstory: "..."
llm: anthropic/claude-3-opus
```
## Testing and Iterating on Agent Design
Agent design is often an iterative process. Here's a practical approach:
1. **Start with a prototype**: Create an initial agent definition
2. **Test with sample tasks**: Evaluate performance on representative tasks
3. **Analyze outputs**: Identify strengths and weaknesses
4. **Refine the definition**: Adjust role, goal, and backstory based on observations
5. **Test in collaboration**: Evaluate how the agent performs in a crew setting
## Conclusion
Crafting effective agents is both an art and a science. By carefully defining roles, goals, and backstories that align with your specific needs, and combining them with well-designed tasks, you can create specialized AI collaborators that produce exceptional results.
Remember that agent and task design is an iterative process. Start with these best practices, observe your agents in action, and refine your approach based on what you learn. And always keep in mind the 80/20 rule - focus most of your effort on creating clear, focused tasks to get the best results from your agents.
Congratulations! You now understand the principles and practices of effective agent design. Apply these techniques to create powerful, specialized agents that work together seamlessly to accomplish complex tasks.
## Next Steps
* Experiment with different agent configurations for your specific use case
* Learn about [building your first crew](/guides/crews/first-crew) to see how agents work together
* Explore [CrewAI Flows](/guides/flows/first-flow) for more advanced orchestration
# Evaluating Use Cases for CrewAI
Source: https://docs.crewai.com/guides/concepts/evaluating-use-cases
Learn how to assess your AI application needs and choose the right approach between Crews and Flows based on complexity and precision requirements.
# Evaluating Use Cases for CrewAI
## Understanding the Decision Framework
When building AI applications with CrewAI, one of the most important decisions you'll make is choosing the right approach for your specific use case. Should you use a Crew? A Flow? A combination of both? This guide will help you evaluate your requirements and make informed architectural decisions.
At the heart of this decision is understanding the relationship between **complexity** and **precision** in your application:
This matrix helps visualize how different approaches align with varying requirements for complexity and precision. Let's explore what each quadrant means and how it guides your architectural choices.
## The Complexity-Precision Matrix Explained
### What is Complexity?
In the context of CrewAI applications, **complexity** refers to:
* The number of distinct steps or operations required
* The diversity of tasks that need to be performed
* The interdependencies between different components
* The need for conditional logic and branching
* The sophistication of the overall workflow
### What is Precision?
**Precision** in this context refers to:
* The accuracy required in the final output
* The need for structured, predictable results
* The importance of reproducibility
* The level of control needed over each step
* The tolerance for variation in outputs
### The Four Quadrants
#### 1. Low Complexity, Low Precision
**Characteristics:**
* Simple, straightforward tasks
* Tolerance for some variation in outputs
* Limited number of steps
* Creative or exploratory applications
**Recommended Approach:** Simple Crews with minimal agents
**Example Use Cases:**
* Basic content generation
* Idea brainstorming
* Simple summarization tasks
* Creative writing assistance
#### 2. Low Complexity, High Precision
**Characteristics:**
* Simple workflows that require exact, structured outputs
* Need for reproducible results
* Limited steps but high accuracy requirements
* Often involves data processing or transformation
**Recommended Approach:** Flows with direct LLM calls or simple Crews with structured outputs
**Example Use Cases:**
* Data extraction and transformation
* Form filling and validation
* Structured content generation (JSON, XML)
* Simple classification tasks
#### 3. High Complexity, Low Precision
**Characteristics:**
* Multi-stage processes with many steps
* Creative or exploratory outputs
* Complex interactions between components
* Tolerance for variation in final results
**Recommended Approach:** Complex Crews with multiple specialized agents
**Example Use Cases:**
* Research and analysis
* Content creation pipelines
* Exploratory data analysis
* Creative problem-solving
#### 4. High Complexity, High Precision
**Characteristics:**
* Complex workflows requiring structured outputs
* Multiple interdependent steps with strict accuracy requirements
* Need for both sophisticated processing and precise results
* Often mission-critical applications
**Recommended Approach:** Flows orchestrating multiple Crews with validation steps
**Example Use Cases:**
* Enterprise decision support systems
* Complex data processing pipelines
* Multi-stage document processing
* Regulated industry applications
## Choosing Between Crews and Flows
### When to Choose Crews
Crews are ideal when:
1. **You need collaborative intelligence** - Multiple agents with different specializations need to work together
2. **The problem requires emergent thinking** - The solution benefits from different perspectives and approaches
3. **The task is primarily creative or analytical** - The work involves research, content creation, or analysis
4. **You value adaptability over strict structure** - The workflow can benefit from agent autonomy
5. **The output format can be somewhat flexible** - Some variation in output structure is acceptable
```python
# Example: Research Crew for market analysis
from crewai import Agent, Crew, Process, Task
# Create specialized agents
researcher = Agent(
role="Market Research Specialist",
goal="Find comprehensive market data on emerging technologies",
backstory="You are an expert at discovering market trends and gathering data."
)
analyst = Agent(
role="Market Analyst",
goal="Analyze market data and identify key opportunities",
backstory="You excel at interpreting market data and spotting valuable insights."
)
# Define their tasks
research_task = Task(
description="Research the current market landscape for AI-powered healthcare solutions",
expected_output="Comprehensive market data including key players, market size, and growth trends",
agent=researcher
)
analysis_task = Task(
description="Analyze the market data and identify the top 3 investment opportunities",
expected_output="Analysis report with 3 recommended investment opportunities and rationale",
agent=analyst,
context=[research_task]
)
# Create the crew
market_analysis_crew = Crew(
agents=[researcher, analyst],
tasks=[research_task, analysis_task],
process=Process.sequential,
verbose=True
)
# Run the crew
result = market_analysis_crew.kickoff()
```
### When to Choose Flows
Flows are ideal when:
1. **You need precise control over execution** - The workflow requires exact sequencing and state management
2. **The application has complex state requirements** - You need to maintain and transform state across multiple steps
3. **You need structured, predictable outputs** - The application requires consistent, formatted results
4. **The workflow involves conditional logic** - Different paths need to be taken based on intermediate results
5. **You need to combine AI with procedural code** - The solution requires both AI capabilities and traditional programming
```python
# Example: Customer Support Flow with structured processing
from crewai.flow.flow import Flow, listen, router, start
from pydantic import BaseModel
from typing import List, Dict
# Define structured state
class SupportTicketState(BaseModel):
ticket_id: str = ""
customer_name: str = ""
issue_description: str = ""
category: str = ""
priority: str = "medium"
resolution: str = ""
satisfaction_score: int = 0
class CustomerSupportFlow(Flow[SupportTicketState]):
@start()
def receive_ticket(self):
# In a real app, this might come from an API
self.state.ticket_id = "TKT-12345"
self.state.customer_name = "Alex Johnson"
self.state.issue_description = "Unable to access premium features after payment"
return "Ticket received"
@listen(receive_ticket)
def categorize_ticket(self, _):
# Use a direct LLM call for categorization
from crewai import LLM
llm = LLM(model="openai/gpt-4o-mini")
prompt = f"""
Categorize the following customer support issue into one of these categories:
- Billing
- Account Access
- Technical Issue
- Feature Request
- Other
Issue: {self.state.issue_description}
Return only the category name.
"""
self.state.category = llm.call(prompt).strip()
return self.state.category
@router(categorize_ticket)
def route_by_category(self, category):
# Route to different handlers based on category
return category.lower().replace(" ", "_")
@listen("billing")
def handle_billing_issue(self):
# Handle billing-specific logic
self.state.priority = "high"
# More billing-specific processing...
return "Billing issue handled"
@listen("account_access")
def handle_access_issue(self):
# Handle access-specific logic
self.state.priority = "high"
# More access-specific processing...
return "Access issue handled"
# Additional category handlers...
@listen("billing", "account_access", "technical_issue", "feature_request", "other")
def resolve_ticket(self, resolution_info):
# Final resolution step
self.state.resolution = f"Issue resolved: {resolution_info}"
return self.state.resolution
# Run the flow
support_flow = CustomerSupportFlow()
result = support_flow.kickoff()
```
### When to Combine Crews and Flows
The most sophisticated applications often benefit from combining Crews and Flows:
1. **Complex multi-stage processes** - Use Flows to orchestrate the overall process and Crews for complex subtasks
2. **Applications requiring both creativity and structure** - Use Crews for creative tasks and Flows for structured processing
3. **Enterprise-grade AI applications** - Use Flows to manage state and process flow while leveraging Crews for specialized work
```python
# Example: Content Production Pipeline combining Crews and Flows
from crewai.flow.flow import Flow, listen, start
from crewai import Agent, Crew, Process, Task
from pydantic import BaseModel
from typing import List, Dict
class ContentState(BaseModel):
topic: str = ""
target_audience: str = ""
content_type: str = ""
outline: Dict = {}
draft_content: str = ""
final_content: str = ""
seo_score: int = 0
class ContentProductionFlow(Flow[ContentState]):
@start()
def initialize_project(self):
# Set initial parameters
self.state.topic = "Sustainable Investing"
self.state.target_audience = "Millennial Investors"
self.state.content_type = "Blog Post"
return "Project initialized"
@listen(initialize_project)
def create_outline(self, _):
# Use a research crew to create an outline
researcher = Agent(
role="Content Researcher",
goal=f"Research {self.state.topic} for {self.state.target_audience}",
backstory="You are an expert researcher with deep knowledge of content creation."
)
outliner = Agent(
role="Content Strategist",
goal=f"Create an engaging outline for a {self.state.content_type}",
backstory="You excel at structuring content for maximum engagement."
)
research_task = Task(
description=f"Research {self.state.topic} focusing on what would interest {self.state.target_audience}",
expected_output="Comprehensive research notes with key points and statistics",
agent=researcher
)
outline_task = Task(
description=f"Create an outline for a {self.state.content_type} about {self.state.topic}",
expected_output="Detailed content outline with sections and key points",
agent=outliner,
context=[research_task]
)
outline_crew = Crew(
agents=[researcher, outliner],
tasks=[research_task, outline_task],
process=Process.sequential,
verbose=True
)
# Run the crew and store the result
result = outline_crew.kickoff()
# Parse the outline (in a real app, you might use a more robust parsing approach)
import json
try:
self.state.outline = json.loads(result.raw)
except:
# Fallback if not valid JSON
self.state.outline = {"sections": result.raw}
return "Outline created"
@listen(create_outline)
def write_content(self, _):
# Use a writing crew to create the content
writer = Agent(
role="Content Writer",
goal=f"Write engaging content for {self.state.target_audience}",
backstory="You are a skilled writer who creates compelling content."
)
editor = Agent(
role="Content Editor",
goal="Ensure content is polished, accurate, and engaging",
backstory="You have a keen eye for detail and a talent for improving content."
)
writing_task = Task(
description=f"Write a {self.state.content_type} about {self.state.topic} following this outline: {self.state.outline}",
expected_output="Complete draft content in markdown format",
agent=writer
)
editing_task = Task(
description="Edit and improve the draft content for clarity, engagement, and accuracy",
expected_output="Polished final content in markdown format",
agent=editor,
context=[writing_task]
)
writing_crew = Crew(
agents=[writer, editor],
tasks=[writing_task, editing_task],
process=Process.sequential,
verbose=True
)
# Run the crew and store the result
result = writing_crew.kickoff()
self.state.final_content = result.raw
return "Content created"
@listen(write_content)
def optimize_for_seo(self, _):
# Use a direct LLM call for SEO optimization
from crewai import LLM
llm = LLM(model="openai/gpt-4o-mini")
prompt = f"""
Analyze this content for SEO effectiveness for the keyword "{self.state.topic}".
Rate it on a scale of 1-100 and provide 3 specific recommendations for improvement.
Content: {self.state.final_content[:1000]}... (truncated for brevity)
Format your response as JSON with the following structure:
{{
"score": 85,
"recommendations": [
"Recommendation 1",
"Recommendation 2",
"Recommendation 3"
]
}}
"""
seo_analysis = llm.call(prompt)
# Parse the SEO analysis
import json
try:
analysis = json.loads(seo_analysis)
self.state.seo_score = analysis.get("score", 0)
return analysis
except:
self.state.seo_score = 50
return {"score": 50, "recommendations": ["Unable to parse SEO analysis"]}
# Run the flow
content_flow = ContentProductionFlow()
result = content_flow.kickoff()
```
## Practical Evaluation Framework
To determine the right approach for your specific use case, follow this step-by-step evaluation framework:
### Step 1: Assess Complexity
Rate your application's complexity on a scale of 1-10 by considering:
1. **Number of steps**: How many distinct operations are required?
* 1-3 steps: Low complexity (1-3)
* 4-7 steps: Medium complexity (4-7)
* 8+ steps: High complexity (8-10)
2. **Interdependencies**: How interconnected are the different parts?
* Few dependencies: Low complexity (1-3)
* Some dependencies: Medium complexity (4-7)
* Many complex dependencies: High complexity (8-10)
3. **Conditional logic**: How much branching and decision-making is needed?
* Linear process: Low complexity (1-3)
* Some branching: Medium complexity (4-7)
* Complex decision trees: High complexity (8-10)
4. **Domain knowledge**: How specialized is the knowledge required?
* General knowledge: Low complexity (1-3)
* Some specialized knowledge: Medium complexity (4-7)
* Deep expertise in multiple domains: High complexity (8-10)
Calculate your average score to determine overall complexity.
### Step 2: Assess Precision Requirements
Rate your precision requirements on a scale of 1-10 by considering:
1. **Output structure**: How structured must the output be?
* Free-form text: Low precision (1-3)
* Semi-structured: Medium precision (4-7)
* Strictly formatted (JSON, XML): High precision (8-10)
2. **Accuracy needs**: How important is factual accuracy?
* Creative content: Low precision (1-3)
* Informational content: Medium precision (4-7)
* Critical information: High precision (8-10)
3. **Reproducibility**: How consistent must results be across runs?
* Variation acceptable: Low precision (1-3)
* Some consistency needed: Medium precision (4-7)
* Exact reproducibility required: High precision (8-10)
4. **Error tolerance**: What is the impact of errors?
* Low impact: Low precision (1-3)
* Moderate impact: Medium precision (4-7)
* High impact: High precision (8-10)
Calculate your average score to determine overall precision requirements.
### Step 3: Map to the Matrix
Plot your complexity and precision scores on the matrix:
* **Low Complexity (1-4), Low Precision (1-4)**: Simple Crews
* **Low Complexity (1-4), High Precision (5-10)**: Flows with direct LLM calls
* **High Complexity (5-10), Low Precision (1-4)**: Complex Crews
* **High Complexity (5-10), High Precision (5-10)**: Flows orchestrating Crews
### Step 4: Consider Additional Factors
Beyond complexity and precision, consider:
1. **Development time**: Crews are often faster to prototype
2. **Maintenance needs**: Flows provide better long-term maintainability
3. **Team expertise**: Consider your team's familiarity with different approaches
4. **Scalability requirements**: Flows typically scale better for complex applications
5. **Integration needs**: Consider how the solution will integrate with existing systems
## Conclusion
Choosing between Crews and Flows—or combining them—is a critical architectural decision that impacts the effectiveness, maintainability, and scalability of your CrewAI application. By evaluating your use case along the dimensions of complexity and precision, you can make informed decisions that align with your specific requirements.
Remember that the best approach often evolves as your application matures. Start with the simplest solution that meets your needs, and be prepared to refine your architecture as you gain experience and your requirements become clearer.
You now have a framework for evaluating CrewAI use cases and choosing the right approach based on complexity and precision requirements. This will help you build more effective, maintainable, and scalable AI applications.
## Next Steps
* Learn more about [crafting effective agents](/guides/agents/crafting-effective-agents)
* Explore [building your first crew](/guides/crews/first-crew)
* Dive into [mastering flow state management](/guides/flows/mastering-flow-state)
* Check out the [core concepts](/concepts/agents) for deeper understanding
# Build Your First Crew
Source: https://docs.crewai.com/guides/crews/first-crew
Step-by-step tutorial to create a collaborative AI team that works together to solve complex problems.
# Build Your First Crew
## Unleashing the Power of Collaborative AI
Imagine having a team of specialized AI agents working together seamlessly to solve complex problems, each contributing their unique skills to achieve a common goal. This is the power of CrewAI - a framework that enables you to create collaborative AI systems that can accomplish tasks far beyond what a single AI could achieve alone.
In this guide, we'll walk through creating a research crew that will help us research and analyze a topic, then create a comprehensive report. This practical example demonstrates how AI agents can collaborate to accomplish complex tasks, but it's just the beginning of what's possible with CrewAI.
### What You'll Build and Learn
By the end of this guide, you'll have:
1. **Created a specialized AI research team** with distinct roles and responsibilities
2. **Orchestrated collaboration** between multiple AI agents
3. **Automated a complex workflow** that involves gathering information, analysis, and report generation
4. **Built foundational skills** that you can apply to more ambitious projects
While we're building a simple research crew in this guide, the same patterns and techniques can be applied to create much more sophisticated teams for tasks like:
* Multi-stage content creation with specialized writers, editors, and fact-checkers
* Complex customer service systems with tiered support agents
* Autonomous business analysts that gather data, create visualizations, and generate insights
* Product development teams that ideate, design, and plan implementation
Let's get started building your first crew!
### Prerequisites
Before starting, make sure you have:
1. Installed CrewAI following the [installation guide](/installation)
2. Set up your OpenAI API key in your environment variables
3. Basic understanding of Python
## Step 1: Create a New CrewAI Project
First, let's create a new CrewAI project using the CLI. This command will set up a complete project structure with all the necessary files, allowing you to focus on defining your agents and their tasks rather than setting up boilerplate code.
```bash
crewai create crew research_crew
cd research_crew
```
This will generate a project with the basic structure needed for your crew. The CLI automatically creates:
* A project directory with the necessary files
* Configuration files for agents and tasks
* A basic crew implementation
* A main script to run the crew
## Step 2: Explore the Project Structure
Let's take a moment to understand the project structure created by the CLI. CrewAI follows best practices for Python projects, making it easy to maintain and extend your code as your crews become more complex.
```
research_crew/
├── .gitignore
├── pyproject.toml
├── README.md
├── .env
└── src/
└── research_crew/
├── __init__.py
├── main.py
├── crew.py
├── tools/
│ ├── custom_tool.py
│ └── __init__.py
└── config/
├── agents.yaml
└── tasks.yaml
```
This structure follows best practices for Python projects and makes it easy to organize your code. The separation of configuration files (in YAML) from implementation code (in Python) makes it easy to modify your crew's behavior without changing the underlying code.
## Step 3: Configure Your Agents
Now comes the fun part - defining your AI agents! In CrewAI, agents are specialized entities with specific roles, goals, and backstories that shape their behavior. Think of them as characters in a play, each with their own personality and purpose.
For our research crew, we'll create two agents:
1. A **researcher** who excels at finding and organizing information
2. An **analyst** who can interpret research findings and create insightful reports
Let's modify the `agents.yaml` file to define these specialized agents:
```yaml
# src/research_crew/config/agents.yaml
researcher:
role: >
Senior Research Specialist for {topic}
goal: >
Find comprehensive and accurate information about {topic}
with a focus on recent developments and key insights
backstory: >
You are an experienced research specialist with a talent for
finding relevant information from various sources. You excel at
organizing information in a clear and structured manner, making
complex topics accessible to others.
llm: openai/gpt-4o-mini
analyst:
role: >
Data Analyst and Report Writer for {topic}
goal: >
Analyze research findings and create a comprehensive, well-structured
report that presents insights in a clear and engaging way
backstory: >
You are a skilled analyst with a background in data interpretation
and technical writing. You have a talent for identifying patterns
and extracting meaningful insights from research data, then
communicating those insights effectively through well-crafted reports.
llm: openai/gpt-4o-mini
```
Notice how each agent has a distinct role, goal, and backstory. These elements aren't just descriptive - they actively shape how the agent approaches its tasks. By crafting these carefully, you can create agents with specialized skills and perspectives that complement each other.
## Step 4: Define Your Tasks
With our agents defined, we now need to give them specific tasks to perform. Tasks in CrewAI represent the concrete work that agents will perform, with detailed instructions and expected outputs.
For our research crew, we'll define two main tasks:
1. A **research task** for gathering comprehensive information
2. An **analysis task** for creating an insightful report
Let's modify the `tasks.yaml` file:
```yaml
# src/research_crew/config/tasks.yaml
research_task:
description: >
Conduct thorough research on {topic}. Focus on:
1. Key concepts and definitions
2. Historical development and recent trends
3. Major challenges and opportunities
4. Notable applications or case studies
5. Future outlook and potential developments
Make sure to organize your findings in a structured format with clear sections.
expected_output: >
A comprehensive research document with well-organized sections covering
all the requested aspects of {topic}. Include specific facts, figures,
and examples where relevant.
agent: researcher
analysis_task:
description: >
Analyze the research findings and create a comprehensive report on {topic}.
Your report should:
1. Begin with an executive summary
2. Include all key information from the research
3. Provide insightful analysis of trends and patterns
4. Offer recommendations or future considerations
5. Be formatted in a professional, easy-to-read style with clear headings
expected_output: >
A polished, professional report on {topic} that presents the research
findings with added analysis and insights. The report should be well-structured
with an executive summary, main sections, and conclusion.
agent: analyst
context:
- research_task
output_file: output/report.md
```
Note the `context` field in the analysis task - this is a powerful feature that allows the analyst to access the output of the research task. This creates a workflow where information flows naturally between agents, just as it would in a human team.
## Step 5: Configure Your Crew
Now it's time to bring everything together by configuring our crew. The crew is the container that orchestrates how agents work together to complete tasks.
Let's modify the `crew.py` file:
```python
# src/research_crew/crew.py
from crewai import Agent, Crew, Process, Task
from crewai.project import CrewBase, agent, crew, task
from crewai_tools import SerperDevTool
from crewai.agents.agent_builder.base_agent import BaseAgent
from typing import List
@CrewBase
class ResearchCrew():
"""Research crew for comprehensive topic analysis and reporting"""
agents: List[BaseAgent]
tasks: List[Task]
@agent
def researcher(self) -> Agent:
return Agent(
config=self.agents_config['researcher'], # type: ignore[index]
verbose=True,
tools=[SerperDevTool()]
)
@agent
def analyst(self) -> Agent:
return Agent(
config=self.agents_config['analyst'], # type: ignore[index]
verbose=True
)
@task
def research_task(self) -> Task:
return Task(
config=self.tasks_config['research_task'] # type: ignore[index]
)
@task
def analysis_task(self) -> Task:
return Task(
config=self.tasks_config['analysis_task'], # type: ignore[index]
output_file='output/report.md'
)
@crew
def crew(self) -> Crew:
"""Creates the research crew"""
return Crew(
agents=self.agents,
tasks=self.tasks,
process=Process.sequential,
verbose=True,
)
```
In this code, we're:
1. Creating the researcher agent and equipping it with the SerperDevTool to search the web
2. Creating the analyst agent
3. Setting up the research and analysis tasks
4. Configuring the crew to run tasks sequentially (the analyst will wait for the researcher to finish)
This is where the magic happens - with just a few lines of code, we've defined a collaborative AI system where specialized agents work together in a coordinated process.
## Step 6: Set Up Your Main Script
Now, let's set up the main script that will run our crew. This is where we provide the specific topic we want our crew to research.
```python
#!/usr/bin/env python
# src/research_crew/main.py
import os
from research_crew.crew import ResearchCrew
# Create output directory if it doesn't exist
os.makedirs('output', exist_ok=True)
def run():
"""
Run the research crew.
"""
inputs = {
'topic': 'Artificial Intelligence in Healthcare'
}
# Create and run the crew
result = ResearchCrew().crew().kickoff(inputs=inputs)
# Print the result
print("\n\n=== FINAL REPORT ===\n\n")
print(result.raw)
print("\n\nReport has been saved to output/report.md")
if __name__ == "__main__":
run()
```
This script prepares the environment, specifies our research topic, and kicks off the crew's work. The power of CrewAI is evident in how simple this code is - all the complexity of managing multiple AI agents is handled by the framework.
## Step 7: Set Up Your Environment Variables
Create a `.env` file in your project root with your API keys:
```
OPENAI_API_KEY=your_openai_api_key
SERPER_API_KEY=your_serper_api_key
```
You can get a Serper API key from [Serper.dev](https://serper.dev/).
## Step 8: Install Dependencies
Install the required dependencies using the CrewAI CLI:
```bash
crewai install
```
This command will:
1. Read the dependencies from your project configuration
2. Create a virtual environment if needed
3. Install all required packages
## Step 9: Run Your Crew
Now for the exciting moment - it's time to run your crew and see AI collaboration in action!
```bash
crewai run
```
When you run this command, you'll see your crew spring to life. The researcher will gather information about the specified topic, and the analyst will then create a comprehensive report based on that research. You'll see the agents' thought processes, actions, and outputs in real-time as they work together to complete their tasks.
## Step 10: Review the Output
Once the crew completes its work, you'll find the final report in the `output/report.md` file. The report will include:
1. An executive summary
2. Detailed information about the topic
3. Analysis and insights
4. Recommendations or future considerations
Take a moment to appreciate what you've accomplished - you've created a system where multiple AI agents collaborated on a complex task, each contributing their specialized skills to produce a result that's greater than what any single agent could achieve alone.
## Exploring Other CLI Commands
CrewAI offers several other useful CLI commands for working with crews:
```bash
# View all available commands
crewai --help
# Run the crew
crewai run
# Test the crew
crewai test
# Reset crew memories
crewai reset-memories
# Replay from a specific task
crewai replay -t
```
## The Art of the Possible: Beyond Your First Crew
What you've built in this guide is just the beginning. The skills and patterns you've learned can be applied to create increasingly sophisticated AI systems. Here are some ways you could extend this basic research crew:
### Expanding Your Crew
You could add more specialized agents to your crew:
* A **fact-checker** to verify research findings
* A **data visualizer** to create charts and graphs
* A **domain expert** with specialized knowledge in a particular area
* A **critic** to identify weaknesses in the analysis
### Adding Tools and Capabilities
You could enhance your agents with additional tools:
* Web browsing tools for real-time research
* CSV/database tools for data analysis
* Code execution tools for data processing
* API connections to external services
### Creating More Complex Workflows
You could implement more sophisticated processes:
* Hierarchical processes where manager agents delegate to worker agents
* Iterative processes with feedback loops for refinement
* Parallel processes where multiple agents work simultaneously
* Dynamic processes that adapt based on intermediate results
### Applying to Different Domains
The same patterns can be applied to create crews for:
* **Content creation**: Writers, editors, fact-checkers, and designers working together
* **Customer service**: Triage agents, specialists, and quality control working together
* **Product development**: Researchers, designers, and planners collaborating
* **Data analysis**: Data collectors, analysts, and visualization specialists
## Next Steps
Now that you've built your first crew, you can:
1. Experiment with different agent configurations and personalities
2. Try more complex task structures and workflows
3. Implement custom tools to give your agents new capabilities
4. Apply your crew to different topics or problem domains
5. Explore [CrewAI Flows](/guides/flows/first-flow) for more advanced workflows with procedural programming
Congratulations! You've successfully built your first CrewAI crew that can research and analyze any topic you provide. This foundational experience has equipped you with the skills to create increasingly sophisticated AI systems that can tackle complex, multi-stage problems through collaborative intelligence.
# Build Your First Flow
Source: https://docs.crewai.com/guides/flows/first-flow
Learn how to create structured, event-driven workflows with precise control over execution.
# Build Your First Flow
## Taking Control of AI Workflows with Flows
CrewAI Flows represent the next level in AI orchestration - combining the collaborative power of AI agent crews with the precision and flexibility of procedural programming. While crews excel at agent collaboration, flows give you fine-grained control over exactly how and when different components of your AI system interact.
In this guide, we'll walk through creating a powerful CrewAI Flow that generates a comprehensive learning guide on any topic. This tutorial will demonstrate how Flows provide structured, event-driven control over your AI workflows by combining regular code, direct LLM calls, and crew-based processing.
### What Makes Flows Powerful
Flows enable you to:
1. **Combine different AI interaction patterns** - Use crews for complex collaborative tasks, direct LLM calls for simpler operations, and regular code for procedural logic
2. **Build event-driven systems** - Define how components respond to specific events and data changes
3. **Maintain state across components** - Share and transform data between different parts of your application
4. **Integrate with external systems** - Seamlessly connect your AI workflow with databases, APIs, and user interfaces
5. **Create complex execution paths** - Design conditional branches, parallel processing, and dynamic workflows
### What You'll Build and Learn
By the end of this guide, you'll have:
1. **Created a sophisticated content generation system** that combines user input, AI planning, and multi-agent content creation
2. **Orchestrated the flow of information** between different components of your system
3. **Implemented event-driven architecture** where each step responds to the completion of previous steps
4. **Built a foundation for more complex AI applications** that you can expand and customize
This guide creator flow demonstrates fundamental patterns that can be applied to create much more advanced applications, such as:
* Interactive AI assistants that combine multiple specialized subsystems
* Complex data processing pipelines with AI-enhanced transformations
* Autonomous agents that integrate with external services and APIs
* Multi-stage decision-making systems with human-in-the-loop processes
Let's dive in and build your first flow!
## Prerequisites
Before starting, make sure you have:
1. Installed CrewAI following the [installation guide](/installation)
2. Set up your OpenAI API key in your environment variables
3. Basic understanding of Python
## Step 1: Create a New CrewAI Flow Project
First, let's create a new CrewAI Flow project using the CLI. This command sets up a scaffolded project with all the necessary directories and template files for your flow.
```bash
crewai create flow guide_creator_flow
cd guide_creator_flow
```
This will generate a project with the basic structure needed for your flow.
## Step 2: Understanding the Project Structure
The generated project has the following structure. Take a moment to familiarize yourself with it, as understanding this structure will help you create more complex flows in the future.
```
guide_creator_flow/
├── .gitignore
├── pyproject.toml
├── README.md
├── .env
├── main.py
├── crews/
│ └── poem_crew/
│ ├── config/
│ │ ├── agents.yaml
│ │ └── tasks.yaml
│ └── poem_crew.py
└── tools/
└── custom_tool.py
```
This structure provides a clear separation between different components of your flow:
* The main flow logic in the `main.py` file
* Specialized crews in the `crews` directory
* Custom tools in the `tools` directory
We'll modify this structure to create our guide creator flow, which will orchestrate the process of generating comprehensive learning guides.
## Step 3: Add a Content Writer Crew
Our flow will need a specialized crew to handle the content creation process. Let's use the CrewAI CLI to add a content writer crew:
```bash
crewai flow add-crew content-crew
```
This command automatically creates the necessary directories and template files for your crew. The content writer crew will be responsible for writing and reviewing sections of our guide, working within the overall flow orchestrated by our main application.
## Step 4: Configure the Content Writer Crew
Now, let's modify the generated files for the content writer crew. We'll set up two specialized agents - a writer and a reviewer - that will collaborate to create high-quality content for our guide.
1. First, update the agents configuration file to define our content creation team:
```yaml
# src/guide_creator_flow/crews/content_crew/config/agents.yaml
content_writer:
role: >
Educational Content Writer
goal: >
Create engaging, informative content that thoroughly explains the assigned topic
and provides valuable insights to the reader
backstory: >
You are a talented educational writer with expertise in creating clear, engaging
content. You have a gift for explaining complex concepts in accessible language
and organizing information in a way that helps readers build their understanding.
llm: openai/gpt-4o-mini
content_reviewer:
role: >
Educational Content Reviewer and Editor
goal: >
Ensure content is accurate, comprehensive, well-structured, and maintains
consistency with previously written sections
backstory: >
You are a meticulous editor with years of experience reviewing educational
content. You have an eye for detail, clarity, and coherence. You excel at
improving content while maintaining the original author's voice and ensuring
consistent quality across multiple sections.
llm: openai/gpt-4o-mini
```
These agent definitions establish the specialized roles and perspectives that will shape how our AI agents approach content creation. Notice how each agent has a distinct purpose and expertise.
2. Next, update the tasks configuration file to define the specific writing and reviewing tasks:
```yaml
# src/guide_creator_flow/crews/content_crew/config/tasks.yaml
write_section_task:
description: >
Write a comprehensive section on the topic: "{section_title}"
Section description: {section_description}
Target audience: {audience_level} level learners
Your content should:
1. Begin with a brief introduction to the section topic
2. Explain all key concepts clearly with examples
3. Include practical applications or exercises where appropriate
4. End with a summary of key points
5. Be approximately 500-800 words in length
Format your content in Markdown with appropriate headings, lists, and emphasis.
Previously written sections:
{previous_sections}
Make sure your content maintains consistency with previously written sections
and builds upon concepts that have already been explained.
expected_output: >
A well-structured, comprehensive section in Markdown format that thoroughly
explains the topic and is appropriate for the target audience.
agent: content_writer
review_section_task:
description: >
Review and improve the following section on "{section_title}":
{draft_content}
Target audience: {audience_level} level learners
Previously written sections:
{previous_sections}
Your review should:
1. Fix any grammatical or spelling errors
2. Improve clarity and readability
3. Ensure content is comprehensive and accurate
4. Verify consistency with previously written sections
5. Enhance the structure and flow
6. Add any missing key information
Provide the improved version of the section in Markdown format.
expected_output: >
An improved, polished version of the section that maintains the original
structure but enhances clarity, accuracy, and consistency.
agent: content_reviewer
context:
- write_section_task
```
These task definitions provide detailed instructions to our agents, ensuring they produce content that meets our quality standards. Note how the `context` parameter in the review task creates a workflow where the reviewer has access to the writer's output.
3. Now, update the crew implementation file to define how our agents and tasks work together:
```python
# src/guide_creator_flow/crews/content_crew/content_crew.py
from crewai import Agent, Crew, Process, Task
from crewai.project import CrewBase, agent, crew, task
from crewai.agents.agent_builder.base_agent import BaseAgent
from typing import List
@CrewBase
class ContentCrew():
"""Content writing crew"""
agents: List[BaseAgent]
tasks: List[Task]
@agent
def content_writer(self) -> Agent:
return Agent(
config=self.agents_config['content_writer'], # type: ignore[index]
verbose=True
)
@agent
def content_reviewer(self) -> Agent:
return Agent(
config=self.agents_config['content_reviewer'], # type: ignore[index]
verbose=True
)
@task
def write_section_task(self) -> Task:
return Task(
config=self.tasks_config['write_section_task'] # type: ignore[index]
)
@task
def review_section_task(self) -> Task:
return Task(
config=self.tasks_config['review_section_task'], # type: ignore[index]
context=[self.write_section_task()]
)
@crew
def crew(self) -> Crew:
"""Creates the content writing crew"""
return Crew(
agents=self.agents,
tasks=self.tasks,
process=Process.sequential,
verbose=True,
)
```
This crew definition establishes the relationship between our agents and tasks, setting up a sequential process where the content writer creates a draft and then the reviewer improves it. While this crew can function independently, in our flow it will be orchestrated as part of a larger system.
## Step 5: Create the Flow
Now comes the exciting part - creating the flow that will orchestrate the entire guide creation process. This is where we'll combine regular Python code, direct LLM calls, and our content creation crew into a cohesive system.
Our flow will:
1. Get user input for a topic and audience level
2. Make a direct LLM call to create a structured guide outline
3. Process each section sequentially using the content writer crew
4. Combine everything into a final comprehensive document
Let's create our flow in the `main.py` file:
```python
#!/usr/bin/env python
import json
import os
from typing import List, Dict
from pydantic import BaseModel, Field
from crewai import LLM
from crewai.flow.flow import Flow, listen, start
from guide_creator_flow.crews.content_crew.content_crew import ContentCrew
# Define our models for structured data
class Section(BaseModel):
title: str = Field(description="Title of the section")
description: str = Field(description="Brief description of what the section should cover")
class GuideOutline(BaseModel):
title: str = Field(description="Title of the guide")
introduction: str = Field(description="Introduction to the topic")
target_audience: str = Field(description="Description of the target audience")
sections: List[Section] = Field(description="List of sections in the guide")
conclusion: str = Field(description="Conclusion or summary of the guide")
# Define our flow state
class GuideCreatorState(BaseModel):
topic: str = ""
audience_level: str = ""
guide_outline: GuideOutline = None
sections_content: Dict[str, str] = {}
class GuideCreatorFlow(Flow[GuideCreatorState]):
"""Flow for creating a comprehensive guide on any topic"""
@start()
def get_user_input(self):
"""Get input from the user about the guide topic and audience"""
print("\n=== Create Your Comprehensive Guide ===\n")
# Get user input
self.state.topic = input("What topic would you like to create a guide for? ")
# Get audience level with validation
while True:
audience = input("Who is your target audience? (beginner/intermediate/advanced) ").lower()
if audience in ["beginner", "intermediate", "advanced"]:
self.state.audience_level = audience
break
print("Please enter 'beginner', 'intermediate', or 'advanced'")
print(f"\nCreating a guide on {self.state.topic} for {self.state.audience_level} audience...\n")
return self.state
@listen(get_user_input)
def create_guide_outline(self, state):
"""Create a structured outline for the guide using a direct LLM call"""
print("Creating guide outline...")
# Initialize the LLM
llm = LLM(model="openai/gpt-4o-mini", response_format=GuideOutline)
# Create the messages for the outline
messages = [
{"role": "system", "content": "You are a helpful assistant designed to output JSON."},
{"role": "user", "content": f"""
Create a detailed outline for a comprehensive guide on "{state.topic}" for {state.audience_level} level learners.
The outline should include:
1. A compelling title for the guide
2. An introduction to the topic
3. 4-6 main sections that cover the most important aspects of the topic
4. A conclusion or summary
For each section, provide a clear title and a brief description of what it should cover.
"""}
]
# Make the LLM call with JSON response format
response = llm.call(messages=messages)
# Parse the JSON response
outline_dict = json.loads(response)
self.state.guide_outline = GuideOutline(**outline_dict)
# Ensure output directory exists before saving
os.makedirs("output", exist_ok=True)
# Save the outline to a file
with open("output/guide_outline.json", "w") as f:
json.dump(outline_dict, f, indent=2)
print(f"Guide outline created with {len(self.state.guide_outline.sections)} sections")
return self.state.guide_outline
@listen(create_guide_outline)
def write_and_compile_guide(self, outline):
"""Write all sections and compile the guide"""
print("Writing guide sections and compiling...")
completed_sections = []
# Process sections one by one to maintain context flow
for section in outline.sections:
print(f"Processing section: {section.title}")
# Build context from previous sections
previous_sections_text = ""
if completed_sections:
previous_sections_text = "# Previously Written Sections\n\n"
for title in completed_sections:
previous_sections_text += f"## {title}\n\n"
previous_sections_text += self.state.sections_content.get(title, "") + "\n\n"
else:
previous_sections_text = "No previous sections written yet."
# Run the content crew for this section
result = ContentCrew().crew().kickoff(inputs={
"section_title": section.title,
"section_description": section.description,
"audience_level": self.state.audience_level,
"previous_sections": previous_sections_text,
"draft_content": ""
})
# Store the content
self.state.sections_content[section.title] = result.raw
completed_sections.append(section.title)
print(f"Section completed: {section.title}")
# Compile the final guide
guide_content = f"# {outline.title}\n\n"
guide_content += f"## Introduction\n\n{outline.introduction}\n\n"
# Add each section in order
for section in outline.sections:
section_content = self.state.sections_content.get(section.title, "")
guide_content += f"\n\n{section_content}\n\n"
# Add conclusion
guide_content += f"## Conclusion\n\n{outline.conclusion}\n\n"
# Save the guide
with open("output/complete_guide.md", "w") as f:
f.write(guide_content)
print("\nComplete guide compiled and saved to output/complete_guide.md")
return "Guide creation completed successfully"
def kickoff():
"""Run the guide creator flow"""
GuideCreatorFlow().kickoff()
print("\n=== Flow Complete ===")
print("Your comprehensive guide is ready in the output directory.")
print("Open output/complete_guide.md to view it.")
def plot():
"""Generate a visualization of the flow"""
flow = GuideCreatorFlow()
flow.plot("guide_creator_flow")
print("Flow visualization saved to guide_creator_flow.html")
if __name__ == "__main__":
kickoff()
```
Let's analyze what's happening in this flow:
1. We define Pydantic models for structured data, ensuring type safety and clear data representation
2. We create a state class to maintain data across different steps of the flow
3. We implement three main flow steps:
* Getting user input with the `@start()` decorator
* Creating a guide outline with a direct LLM call
* Processing sections with our content crew
4. We use the `@listen()` decorator to establish event-driven relationships between steps
This is the power of flows - combining different types of processing (user interaction, direct LLM calls, crew-based tasks) into a coherent, event-driven system.
## Step 6: Set Up Your Environment Variables
Create a `.env` file in your project root with your API keys:
```
OPENAI_API_KEY=your_openai_api_key
```
## Step 7: Install Dependencies
Install the required dependencies:
```bash
crewai install
```
## Step 8: Run Your Flow
Now it's time to see your flow in action! Run it using the CrewAI CLI:
```bash
crewai flow kickoff
```
When you run this command, you'll see your flow spring to life:
1. It will prompt you for a topic and audience level
2. It will create a structured outline for your guide
3. It will process each section, with the content writer and reviewer collaborating on each
4. Finally, it will compile everything into a comprehensive guide
This demonstrates the power of flows to orchestrate complex processes involving multiple components, both AI and non-AI.
## Step 9: Visualize Your Flow
One of the powerful features of flows is the ability to visualize their structure:
```bash
crewai flow plot
```
This will create an HTML file that shows the structure of your flow, including the relationships between different steps and the data that flows between them. This visualization can be invaluable for understanding and debugging complex flows.
## Step 10: Review the Output
Once the flow completes, you'll find two files in the `output` directory:
1. `guide_outline.json`: Contains the structured outline of the guide
2. `complete_guide.md`: The comprehensive guide with all sections
Take a moment to review these files and appreciate what you've built - a system that combines user input, direct AI interactions, and collaborative agent work to produce a complex, high-quality output.
## The Art of the Possible: Beyond Your First Flow
What you've learned in this guide provides a foundation for creating much more sophisticated AI systems. Here are some ways you could extend this basic flow:
### Enhancing User Interaction
You could create more interactive flows with:
* Web interfaces for input and output
* Real-time progress updates
* Interactive feedback and refinement loops
* Multi-stage user interactions
### Adding More Processing Steps
You could expand your flow with additional steps for:
* Research before outline creation
* Image generation for illustrations
* Code snippet generation for technical guides
* Final quality assurance and fact-checking
### Creating More Complex Flows
You could implement more sophisticated flow patterns:
* Conditional branching based on user preferences or content type
* Parallel processing of independent sections
* Iterative refinement loops with feedback
* Integration with external APIs and services
### Applying to Different Domains
The same patterns can be applied to create flows for:
* **Interactive storytelling**: Create personalized stories based on user input
* **Business intelligence**: Process data, generate insights, and create reports
* **Product development**: Facilitate ideation, design, and planning
* **Educational systems**: Create personalized learning experiences
## Key Features Demonstrated
This guide creator flow demonstrates several powerful features of CrewAI:
1. **User interaction**: The flow collects input directly from the user
2. **Direct LLM calls**: Uses the LLM class for efficient, single-purpose AI interactions
3. **Structured data with Pydantic**: Uses Pydantic models to ensure type safety
4. **Sequential processing with context**: Writes sections in order, providing previous sections for context
5. **Multi-agent crews**: Leverages specialized agents (writer and reviewer) for content creation
6. **State management**: Maintains state across different steps of the process
7. **Event-driven architecture**: Uses the `@listen` decorator to respond to events
## Understanding the Flow Structure
Let's break down the key components of flows to help you understand how to build your own:
### 1. Direct LLM Calls
Flows allow you to make direct calls to language models when you need simple, structured responses:
```python
llm = LLM(model="openai/gpt-4o-mini", response_format=GuideOutline)
response = llm.call(messages=messages)
```
This is more efficient than using a crew when you need a specific, structured output.
### 2. Event-Driven Architecture
Flows use decorators to establish relationships between components:
```python
@start()
def get_user_input(self):
# First step in the flow
# ...
@listen(get_user_input)
def create_guide_outline(self, state):
# This runs when get_user_input completes
# ...
```
This creates a clear, declarative structure for your application.
### 3. State Management
Flows maintain state across steps, making it easy to share data:
```python
class GuideCreatorState(BaseModel):
topic: str = ""
audience_level: str = ""
guide_outline: GuideOutline = None
sections_content: Dict[str, str] = {}
```
This provides a type-safe way to track and transform data throughout your flow.
### 4. Crew Integration
Flows can seamlessly integrate with crews for complex collaborative tasks:
```python
result = ContentCrew().crew().kickoff(inputs={
"section_title": section.title,
# ...
})
```
This allows you to use the right tool for each part of your application - direct LLM calls for simple tasks and crews for complex collaboration.
## Next Steps
Now that you've built your first flow, you can:
1. Experiment with more complex flow structures and patterns
2. Try using `@router()` to create conditional branches in your flows
3. Explore the `and_` and `or_` functions for more complex parallel execution
4. Connect your flow to external APIs, databases, or user interfaces
5. Combine multiple specialized crews in a single flow
Congratulations! You've successfully built your first CrewAI Flow that combines regular code, direct LLM calls, and crew-based processing to create a comprehensive guide. These foundational skills enable you to create increasingly sophisticated AI applications that can tackle complex, multi-stage problems through a combination of procedural control and collaborative intelligence.
# Mastering Flow State Management
Source: https://docs.crewai.com/guides/flows/mastering-flow-state
A comprehensive guide to managing, persisting, and leveraging state in CrewAI Flows for building robust AI applications.
# Mastering Flow State Management
## Understanding the Power of State in Flows
State management is the backbone of any sophisticated AI workflow. In CrewAI Flows, the state system allows you to maintain context, share data between steps, and build complex application logic. Mastering state management is essential for creating reliable, maintainable, and powerful AI applications.
This guide will walk you through everything you need to know about managing state in CrewAI Flows, from basic concepts to advanced techniques, with practical code examples along the way.
### Why State Management Matters
Effective state management enables you to:
1. **Maintain context across execution steps** - Pass information seamlessly between different stages of your workflow
2. **Build complex conditional logic** - Make decisions based on accumulated data
3. **Create persistent applications** - Save and restore workflow progress
4. **Handle errors gracefully** - Implement recovery patterns for more robust applications
5. **Scale your applications** - Support complex workflows with proper data organization
6. **Enable conversational applications** - Store and access conversation history for context-aware AI interactions
Let's explore how to leverage these capabilities effectively.
## State Management Fundamentals
### The Flow State Lifecycle
In CrewAI Flows, the state follows a predictable lifecycle:
1. **Initialization** - When a flow is created, its state is initialized (either as an empty dictionary or a Pydantic model instance)
2. **Modification** - Flow methods access and modify the state as they execute
3. **Transmission** - State is passed automatically between flow methods
4. **Persistence** (optional) - State can be saved to storage and later retrieved
5. **Completion** - The final state reflects the cumulative changes from all executed methods
Understanding this lifecycle is crucial for designing effective flows.
### Two Approaches to State Management
CrewAI offers two ways to manage state in your flows:
1. **Unstructured State** - Using dictionary-like objects for flexibility
2. **Structured State** - Using Pydantic models for type safety and validation
Let's examine each approach in detail.
## Unstructured State Management
Unstructured state uses a dictionary-like approach, offering flexibility and simplicity for straightforward applications.
### How It Works
With unstructured state:
* You access state via `self.state` which behaves like a dictionary
* You can freely add, modify, or remove keys at any point
* All state is automatically available to all flow methods
### Basic Example
Here's a simple example of unstructured state management:
```python
from crewai.flow.flow import Flow, listen, start
class UnstructuredStateFlow(Flow):
@start()
def initialize_data(self):
print("Initializing flow data")
# Add key-value pairs to state
self.state["user_name"] = "Alex"
self.state["preferences"] = {
"theme": "dark",
"language": "English"
}
self.state["items"] = []
# The flow state automatically gets a unique ID
print(f"Flow ID: {self.state['id']}")
return "Initialized"
@listen(initialize_data)
def process_data(self, previous_result):
print(f"Previous step returned: {previous_result}")
# Access and modify state
user = self.state["user_name"]
print(f"Processing data for {user}")
# Add items to a list in state
self.state["items"].append("item1")
self.state["items"].append("item2")
# Add a new key-value pair
self.state["processed"] = True
return "Processed"
@listen(process_data)
def generate_summary(self, previous_result):
# Access multiple state values
user = self.state["user_name"]
theme = self.state["preferences"]["theme"]
items = self.state["items"]
processed = self.state.get("processed", False)
summary = f"User {user} has {len(items)} items with {theme} theme. "
summary += "Data is processed." if processed else "Data is not processed."
return summary
# Run the flow
flow = UnstructuredStateFlow()
result = flow.kickoff()
print(f"Final result: {result}")
print(f"Final state: {flow.state}")
```
### When to Use Unstructured State
Unstructured state is ideal for:
* Quick prototyping and simple flows
* Dynamically evolving state needs
* Cases where the structure may not be known in advance
* Flows with simple state requirements
While flexible, unstructured state lacks type checking and schema validation, which can lead to errors in complex applications.
## Structured State Management
Structured state uses Pydantic models to define a schema for your flow's state, providing type safety, validation, and better developer experience.
### How It Works
With structured state:
* You define a Pydantic model that represents your state structure
* You pass this model type to your Flow class as a type parameter
* You access state via `self.state`, which behaves like a Pydantic model instance
* All fields are validated according to their defined types
* You get IDE autocompletion and type checking support
### Basic Example
Here's how to implement structured state management:
```python
from crewai.flow.flow import Flow, listen, start
from pydantic import BaseModel, Field
from typing import List, Dict, Optional
# Define your state model
class UserPreferences(BaseModel):
theme: str = "light"
language: str = "English"
class AppState(BaseModel):
user_name: str = ""
preferences: UserPreferences = UserPreferences()
items: List[str] = []
processed: bool = False
completion_percentage: float = 0.0
# Create a flow with typed state
class StructuredStateFlow(Flow[AppState]):
@start()
def initialize_data(self):
print("Initializing flow data")
# Set state values (type-checked)
self.state.user_name = "Taylor"
self.state.preferences.theme = "dark"
# The ID field is automatically available
print(f"Flow ID: {self.state.id}")
return "Initialized"
@listen(initialize_data)
def process_data(self, previous_result):
print(f"Processing data for {self.state.user_name}")
# Modify state (with type checking)
self.state.items.append("item1")
self.state.items.append("item2")
self.state.processed = True
self.state.completion_percentage = 50.0
return "Processed"
@listen(process_data)
def generate_summary(self, previous_result):
# Access state (with autocompletion)
summary = f"User {self.state.user_name} has {len(self.state.items)} items "
summary += f"with {self.state.preferences.theme} theme. "
summary += "Data is processed." if self.state.processed else "Data is not processed."
summary += f" Completion: {self.state.completion_percentage}%"
return summary
# Run the flow
flow = StructuredStateFlow()
result = flow.kickoff()
print(f"Final result: {result}")
print(f"Final state: {flow.state}")
```
### Benefits of Structured State
Using structured state provides several advantages:
1. **Type Safety** - Catch type errors at development time
2. **Self-Documentation** - The state model clearly documents what data is available
3. **Validation** - Automatic validation of data types and constraints
4. **IDE Support** - Get autocomplete and inline documentation
5. **Default Values** - Easily define fallbacks for missing data
### When to Use Structured State
Structured state is recommended for:
* Complex flows with well-defined data schemas
* Team projects where multiple developers work on the same code
* Applications where data validation is important
* Flows that need to enforce specific data types and constraints
## The Automatic State ID
Both unstructured and structured states automatically receive a unique identifier (UUID) to help track and manage state instances.
### How It Works
* For unstructured state, the ID is accessible as `self.state["id"]`
* For structured state, the ID is accessible as `self.state.id`
* This ID is generated automatically when the flow is created
* The ID remains the same throughout the flow's lifecycle
* The ID can be used for tracking, logging, and retrieving persisted states
This UUID is particularly valuable when implementing persistence or tracking multiple flow executions.
## Dynamic State Updates
Regardless of whether you're using structured or unstructured state, you can update state dynamically throughout your flow's execution.
### Passing Data Between Steps
Flow methods can return values that are then passed as arguments to listening methods:
```python
from crewai.flow.flow import Flow, listen, start
class DataPassingFlow(Flow):
@start()
def generate_data(self):
# This return value will be passed to listening methods
return "Generated data"
@listen(generate_data)
def process_data(self, data_from_previous_step):
print(f"Received: {data_from_previous_step}")
# You can modify the data and pass it along
processed_data = f"{data_from_previous_step} - processed"
# Also update state
self.state["last_processed"] = processed_data
return processed_data
@listen(process_data)
def finalize_data(self, processed_data):
print(f"Received processed data: {processed_data}")
# Access both the passed data and state
last_processed = self.state.get("last_processed", "")
return f"Final: {processed_data} (from state: {last_processed})"
```
This pattern allows you to combine direct data passing with state updates for maximum flexibility.
## Persisting Flow State
One of CrewAI's most powerful features is the ability to persist flow state across executions. This enables workflows that can be paused, resumed, and even recovered after failures.
### The @persist Decorator
The `@persist` decorator automates state persistence, saving your flow's state at key points in execution.
#### Class-Level Persistence
When applied at the class level, `@persist` saves state after every method execution:
```python
from crewai.flow.flow import Flow, listen, persist, start
from pydantic import BaseModel
class CounterState(BaseModel):
value: int = 0
@persist # Apply to the entire flow class
class PersistentCounterFlow(Flow[CounterState]):
@start()
def increment(self):
self.state.value += 1
print(f"Incremented to {self.state.value}")
return self.state.value
@listen(increment)
def double(self, value):
self.state.value = value * 2
print(f"Doubled to {self.state.value}")
return self.state.value
# First run
flow1 = PersistentCounterFlow()
result1 = flow1.kickoff()
print(f"First run result: {result1}")
# Second run - state is automatically loaded
flow2 = PersistentCounterFlow()
result2 = flow2.kickoff()
print(f"Second run result: {result2}") # Will be higher due to persisted state
```
#### Method-Level Persistence
For more granular control, you can apply `@persist` to specific methods:
```python
from crewai.flow.flow import Flow, listen, persist, start
class SelectivePersistFlow(Flow):
@start()
def first_step(self):
self.state["count"] = 1
return "First step"
@persist # Only persist after this method
@listen(first_step)
def important_step(self, prev_result):
self.state["count"] += 1
self.state["important_data"] = "This will be persisted"
return "Important step completed"
@listen(important_step)
def final_step(self, prev_result):
self.state["count"] += 1
return f"Complete with count {self.state['count']}"
```
## Advanced State Patterns
### State-Based Conditional Logic
You can use state to implement complex conditional logic in your flows:
```python
from crewai.flow.flow import Flow, listen, router, start
from pydantic import BaseModel
class PaymentState(BaseModel):
amount: float = 0.0
is_approved: bool = False
retry_count: int = 0
class PaymentFlow(Flow[PaymentState]):
@start()
def process_payment(self):
# Simulate payment processing
self.state.amount = 100.0
self.state.is_approved = self.state.amount < 1000
return "Payment processed"
@router(process_payment)
def check_approval(self, previous_result):
if self.state.is_approved:
return "approved"
elif self.state.retry_count < 3:
return "retry"
else:
return "rejected"
@listen("approved")
def handle_approval(self):
return f"Payment of ${self.state.amount} approved!"
@listen("retry")
def handle_retry(self):
self.state.retry_count += 1
print(f"Retrying payment (attempt {self.state.retry_count})...")
# Could implement retry logic here
return "Retry initiated"
@listen("rejected")
def handle_rejection(self):
return f"Payment of ${self.state.amount} rejected after {self.state.retry_count} retries."
```
### Handling Complex State Transformations
For complex state transformations, you can create dedicated methods:
```python
from crewai.flow.flow import Flow, listen, start
from pydantic import BaseModel
from typing import List, Dict
class UserData(BaseModel):
name: str
active: bool = True
login_count: int = 0
class ComplexState(BaseModel):
users: Dict[str, UserData] = {}
active_user_count: int = 0
class TransformationFlow(Flow[ComplexState]):
@start()
def initialize(self):
# Add some users
self.add_user("alice", "Alice")
self.add_user("bob", "Bob")
self.add_user("charlie", "Charlie")
return "Initialized"
@listen(initialize)
def process_users(self, _):
# Increment login counts
for user_id in self.state.users:
self.increment_login(user_id)
# Deactivate one user
self.deactivate_user("bob")
# Update active count
self.update_active_count()
return f"Processed {len(self.state.users)} users"
# Helper methods for state transformations
def add_user(self, user_id: str, name: str):
self.state.users[user_id] = UserData(name=name)
self.update_active_count()
def increment_login(self, user_id: str):
if user_id in self.state.users:
self.state.users[user_id].login_count += 1
def deactivate_user(self, user_id: str):
if user_id in self.state.users:
self.state.users[user_id].active = False
self.update_active_count()
def update_active_count(self):
self.state.active_user_count = sum(
1 for user in self.state.users.values() if user.active
)
```
This pattern of creating helper methods keeps your flow methods clean while enabling complex state manipulations.
## State Management with Crews
One of the most powerful patterns in CrewAI is combining flow state management with crew execution.
### Passing State to Crews
You can use flow state to parameterize crews:
```python
from crewai.flow.flow import Flow, listen, start
from crewai import Agent, Crew, Process, Task
from pydantic import BaseModel
class ResearchState(BaseModel):
topic: str = ""
depth: str = "medium"
results: str = ""
class ResearchFlow(Flow[ResearchState]):
@start()
def get_parameters(self):
# In a real app, this might come from user input
self.state.topic = "Artificial Intelligence Ethics"
self.state.depth = "deep"
return "Parameters set"
@listen(get_parameters)
def execute_research(self, _):
# Create agents
researcher = Agent(
role="Research Specialist",
goal=f"Research {self.state.topic} in {self.state.depth} detail",
backstory="You are an expert researcher with a talent for finding accurate information."
)
writer = Agent(
role="Content Writer",
goal="Transform research into clear, engaging content",
backstory="You excel at communicating complex ideas clearly and concisely."
)
# Create tasks
research_task = Task(
description=f"Research {self.state.topic} with {self.state.depth} analysis",
expected_output="Comprehensive research notes in markdown format",
agent=researcher
)
writing_task = Task(
description=f"Create a summary on {self.state.topic} based on the research",
expected_output="Well-written article in markdown format",
agent=writer,
context=[research_task]
)
# Create and run crew
research_crew = Crew(
agents=[researcher, writer],
tasks=[research_task, writing_task],
process=Process.sequential,
verbose=True
)
# Run crew and store result in state
result = research_crew.kickoff()
self.state.results = result.raw
return "Research completed"
@listen(execute_research)
def summarize_results(self, _):
# Access the stored results
result_length = len(self.state.results)
return f"Research on {self.state.topic} completed with {result_length} characters of results."
```
### Handling Crew Outputs in State
When a crew completes, you can process its output and store it in your flow state:
```python
@listen(execute_crew)
def process_crew_results(self, _):
# Parse the raw results (assuming JSON output)
import json
try:
results_dict = json.loads(self.state.raw_results)
self.state.processed_results = {
"title": results_dict.get("title", ""),
"main_points": results_dict.get("main_points", []),
"conclusion": results_dict.get("conclusion", "")
}
return "Results processed successfully"
except json.JSONDecodeError:
self.state.error = "Failed to parse crew results as JSON"
return "Error processing results"
```
## Best Practices for State Management
### 1. Keep State Focused
Design your state to contain only what's necessary:
```python
# Too broad
class BloatedState(BaseModel):
user_data: Dict = {}
system_settings: Dict = {}
temporary_calculations: List = []
debug_info: Dict = {}
# ...many more fields
# Better: Focused state
class FocusedState(BaseModel):
user_id: str
preferences: Dict[str, str]
completion_status: Dict[str, bool]
```
### 2. Use Structured State for Complex Flows
As your flows grow in complexity, structured state becomes increasingly valuable:
```python
# Simple flow can use unstructured state
class SimpleGreetingFlow(Flow):
@start()
def greet(self):
self.state["name"] = "World"
return f"Hello, {self.state['name']}!"
# Complex flow benefits from structured state
class UserRegistrationState(BaseModel):
username: str
email: str
verification_status: bool = False
registration_date: datetime = Field(default_factory=datetime.now)
last_login: Optional[datetime] = None
class RegistrationFlow(Flow[UserRegistrationState]):
# Methods with strongly-typed state access
```
### 3. Document State Transitions
For complex flows, document how state changes throughout the execution:
```python
@start()
def initialize_order(self):
"""
Initialize order state with empty values.
State before: {}
State after: {order_id: str, items: [], status: 'new'}
"""
self.state.order_id = str(uuid.uuid4())
self.state.items = []
self.state.status = "new"
return "Order initialized"
```
### 4. Handle State Errors Gracefully
Implement error handling for state access:
```python
@listen(previous_step)
def process_data(self, _):
try:
# Try to access a value that might not exist
user_preference = self.state.preferences.get("theme", "default")
except (AttributeError, KeyError):
# Handle the error gracefully
self.state.errors = self.state.get("errors", [])
self.state.errors.append("Failed to access preferences")
user_preference = "default"
return f"Used preference: {user_preference}"
```
### 5. Use State for Progress Tracking
Leverage state to track progress in long-running flows:
```python
class ProgressTrackingFlow(Flow):
@start()
def initialize(self):
self.state["total_steps"] = 3
self.state["current_step"] = 0
self.state["progress"] = 0.0
self.update_progress()
return "Initialized"
def update_progress(self):
"""Helper method to calculate and update progress"""
if self.state.get("total_steps", 0) > 0:
self.state["progress"] = (self.state.get("current_step", 0) /
self.state["total_steps"]) * 100
print(f"Progress: {self.state['progress']:.1f}%")
@listen(initialize)
def step_one(self, _):
# Do work...
self.state["current_step"] = 1
self.update_progress()
return "Step 1 complete"
# Additional steps...
```
### 6. Use Immutable Operations When Possible
Especially with structured state, prefer immutable operations for clarity:
```python
# Instead of modifying lists in place:
self.state.items.append(new_item) # Mutable operation
# Consider creating new state:
from pydantic import BaseModel
from typing import List
class ItemState(BaseModel):
items: List[str] = []
class ImmutableFlow(Flow[ItemState]):
@start()
def add_item(self):
# Create new list with the added item
self.state.items = [*self.state.items, "new item"]
return "Item added"
```
## Debugging Flow State
### Logging State Changes
When developing, add logging to track state changes:
```python
import logging
logging.basicConfig(level=logging.INFO)
class LoggingFlow(Flow):
def log_state(self, step_name):
logging.info(f"State after {step_name}: {self.state}")
@start()
def initialize(self):
self.state["counter"] = 0
self.log_state("initialize")
return "Initialized"
@listen(initialize)
def increment(self, _):
self.state["counter"] += 1
self.log_state("increment")
return f"Incremented to {self.state['counter']}"
```
### State Visualization
You can add methods to visualize your state for debugging:
```python
def visualize_state(self):
"""Create a simple visualization of the current state"""
import json
from rich.console import Console
from rich.panel import Panel
console = Console()
if hasattr(self.state, "model_dump"):
# Pydantic v2
state_dict = self.state.model_dump()
elif hasattr(self.state, "dict"):
# Pydantic v1
state_dict = self.state.dict()
else:
# Unstructured state
state_dict = dict(self.state)
# Remove id for cleaner output
if "id" in state_dict:
state_dict.pop("id")
state_json = json.dumps(state_dict, indent=2, default=str)
console.print(Panel(state_json, title="Current Flow State"))
```
## Conclusion
Mastering state management in CrewAI Flows gives you the power to build sophisticated, robust AI applications that maintain context, make complex decisions, and deliver consistent results.
Whether you choose unstructured or structured state, implementing proper state management practices will help you create flows that are maintainable, extensible, and effective at solving real-world problems.
As you develop more complex flows, remember that good state management is about finding the right balance between flexibility and structure, making your code both powerful and easy to understand.
You've now mastered the concepts and practices of state management in CrewAI Flows! With this knowledge, you can create robust AI workflows that effectively maintain context, share data between steps, and build sophisticated application logic.
## Next Steps
* Experiment with both structured and unstructured state in your flows
* Try implementing state persistence for long-running workflows
* Explore [building your first crew](/guides/crews/first-crew) to see how crews and flows can work together
* Check out the [Flow reference documentation](/concepts/flows) for more advanced features
# AgentOps Integration
Source: https://docs.crewai.com/how-to/agentops-observability
Understanding and logging your agent performance with AgentOps.
# Introduction
Observability is a key aspect of developing and deploying conversational AI agents. It allows developers to understand how their agents are performing,
how their agents are interacting with users, and how their agents use external tools and APIs.
AgentOps is a product independent of CrewAI that provides a comprehensive observability solution for agents.
## AgentOps
[AgentOps](https://agentops.ai/?=crew) provides session replays, metrics, and monitoring for agents.
At a high level, AgentOps gives you the ability to monitor cost, token usage, latency, agent failures, session-wide statistics, and more.
For more info, check out the [AgentOps Repo](https://github.com/AgentOps-AI/agentops).
### Overview
AgentOps provides monitoring for agents in development and production.
It provides a dashboard for tracking agent performance, session replays, and custom reporting.
Additionally, AgentOps provides session drilldowns for viewing Crew agent interactions, LLM calls, and tool usage in real-time.
This feature is useful for debugging and understanding how agents interact with users as well as other agents.
### Features
* **LLM Cost Management and Tracking**: Track spend with foundation model providers.
* **Replay Analytics**: Watch step-by-step agent execution graphs.
* **Recursive Thought Detection**: Identify when agents fall into infinite loops.
* **Custom Reporting**: Create custom analytics on agent performance.
* **Analytics Dashboard**: Monitor high-level statistics about agents in development and production.
* **Public Model Testing**: Test your agents against benchmarks and leaderboards.
* **Custom Tests**: Run your agents against domain-specific tests.
* **Time Travel Debugging**: Restart your sessions from checkpoints.
* **Compliance and Security**: Create audit logs and detect potential threats such as profanity and PII leaks.
* **Prompt Injection Detection**: Identify potential code injection and secret leaks.
### Using AgentOps
Create a user API key here: [Create API Key](https://app.agentops.ai/account)
Add your API key to your environment variables:
```bash
AGENTOPS_API_KEY=
```
Install AgentOps with:
```bash
pip install 'crewai[agentops]'
```
or
```bash
pip install agentops
```
Before using `Crew` in your script, include these lines:
```python
import agentops
agentops.init()
```
This will initiate an AgentOps session as well as automatically track Crew agents. For further info on how to outfit more complex agentic systems,
check out the [AgentOps documentation](https://docs.agentops.ai) or join the [Discord](https://discord.gg/j4f3KbeH).
### Crew + AgentOps Examples
Example of a Crew agent that generates job posts.
Example of a Crew agent that validates Markdown files.
Example of a Crew agent that generates Instagram posts.
### Further Information
To get started, create an [AgentOps account](https://agentops.ai/?=crew).
For feature requests or bug reports, please reach out to the AgentOps team on the [AgentOps Repo](https://github.com/AgentOps-AI/agentops).
#### Extra links
🐦 Twitter • 📢 Discord • 🖇️ AgentOps Dashboard • 📙 Documentation
# Arize Phoenix
Source: https://docs.crewai.com/how-to/arize-phoenix-observability
Arize Phoenix integration for CrewAI with OpenTelemetry and OpenInference
# Arize Phoenix Integration
This guide demonstrates how to integrate **Arize Phoenix** with **CrewAI** using OpenTelemetry via the [OpenInference](https://github.com/openinference/openinference) SDK. By the end of this guide, you will be able to trace your CrewAI agents and easily debug your agents.
> **What is Arize Phoenix?** [Arize Phoenix](https://phoenix.arize.com) is an LLM observability platform that provides tracing and evaluation for AI applications.
[](https://www.youtube.com/watch?v=Yc5q3l6F7Ww)
## Get Started
We'll walk through a simple example of using CrewAI and integrating it with Arize Phoenix via OpenTelemetry using OpenInference.
You can also access this guide on [Google Colab](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/tracing/crewai_tracing_tutorial.ipynb).
### Step 1: Install Dependencies
```bash
pip install openinference-instrumentation-crewai crewai crewai-tools arize-phoenix-otel
```
### Step 2: Set Up Environment Variables
Setup Phoenix Cloud API keys and configure OpenTelemetry to send traces to Phoenix. Phoenix Cloud is a hosted version of Arize Phoenix, but it is not required to use this integration.
You can get your free Serper API key [here](https://serper.dev/).
```python
import os
from getpass import getpass
# Get your Phoenix Cloud credentials
PHOENIX_API_KEY = getpass("🔑 Enter your Phoenix Cloud API Key: ")
# Get API keys for services
OPENAI_API_KEY = getpass("🔑 Enter your OpenAI API key: ")
SERPER_API_KEY = getpass("🔑 Enter your Serper API key: ")
# Set environment variables
os.environ["PHOENIX_CLIENT_HEADERS"] = f"api_key={PHOENIX_API_KEY}"
os.environ["PHOENIX_COLLECTOR_ENDPOINT"] = "https://app.phoenix.arize.com" # Phoenix Cloud, change this to your own endpoint if you are using a self-hosted instance
os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
os.environ["SERPER_API_KEY"] = SERPER_API_KEY
```
### Step 3: Initialize OpenTelemetry with Phoenix
Initialize the OpenInference OpenTelemetry instrumentation SDK to start capturing traces and send them to Phoenix.
```python
from phoenix.otel import register
tracer_provider = register(
project_name="crewai-tracing-demo",
auto_instrument=True,
)
```
### Step 4: Create a CrewAI Application
We'll create a CrewAI application where two agents collaborate to research and write a blog post about AI advancements.
```python
from crewai import Agent, Crew, Process, Task
from crewai_tools import SerperDevTool
search_tool = SerperDevTool()
# Define your agents with roles and goals
researcher = Agent(
role="Senior Research Analyst",
goal="Uncover cutting-edge developments in AI and data science",
backstory="""You work at a leading tech think tank.
Your expertise lies in identifying emerging trends.
You have a knack for dissecting complex data and presenting actionable insights.""",
verbose=True,
allow_delegation=False,
# You can pass an optional llm attribute specifying what model you wanna use.
# llm=ChatOpenAI(model_name="gpt-3.5", temperature=0.7),
tools=[search_tool],
)
writer = Agent(
role="Tech Content Strategist",
goal="Craft compelling content on tech advancements",
backstory="""You are a renowned Content Strategist, known for your insightful and engaging articles.
You transform complex concepts into compelling narratives.""",
verbose=True,
allow_delegation=True,
)
# Create tasks for your agents
task1 = Task(
description="""Conduct a comprehensive analysis of the latest advancements in AI in 2024.
Identify key trends, breakthrough technologies, and potential industry impacts.""",
expected_output="Full analysis report in bullet points",
agent=researcher,
)
task2 = Task(
description="""Using the insights provided, develop an engaging blog
post that highlights the most significant AI advancements.
Your post should be informative yet accessible, catering to a tech-savvy audience.
Make it sound cool, avoid complex words so it doesn't sound like AI.""",
expected_output="Full blog post of at least 4 paragraphs",
agent=writer,
)
# Instantiate your crew with a sequential process
crew = Crew(
agents=[researcher, writer], tasks=[task1, task2], verbose=1, process=Process.sequential
)
# Get your crew to work!
result = crew.kickoff()
print("######################")
print(result)
```
### Step 5: View Traces in Phoenix
After running the agent, you can view the traces generated by your CrewAI application in Phoenix. You should see detailed steps of the agent interactions and LLM calls, which can help you debug and optimize your AI agents.
Log into your Phoenix Cloud account and navigate to the project you specified in the `project_name` parameter. You'll see a timeline view of your trace with all the agent interactions, tool usages, and LLM calls.
### Version Compatibility Information
* Python 3.8+
* CrewAI >= 0.86.0
* Arize Phoenix >= 7.0.1
* OpenTelemetry SDK >= 1.31.0
### References
* [Phoenix Documentation](https://docs.arize.com/phoenix/) - Overview of the Phoenix platform.
* [CrewAI Documentation](https://docs.crewai.com/) - Overview of the CrewAI framework.
* [OpenTelemetry Docs](https://opentelemetry.io/docs/) - OpenTelemetry guide
* [OpenInference GitHub](https://github.com/openinference/openinference) - Source code for OpenInference SDK.
# Coding Agents
Source: https://docs.crewai.com/how-to/coding-agents
Learn how to enable your CrewAI Agents to write and execute code, and explore advanced features for enhanced functionality.
## Introduction
CrewAI Agents now have the powerful ability to write and execute code, significantly enhancing their problem-solving capabilities. This feature is particularly useful for tasks that require computational or programmatic solutions.
## Enabling Code Execution
To enable code execution for an agent, set the `allow_code_execution` parameter to `True` when creating the agent.
Here's an example:
```python Code
from crewai import Agent
coding_agent = Agent(
role="Senior Python Developer",
goal="Craft well-designed and thought-out code",
backstory="You are a senior Python developer with extensive experience in software architecture and best practices.",
allow_code_execution=True
)
```
Note that `allow_code_execution` parameter defaults to `False`.
## Important Considerations
1. **Model Selection**: It is strongly recommended to use more capable models like Claude 3.5 Sonnet and GPT-4 when enabling code execution.
These models have a better understanding of programming concepts and are more likely to generate correct and efficient code.
2. **Error Handling**: The code execution feature includes error handling. If executed code raises an exception, the agent will receive the error message and can attempt to correct the code or
provide alternative solutions. The `max_retry_limit` parameter, which defaults to 2, controls the maximum number of retries for a task.
3. **Dependencies**: To use the code execution feature, you need to install the `crewai_tools` package. If not installed, the agent will log an info message:
"Coding tools not available. Install crewai\_tools."
## Code Execution Process
When an agent with code execution enabled encounters a task requiring programming:
The agent analyzes the task and determines that code execution is necessary.
It formulates the Python code needed to solve the problem.
The code is sent to the internal code execution tool (`CodeInterpreterTool`).
The agent interprets the result and incorporates it into its response or uses it for further problem-solving.
## Example Usage
Here's a detailed example of creating an agent with code execution capabilities and using it in a task:
```python Code
from crewai import Agent, Task, Crew
# Create an agent with code execution enabled
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
# Create a task that requires code execution
data_analysis_task = Task(
description="Analyze the given dataset and calculate the average age of participants.",
agent=coding_agent
)
# Create a crew and add the task
analysis_crew = Crew(
agents=[coding_agent],
tasks=[data_analysis_task]
)
# Execute the crew
result = analysis_crew.kickoff()
print(result)
```
In this example, the `coding_agent` can write and execute Python code to perform data analysis tasks.
# Conditional Tasks
Source: https://docs.crewai.com/how-to/conditional-tasks
Learn how to use conditional tasks in a crewAI kickoff
## Introduction
Conditional Tasks in crewAI allow for dynamic workflow adaptation based on the outcomes of previous tasks.
This powerful feature enables crews to make decisions and execute tasks selectively, enhancing the flexibility and efficiency of your AI-driven processes.
## Example Usage
```python Code
from typing import List
from pydantic import BaseModel
from crewai import Agent, Crew
from crewai.tasks.conditional_task import ConditionalTask
from crewai.tasks.task_output import TaskOutput
from crewai.task import Task
from crewai_tools import SerperDevTool
# Define a condition function for the conditional task
# If false, the task will be skipped, if true, then execute the task.
def is_data_missing(output: TaskOutput) -> bool:
return len(output.pydantic.events) < 10 # this will skip this task
# Define the agents
data_fetcher_agent = Agent(
role="Data Fetcher",
goal="Fetch data online using Serper tool",
backstory="Backstory 1",
verbose=True,
tools=[SerperDevTool()]
)
data_processor_agent = Agent(
role="Data Processor",
goal="Process fetched data",
backstory="Backstory 2",
verbose=True
)
summary_generator_agent = Agent(
role="Summary Generator",
goal="Generate summary from fetched data",
backstory="Backstory 3",
verbose=True
)
class EventOutput(BaseModel):
events: List[str]
task1 = Task(
description="Fetch data about events in San Francisco using Serper tool",
expected_output="List of 10 things to do in SF this week",
agent=data_fetcher_agent,
output_pydantic=EventOutput,
)
conditional_task = ConditionalTask(
description="""
Check if data is missing. If we have less than 10 events,
fetch more events using Serper tool so that
we have a total of 10 events in SF this week..
""",
expected_output="List of 10 Things to do in SF this week",
condition=is_data_missing,
agent=data_processor_agent,
)
task3 = Task(
description="Generate summary of events in San Francisco from fetched data",
expected_output="A complete report on the customer and their customers and competitors, including their demographics, preferences, market positioning and audience engagement.",
agent=summary_generator_agent,
)
# Create a crew with the tasks
crew = Crew(
agents=[data_fetcher_agent, data_processor_agent, summary_generator_agent],
tasks=[task1, conditional_task, task3],
verbose=True,
planning=True
)
# Run the crew
result = crew.kickoff()
print("results", result)
```
# Create Custom Tools
Source: https://docs.crewai.com/how-to/create-custom-tools
Comprehensive guide on crafting, using, and managing custom tools within the CrewAI framework, including new functionalities and error handling.
## Creating and Utilizing Tools in CrewAI
This guide provides detailed instructions on creating custom tools for the CrewAI framework and how to efficiently manage and utilize these tools,
incorporating the latest functionalities such as tool delegation, error handling, and dynamic tool calling. It also highlights the importance of collaboration tools,
enabling agents to perform a wide range of actions.
### Subclassing `BaseTool`
To create a personalized tool, inherit from `BaseTool` and define the necessary attributes, including the `args_schema` for input validation, and the `_run` method.
```python Code
from typing import Type
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
class MyToolInput(BaseModel):
"""Input schema for MyCustomTool."""
argument: str = Field(..., description="Description of the argument.")
class MyCustomTool(BaseTool):
name: str = "Name of my tool"
description: str = "What this tool does. It's vital for effective utilization."
args_schema: Type[BaseModel] = MyToolInput
def _run(self, argument: str) -> str:
# Your tool's logic here
return "Tool's result"
```
### Using the `tool` Decorator
Alternatively, you can use the tool decorator `@tool`. This approach allows you to define the tool's attributes and functionality directly within a function,
offering a concise and efficient way to create specialized tools tailored to your needs.
```python Code
from crewai.tools import tool
@tool("Tool Name")
def my_simple_tool(question: str) -> str:
"""Tool description for clarity."""
# Tool logic here
return "Tool output"
```
### Defining a Cache Function for the Tool
To optimize tool performance with caching, define custom caching strategies using the `cache_function` attribute.
```python Code
@tool("Tool with Caching")
def cached_tool(argument: str) -> str:
"""Tool functionality description."""
return "Cacheable result"
def my_cache_strategy(arguments: dict, result: str) -> bool:
# Define custom caching logic
return True if some_condition else False
cached_tool.cache_function = my_cache_strategy
```
By adhering to these guidelines and incorporating new functionalities and collaboration tools into your tool creation and management processes,
you can leverage the full capabilities of the CrewAI framework, enhancing both the development experience and the efficiency of your AI agents.
# Create Your Own Manager Agent
Source: https://docs.crewai.com/how-to/custom-manager-agent
Learn how to set a custom agent as the manager in CrewAI, providing more control over task management and coordination.
# Setting a Specific Agent as Manager in CrewAI
CrewAI allows users to set a specific agent as the manager of the crew, providing more control over the management and coordination of tasks.
This feature enables the customization of the managerial role to better fit your project's requirements.
## Using the `manager_agent` Attribute
### Custom Manager Agent
The `manager_agent` attribute allows you to define a custom agent to manage the crew. This agent will oversee the entire process, ensuring that tasks are completed efficiently and to the highest standard.
### Example
```python Code
import os
from crewai import Agent, Task, Crew, Process
# Define your agents
researcher = Agent(
role="Researcher",
goal="Conduct thorough research and analysis on AI and AI agents",
backstory="You're an expert researcher, specialized in technology, software engineering, AI, and startups. You work as a freelancer and are currently researching for a new client.",
allow_delegation=False,
)
writer = Agent(
role="Senior Writer",
goal="Create compelling content about AI and AI agents",
backstory="You're a senior writer, specialized in technology, software engineering, AI, and startups. You work as a freelancer and are currently writing content for a new client.",
allow_delegation=False,
)
# Define your task
task = Task(
description="Generate a list of 5 interesting ideas for an article, then write one captivating paragraph for each idea that showcases the potential of a full article on this topic. Return the list of ideas with their paragraphs and your notes.",
expected_output="5 bullet points, each with a paragraph and accompanying notes.",
)
# Define the manager agent
manager = Agent(
role="Project Manager",
goal="Efficiently manage the crew and ensure high-quality task completion",
backstory="You're an experienced project manager, skilled in overseeing complex projects and guiding teams to success. Your role is to coordinate the efforts of the crew members, ensuring that each task is completed on time and to the highest standard.",
allow_delegation=True,
)
# Instantiate your crew with a custom manager
crew = Crew(
agents=[researcher, writer],
tasks=[task],
manager_agent=manager,
process=Process.hierarchical,
)
# Start the crew's work
result = crew.kickoff()
```
## Benefits of a Custom Manager Agent
* **Enhanced Control**: Tailor the management approach to fit the specific needs of your project.
* **Improved Coordination**: Ensure efficient task coordination and management by an experienced agent.
* **Customizable Management**: Define managerial roles and responsibilities that align with your project's goals.
## Setting a Manager LLM
If you're using the hierarchical process and don't want to set a custom manager agent, you can specify the language model for the manager:
```python Code
from crewai import LLM
manager_llm = LLM(model="gpt-4o")
crew = Crew(
agents=[researcher, writer],
tasks=[task],
process=Process.hierarchical,
manager_llm=manager_llm
)
```
Either `manager_agent` or `manager_llm` must be set when using the hierarchical process.
# Customize Agents
Source: https://docs.crewai.com/how-to/customizing-agents
A comprehensive guide to tailoring agents for specific roles, tasks, and advanced customizations within the CrewAI framework.
## Customizable Attributes
Crafting an efficient CrewAI team hinges on the ability to dynamically tailor your AI agents to meet the unique requirements of any project. This section covers the foundational attributes you can customize.
### Key Attributes for Customization
| Attribute | Description |
| :---------------------------------- | :------------------------------------------------------------------------------------------------------------------ |
| **Role** | Specifies the agent's job within the crew, such as 'Analyst' or 'Customer Service Rep'. |
| **Goal** | Defines the agent’s objectives, aligned with its role and the crew’s overarching mission. |
| **Backstory** | Provides depth to the agent's persona, enhancing motivations and engagements within the crew. |
| **Tools** *(Optional)* | Represents the capabilities or methods the agent uses for tasks, from simple functions to complex integrations. |
| **Cache** *(Optional)* | Determines if the agent should use a cache for tool usage. |
| **Max RPM** | Sets the maximum requests per minute (`max_rpm`). Can be set to `None` for unlimited requests to external services. |
| **Verbose** *(Optional)* | Enables detailed logging for debugging and optimization, providing insights into execution processes. |
| **Allow Delegation** *(Optional)* | Controls task delegation to other agents, default is `False`. |
| **Max Iter** *(Optional)* | Limits the maximum number of iterations (`max_iter`) for a task to prevent infinite loops, with a default of 25. |
| **Max Execution Time** *(Optional)* | Sets the maximum time allowed for an agent to complete a task. |
| **System Template** *(Optional)* | Defines the system format for the agent. |
| **Prompt Template** *(Optional)* | Defines the prompt format for the agent. |
| **Response Template** *(Optional)* | Defines the response format for the agent. |
| **Use System Prompt** *(Optional)* | Controls whether the agent will use a system prompt during task execution. |
| **Respect Context Window** | Enables a sliding context window by default, maintaining context size. |
| **Max Retry Limit** | Sets the maximum number of retries (`max_retry_limit`) for an agent in case of errors. |
## Advanced Customization Options
Beyond the basic attributes, CrewAI allows for deeper customization to enhance an agent's behavior and capabilities significantly.
### Language Model Customization
Agents can be customized with specific language models (`llm`) and function-calling language models (`function_calling_llm`), offering advanced control over their processing and decision-making abilities.
It's important to note that setting the `function_calling_llm` allows for overriding the default crew function-calling language model, providing a greater degree of customization.
## Performance and Debugging Settings
Adjusting an agent's performance and monitoring its operations are crucial for efficient task execution.
### Verbose Mode and RPM Limit
* **Verbose Mode**: Enables detailed logging of an agent's actions, useful for debugging and optimization. Specifically, it provides insights into agent execution processes, aiding in the optimization of performance.
* **RPM Limit**: Sets the maximum number of requests per minute (`max_rpm`). This attribute is optional and can be set to `None` for no limit, allowing for unlimited queries to external services if needed.
### Maximum Iterations for Task Execution
The `max_iter` attribute allows users to define the maximum number of iterations an agent can perform for a single task, preventing infinite loops or excessively long executions.
The default value is set to 25, providing a balance between thoroughness and efficiency. Once the agent approaches this number, it will try its best to give a good answer.
## Customizing Agents and Tools
Agents are customized by defining their attributes and tools during initialization. Tools are critical for an agent's functionality, enabling them to perform specialized tasks.
The `tools` attribute should be an array of tools the agent can utilize, and it's initialized as an empty list by default. Tools can be added or modified post-agent initialization to adapt to new requirements.
```shell
pip install 'crewai[tools]'
```
### Example: Assigning Tools to an Agent
```python Code
import os
from crewai import Agent
from crewai_tools import SerperDevTool
# Set API keys for tool initialization
os.environ["OPENAI_API_KEY"] = "Your Key"
os.environ["SERPER_API_KEY"] = "Your Key"
# Initialize a search tool
search_tool = SerperDevTool()
# Initialize the agent with advanced options
agent = Agent(
role='Research Analyst',
goal='Provide up-to-date market analysis',
backstory='An expert analyst with a keen eye for market trends.',
tools=[search_tool],
memory=True, # Enable memory
verbose=True,
max_rpm=None, # No limit on requests per minute
max_iter=25, # Default value for maximum iterations
)
```
## Delegation and Autonomy
Controlling an agent's ability to delegate tasks or ask questions is vital for tailoring its autonomy and collaborative dynamics within the CrewAI framework. By default,
the `allow_delegation` attribute is now set to `False`, disabling agents to seek assistance or delegate tasks as needed. This default behavior can be changed to promote collaborative problem-solving and
efficiency within the CrewAI ecosystem. If needed, delegation can be enabled to suit specific operational requirements.
### Example: Disabling Delegation for an Agent
```python Code
agent = Agent(
role='Content Writer',
goal='Write engaging content on market trends',
backstory='A seasoned writer with expertise in market analysis.',
allow_delegation=True # Enabling delegation
)
```
## Conclusion
Customizing agents in CrewAI by setting their roles, goals, backstories, and tools, alongside advanced options like language model customization, memory, performance settings, and delegation preferences,
equips a nuanced and capable AI team ready for complex challenges.
# Force Tool Output as Result
Source: https://docs.crewai.com/how-to/force-tool-output-as-result
Learn how to force tool output as the result in an Agent's task in CrewAI.
## Introduction
In CrewAI, you can force the output of a tool as the result of an agent's task.
This feature is useful when you want to ensure that the tool output is captured and returned as the task result, avoiding any agent modification during the task execution.
## Forcing Tool Output as Result
To force the tool output as the result of an agent's task, you need to set the `result_as_answer` parameter to `True` when adding a tool to the agent.
This parameter ensures that the tool output is captured and returned as the task result, without any modifications by the agent.
Here's an example of how to force the tool output as the result of an agent's task:
```python Code
from crewai.agent import Agent
from my_tool import MyCustomTool
# Create a coding agent with the custom tool
coding_agent = Agent(
role="Data Scientist",
goal="Produce amazing reports on AI",
backstory="You work with data and AI",
tools=[MyCustomTool(result_as_answer=True)],
)
# Assuming the tool's execution and result population occurs within the system
task_result = coding_agent.execute_task(task)
```
## Workflow in Action
The agent executes the task using the tool provided.
The tool generates the output, which is captured as the task result.
The agent may reflect and take learnings from the tool but the output is not modified.
The tool output is returned as the task result without any modifications.
# Hierarchical Process
Source: https://docs.crewai.com/how-to/hierarchical-process
A comprehensive guide to understanding and applying the hierarchical process within your CrewAI projects, updated to reflect the latest coding practices and functionalities.
## Introduction
The hierarchical process in CrewAI introduces a structured approach to task management, simulating traditional organizational hierarchies for efficient task delegation and execution.
This systematic workflow enhances project outcomes by ensuring tasks are handled with optimal efficiency and accuracy.
The hierarchical process is designed to leverage advanced models like GPT-4, optimizing token usage while handling complex tasks with greater efficiency.
## Hierarchical Process Overview
By default, tasks in CrewAI are managed through a sequential process. However, adopting a hierarchical approach allows for a clear hierarchy in task management,
where a 'manager' agent coordinates the workflow, delegates tasks, and validates outcomes for streamlined and effective execution. This manager agent can now be either
automatically created by CrewAI or explicitly set by the user.
### Key Features
* **Task Delegation**: A manager agent allocates tasks among crew members based on their roles and capabilities.
* **Result Validation**: The manager evaluates outcomes to ensure they meet the required standards.
* **Efficient Workflow**: Emulates corporate structures, providing an organized approach to task management.
* **System Prompt Handling**: Optionally specify whether the system should use predefined prompts.
* **Stop Words Control**: Optionally specify whether stop words should be used, supporting various models including the o1 models.
* **Context Window Respect**: Prioritize important context by enabling respect of the context window, which is now the default behavior.
* **Delegation Control**: Delegation is now disabled by default to give users explicit control.
* **Max Requests Per Minute**: Configurable option to set the maximum number of requests per minute.
* **Max Iterations**: Limit the maximum number of iterations for obtaining a final answer.
## Implementing the Hierarchical Process
To utilize the hierarchical process, it's essential to explicitly set the process attribute to `Process.hierarchical`, as the default behavior is `Process.sequential`.
Define a crew with a designated manager and establish a clear chain of command.
Assign tools at the agent level to facilitate task delegation and execution by the designated agents under the manager's guidance.
Tools can also be specified at the task level for precise control over tool availability during task execution.
Configuring the `manager_llm` parameter is crucial for the hierarchical process.
The system requires a manager LLM to be set up for proper function, ensuring tailored decision-making.
```python Code
from crewai import Crew, Process, Agent
# Agents are defined with attributes for backstory, cache, and verbose mode
researcher = Agent(
role='Researcher',
goal='Conduct in-depth analysis',
backstory='Experienced data analyst with a knack for uncovering hidden trends.',
)
writer = Agent(
role='Writer',
goal='Create engaging content',
backstory='Creative writer passionate about storytelling in technical domains.',
)
# Establishing the crew with a hierarchical process and additional configurations
project_crew = Crew(
tasks=[...], # Tasks to be delegated and executed under the manager's supervision
agents=[researcher, writer],
manager_llm="gpt-4o", # Specify which LLM the manager should use
process=Process.hierarchical,
planning=True,
)
```
### Using a Custom Manager Agent
Alternatively, you can create a custom manager agent with specific attributes tailored to your project's management needs. This gives you more control over the manager's behavior and capabilities.
```python
# Define a custom manager agent
manager = Agent(
role="Project Manager",
goal="Efficiently manage the crew and ensure high-quality task completion",
backstory="You're an experienced project manager, skilled in overseeing complex projects and guiding teams to success.",
allow_delegation=True,
)
# Use the custom manager in your crew
project_crew = Crew(
tasks=[...],
agents=[researcher, writer],
manager_agent=manager, # Use your custom manager agent
process=Process.hierarchical,
planning=True,
)
```
For more details on creating and customizing a manager agent, check out the [Custom Manager Agent documentation](https://docs.crewai.com/how-to/custom-manager-agent#custom-manager-agent).
### Workflow in Action
1. **Task Assignment**: The manager assigns tasks strategically, considering each agent's capabilities and available tools.
2. **Execution and Review**: Agents complete their tasks with the option for asynchronous execution and callback functions for streamlined workflows.
3. **Sequential Task Progression**: Despite being a hierarchical process, tasks follow a logical order for smooth progression, facilitated by the manager's oversight.
## Conclusion
Adopting the hierarchical process in CrewAI, with the correct configurations and understanding of the system's capabilities, facilitates an organized and efficient approach to project management.
Utilize the advanced features and customizations to tailor the workflow to your specific needs, ensuring optimal task execution and project success.
# Human Input on Execution
Source: https://docs.crewai.com/how-to/human-input-on-execution
Integrating CrewAI with human input during execution in complex decision-making processes and leveraging the full capabilities of the agent's attributes and tools.
## Human input in agent execution
Human input is critical in several agent execution scenarios, allowing agents to request additional information or clarification when necessary.
This feature is especially useful in complex decision-making processes or when agents require more details to complete a task effectively.
## Using human input with CrewAI
To integrate human input into agent execution, set the `human_input` flag in the task definition. When enabled, the agent prompts the user for input before delivering its final answer.
This input can provide extra context, clarify ambiguities, or validate the agent's output.
### Example:
```shell
pip install crewai
```
```python Code
import os
from crewai import Agent, Task, Crew
from crewai_tools import SerperDevTool
os.environ["SERPER_API_KEY"] = "Your Key" # serper.dev API key
os.environ["OPENAI_API_KEY"] = "Your Key"
# Loading Tools
search_tool = SerperDevTool()
# Define your agents with roles, goals, tools, and additional attributes
researcher = Agent(
role='Senior Research Analyst',
goal='Uncover cutting-edge developments in AI and data science',
backstory=(
"You are a Senior Research Analyst at a leading tech think tank. "
"Your expertise lies in identifying emerging trends and technologies in AI and data science. "
"You have a knack for dissecting complex data and presenting actionable insights."
),
verbose=True,
allow_delegation=False,
tools=[search_tool]
)
writer = Agent(
role='Tech Content Strategist',
goal='Craft compelling content on tech advancements',
backstory=(
"You are a renowned Tech Content Strategist, known for your insightful and engaging articles on technology and innovation. "
"With a deep understanding of the tech industry, you transform complex concepts into compelling narratives."
),
verbose=True,
allow_delegation=True,
tools=[search_tool],
cache=False, # Disable cache for this agent
)
# Create tasks for your agents
task1 = Task(
description=(
"Conduct a comprehensive analysis of the latest advancements in AI in 2025. "
"Identify key trends, breakthrough technologies, and potential industry impacts. "
"Compile your findings in a detailed report. "
"Make sure to check with a human if the draft is good before finalizing your answer."
),
expected_output='A comprehensive full report on the latest AI advancements in 2025, leave nothing out',
agent=researcher,
human_input=True
)
task2 = Task(
description=(
"Using the insights from the researcher\'s report, develop an engaging blog post that highlights the most significant AI advancements. "
"Your post should be informative yet accessible, catering to a tech-savvy audience. "
"Aim for a narrative that captures the essence of these breakthroughs and their implications for the future."
),
expected_output='A compelling 3 paragraphs blog post formatted as markdown about the latest AI advancements in 2025',
agent=writer,
human_input=True
)
# Instantiate your crew with a sequential process
crew = Crew(
agents=[researcher, writer],
tasks=[task1, task2],
verbose=True,
memory=True,
planning=True # Enable planning feature for the crew
)
# Get your crew to work!
result = crew.kickoff()
print("######################")
print(result)
```
# Kickoff Crew Asynchronously
Source: https://docs.crewai.com/how-to/kickoff-async
Kickoff a Crew Asynchronously
## Introduction
CrewAI provides the ability to kickoff a crew asynchronously, allowing you to start the crew execution in a non-blocking manner.
This feature is particularly useful when you want to run multiple crews concurrently or when you need to perform other tasks while the crew is executing.
## Asynchronous Crew Execution
To kickoff a crew asynchronously, use the `kickoff_async()` method. This method initiates the crew execution in a separate thread, allowing the main thread to continue executing other tasks.
### Method Signature
```python Code
def kickoff_async(self, inputs: dict) -> CrewOutput:
```
### Parameters
* `inputs` (dict): A dictionary containing the input data required for the tasks.
### Returns
* `CrewOutput`: An object representing the result of the crew execution.
## Potential Use Cases
* **Parallel Content Generation**: Kickoff multiple independent crews asynchronously, each responsible for generating content on different topics. For example, one crew might research and draft an article on AI trends, while another crew generates social media posts about a new product launch. Each crew operates independently, allowing content production to scale efficiently.
* **Concurrent Market Research Tasks**: Launch multiple crews asynchronously to conduct market research in parallel. One crew might analyze industry trends, while another examines competitor strategies, and yet another evaluates consumer sentiment. Each crew independently completes its task, enabling faster and more comprehensive insights.
* **Independent Travel Planning Modules**: Execute separate crews to independently plan different aspects of a trip. One crew might handle flight options, another handles accommodation, and a third plans activities. Each crew works asynchronously, allowing various components of the trip to be planned simultaneously and independently for faster results.
## Example: Single Asynchronous Crew Execution
Here's an example of how to kickoff a crew asynchronously using asyncio and awaiting the result:
```python Code
import asyncio
from crewai import Crew, Agent, Task
# Create an agent with code execution enabled
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
# Create a task that requires code execution
data_analysis_task = Task(
description="Analyze the given dataset and calculate the average age of participants. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
# Create a crew and add the task
analysis_crew = Crew(
agents=[coding_agent],
tasks=[data_analysis_task]
)
# Async function to kickoff the crew asynchronously
async def async_crew_execution():
result = await analysis_crew.kickoff_async(inputs={"ages": [25, 30, 35, 40, 45]})
print("Crew Result:", result)
# Run the async function
asyncio.run(async_crew_execution())
```
## Example: Multiple Asynchronous Crew Executions
In this example, we'll show how to kickoff multiple crews asynchronously and wait for all of them to complete using `asyncio.gather()`:
```python Code
import asyncio
from crewai import Crew, Agent, Task
# Create an agent with code execution enabled
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
# Create tasks that require code execution
task_1 = Task(
description="Analyze the first dataset and calculate the average age of participants. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
task_2 = Task(
description="Analyze the second dataset and calculate the average age of participants. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
# Create two crews and add tasks
crew_1 = Crew(agents=[coding_agent], tasks=[task_1])
crew_2 = Crew(agents=[coding_agent], tasks=[task_2])
# Async function to kickoff multiple crews asynchronously and wait for all to finish
async def async_multiple_crews():
result_1 = crew_1.kickoff_async(inputs={"ages": [25, 30, 35, 40, 45]})
result_2 = crew_2.kickoff_async(inputs={"ages": [20, 22, 24, 28, 30]})
# Wait for both crews to finish
results = await asyncio.gather(result_1, result_2)
for i, result in enumerate(results, 1):
print(f"Crew {i} Result:", result)
# Run the async function
asyncio.run(async_multiple_crews())
```
# Kickoff Crew for Each
Source: https://docs.crewai.com/how-to/kickoff-for-each
Kickoff Crew for Each Item in a List
## Introduction
CrewAI provides the ability to kickoff a crew for each item in a list, allowing you to execute the crew for each item in the list.
This feature is particularly useful when you need to perform the same set of tasks for multiple items.
## Kicking Off a Crew for Each Item
To kickoff a crew for each item in a list, use the `kickoff_for_each()` method.
This method executes the crew for each item in the list, allowing you to process multiple items efficiently.
Here's an example of how to kickoff a crew for each item in a list:
```python Code
from crewai import Crew, Agent, Task
# Create an agent with code execution enabled
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
# Create a task that requires code execution
data_analysis_task = Task(
description="Analyze the given dataset and calculate the average age of participants. Ages: {ages}",
agent=coding_agent,
expected_output="The average age calculated from the dataset"
)
# Create a crew and add the task
analysis_crew = Crew(
agents=[coding_agent],
tasks=[data_analysis_task],
verbose=True,
memory=False
)
datasets = [
{ "ages": [25, 30, 35, 40, 45] },
{ "ages": [20, 25, 30, 35, 40] },
{ "ages": [30, 35, 40, 45, 50] }
]
# Execute the crew
result = analysis_crew.kickoff_for_each(inputs=datasets)
```
# Langfuse Integration
Source: https://docs.crewai.com/how-to/langfuse-observability
Learn how to integrate Langfuse with CrewAI via OpenTelemetry using OpenLit
# Integrate Langfuse with CrewAI
This notebook demonstrates how to integrate **Langfuse** with **CrewAI** using OpenTelemetry via the **OpenLit** SDK. By the end of this notebook, you will be able to trace your CrewAI applications with Langfuse for improved observability and debugging.
> **What is Langfuse?** [Langfuse](https://langfuse.com) is an open-source LLM engineering platform. It provides tracing and monitoring capabilities for LLM applications, helping developers debug, analyze, and optimize their AI systems. Langfuse integrates with various tools and frameworks via native integrations, OpenTelemetry, and APIs/SDKs.
[](https://langfuse.com/watch-demo)
## Get Started
We'll walk through a simple example of using CrewAI and integrating it with Langfuse via OpenTelemetry using OpenLit.
### Step 1: Install Dependencies
```python
%pip install langfuse openlit crewai crewai_tools
```
### Step 2: Set Up Environment Variables
Set your Langfuse API keys and configure OpenTelemetry export settings to send traces to Langfuse. Please refer to the [Langfuse OpenTelemetry Docs](https://langfuse.com/docs/opentelemetry/get-started) for more information on the Langfuse OpenTelemetry endpoint `/api/public/otel` and authentication.
```python
import os
import base64
LANGFUSE_PUBLIC_KEY="pk-lf-..."
LANGFUSE_SECRET_KEY="sk-lf-..."
LANGFUSE_AUTH=base64.b64encode(f"{LANGFUSE_PUBLIC_KEY}:{LANGFUSE_SECRET_KEY}".encode()).decode()
os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = "https://cloud.langfuse.com/api/public/otel" # EU data region
# os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = "https://us.cloud.langfuse.com/api/public/otel" # US data region
os.environ["OTEL_EXPORTER_OTLP_HEADERS"] = f"Authorization=Basic {LANGFUSE_AUTH}"
# your openai key
os.environ["OPENAI_API_KEY"] = "sk-..."
```
### Step 3: Initialize OpenLit
Initialize the OpenLit OpenTelemetry instrumentation SDK to start capturing OpenTelemetry traces.
```python
import openlit
openlit.init()
```
### Step 4: Create a Simple CrewAI Application
We'll create a simple CrewAI application where multiple agents collaborate to answer a user's question.
```python
from crewai import Agent, Task, Crew
from crewai_tools import (
WebsiteSearchTool
)
web_rag_tool = WebsiteSearchTool()
writer = Agent(
role="Writer",
goal="You make math engaging and understandable for young children through poetry",
backstory="You're an expert in writing haikus but you know nothing of math.",
tools=[web_rag_tool],
)
task = Task(description=("What is {multiplication}?"),
expected_output=("Compose a haiku that includes the answer."),
agent=writer)
crew = Crew(
agents=[writer],
tasks=[task],
share_crew=False
)
```
### Step 5: See Traces in Langfuse
After running the agent, you can view the traces generated by your CrewAI application in [Langfuse](https://cloud.langfuse.com). You should see detailed steps of the LLM interactions, which can help you debug and optimize your AI agent.
*[Public example trace in Langfuse](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/e2cf380ffc8d47d28da98f136140642b?timestamp=2025-02-05T15%3A12%3A02.717Z\&observation=3b32338ee6a5d9af)*
## References
* [Langfuse OpenTelemetry Docs](https://langfuse.com/docs/opentelemetry/get-started)
# Langtrace Integration
Source: https://docs.crewai.com/how-to/langtrace-observability
How to monitor cost, latency, and performance of CrewAI Agents using Langtrace, an external observability tool.
# Langtrace Overview
Langtrace is an open-source, external tool that helps you set up observability and evaluations for Large Language Models (LLMs), LLM frameworks, and Vector Databases.
While not built directly into CrewAI, Langtrace can be used alongside CrewAI to gain deep visibility into the cost, latency, and performance of your CrewAI Agents.
This integration allows you to log hyperparameters, monitor performance regressions, and establish a process for continuous improvement of your Agents.
## Setup Instructions
Sign up by visiting [https://langtrace.ai/signup](https://langtrace.ai/signup).
Set the project type to `CrewAI` and generate an API key.
Use the following command:
```bash
pip install langtrace-python-sdk
```
Import and initialize Langtrace at the beginning of your script, before any CrewAI imports:
```python
from langtrace_python_sdk import langtrace
langtrace.init(api_key='')
# Now import CrewAI modules
from crewai import Agent, Task, Crew
```
### Features and Their Application to CrewAI
1. **LLM Token and Cost Tracking**
* Monitor the token usage and associated costs for each CrewAI agent interaction.
2. **Trace Graph for Execution Steps**
* Visualize the execution flow of your CrewAI tasks, including latency and logs.
* Useful for identifying bottlenecks in your agent workflows.
3. **Dataset Curation with Manual Annotation**
* Create datasets from your CrewAI task outputs for future training or evaluation.
4. **Prompt Versioning and Management**
* Keep track of different versions of prompts used in your CrewAI agents.
* Useful for A/B testing and optimizing agent performance.
5. **Prompt Playground with Model Comparisons**
* Test and compare different prompts and models for your CrewAI agents before deployment.
6. **Testing and Evaluations**
* Set up automated tests for your CrewAI agents and tasks.
# Connect to any LLM
Source: https://docs.crewai.com/how-to/llm-connections
Comprehensive guide on integrating CrewAI with various Large Language Models (LLMs) using LiteLLM, including supported providers and configuration options.
## Connect CrewAI to LLMs
CrewAI uses LiteLLM to connect to a wide variety of Language Models (LLMs). This integration provides extensive versatility, allowing you to use models from numerous providers with a simple, unified interface.
By default, CrewAI uses the `gpt-4o-mini` model. This is determined by the `OPENAI_MODEL_NAME` environment variable, which defaults to "gpt-4o-mini" if not set.
You can easily configure your agents to use a different model or provider as described in this guide.
## Supported Providers
LiteLLM supports a wide range of providers, including but not limited to:
* OpenAI
* Anthropic
* Google (Vertex AI, Gemini)
* Azure OpenAI
* AWS (Bedrock, SageMaker)
* Cohere
* VoyageAI
* Hugging Face
* Ollama
* Mistral AI
* Replicate
* Together AI
* AI21
* Cloudflare Workers AI
* DeepInfra
* Groq
* SambaNova
* [NVIDIA NIMs](https://docs.api.nvidia.com/nim/reference/models-1)
* And many more!
For a complete and up-to-date list of supported providers, please refer to the [LiteLLM Providers documentation](https://docs.litellm.ai/docs/providers).
## Changing the LLM
To use a different LLM with your CrewAI agents, you have several options:
Pass the model name as a string when initializing the agent:
```python Code
from crewai import Agent
# Using OpenAI's GPT-4
openai_agent = Agent(
role='OpenAI Expert',
goal='Provide insights using GPT-4',
backstory="An AI assistant powered by OpenAI's latest model.",
llm='gpt-4'
)
# Using Anthropic's Claude
claude_agent = Agent(
role='Anthropic Expert',
goal='Analyze data using Claude',
backstory="An AI assistant leveraging Anthropic's language model.",
llm='claude-2'
)
```
For more detailed configuration, use the LLM class:
```python Code
from crewai import Agent, LLM
llm = LLM(
model="gpt-4",
temperature=0.7,
base_url="https://api.openai.com/v1",
api_key="your-api-key-here"
)
agent = Agent(
role='Customized LLM Expert',
goal='Provide tailored responses',
backstory="An AI assistant with custom LLM settings.",
llm=llm
)
```
## Configuration Options
When configuring an LLM for your agent, you have access to a wide range of parameters:
| Parameter | Type | Description |
| :--------------------- | :----------------: | :--------------------------------------------------------------- |
| **model** | `str` | The name of the model to use (e.g., "gpt-4", "claude-2") |
| **temperature** | `float` | Controls randomness in output (0.0 to 1.0) |
| **max\_tokens** | `int` | Maximum number of tokens to generate |
| **top\_p** | `float` | Controls diversity of output (0.0 to 1.0) |
| **frequency\_penalty** | `float` | Penalizes new tokens based on their frequency in the text so far |
| **presence\_penalty** | `float` | Penalizes new tokens based on their presence in the text so far |
| **stop** | `str`, `List[str]` | Sequence(s) to stop generation |
| **base\_url** | `str` | The base URL for the API endpoint |
| **api\_key** | `str` | Your API key for authentication |
For a complete list of parameters and their descriptions, refer to the LLM class documentation.
## Connecting to OpenAI-Compatible LLMs
You can connect to OpenAI-compatible LLMs using either environment variables or by setting specific attributes on the LLM class:
```python Code
import os
os.environ["OPENAI_API_KEY"] = "your-api-key"
os.environ["OPENAI_API_BASE"] = "https://api.your-provider.com/v1"
os.environ["OPENAI_MODEL_NAME"] = "your-model-name"
```
```python Code
llm = LLM(
model="custom-model-name",
api_key="your-api-key",
base_url="https://api.your-provider.com/v1"
)
agent = Agent(llm=llm, ...)
```
## Using Local Models with Ollama
For local models like those provided by Ollama:
[Click here to download and install Ollama](https://ollama.com/download)
For example, run `ollama pull llama3.2` to download the model.
```python Code
agent = Agent(
role='Local AI Expert',
goal='Process information using a local model',
backstory="An AI assistant running on local hardware.",
llm=LLM(model="ollama/llama3.2", base_url="http://localhost:11434")
)
```
## Changing the Base API URL
You can change the base API URL for any LLM provider by setting the `base_url` parameter:
```python Code
llm = LLM(
model="custom-model-name",
base_url="https://api.your-provider.com/v1",
api_key="your-api-key"
)
agent = Agent(llm=llm, ...)
```
This is particularly useful when working with OpenAI-compatible APIs or when you need to specify a different endpoint for your chosen provider.
## Conclusion
By leveraging LiteLLM, CrewAI offers seamless integration with a vast array of LLMs. This flexibility allows you to choose the most suitable model for your specific needs, whether you prioritize performance, cost-efficiency, or local deployment. Remember to consult the [LiteLLM documentation](https://docs.litellm.ai/docs/) for the most up-to-date information on supported models and configuration options.
# MLflow Integration
Source: https://docs.crewai.com/how-to/mlflow-observability
Quickly start monitoring your Agents with MLflow.
# MLflow Overview
[MLflow](https://mlflow.org/) is an open-source platform to assist machine learning practitioners and teams in handling the complexities of the machine learning process.
It provides a tracing feature that enhances LLM observability in your Generative AI applications by capturing detailed information about the execution of your application’s services.
Tracing provides a way to record the inputs, outputs, and metadata associated with each intermediate step of a request, enabling you to easily pinpoint the source of bugs and unexpected behaviors.
### Features
* **Tracing Dashboard**: Monitor activities of your crewAI agents with detailed dashboards that include inputs, outputs and metadata of spans.
* **Automated Tracing**: A fully automated integration with crewAI, which can be enabled by running `mlflow.crewai.autolog()`.
* **Manual Trace Instrumentation with minor efforts**: Customize trace instrumentation through MLflow's high-level fluent APIs such as decorators, function wrappers and context managers.
* **OpenTelemetry Compatibility**: MLflow Tracing supports exporting traces to an OpenTelemetry Collector, which can then be used to export traces to various backends such as Jaeger, Zipkin, and AWS X-Ray.
* **Package and Deploy Agents**: Package and deploy your crewAI agents to an inference server with a variety of deployment targets.
* **Securely Host LLMs**: Host multiple LLM from various providers in one unified endpoint through MFflow gateway.
* **Evaluation**: Evaluate your crewAI agents with a wide range of metrics using a convenient API `mlflow.evaluate()`.
## Setup Instructions
```shell
# The crewAI integration is available in mlflow>=2.19.0
pip install mlflow
```
```shell
# This process is optional, but it is recommended to use MLflow tracking server for better visualization and broader features.
mlflow server
```
Add the following two lines to your application code:
```python
import mlflow
mlflow.crewai.autolog()
# Optional: Set a tracking URI and an experiment name if you have a tracking server
mlflow.set_tracking_uri("http://localhost:5000")
mlflow.set_experiment("CrewAI")
```
Example Usage for tracing CrewAI Agents:
```python
from crewai import Agent, Crew, Task
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
from crewai_tools import SerperDevTool, WebsiteSearchTool
from textwrap import dedent
content = "Users name is John. He is 30 years old and lives in San Francisco."
string_source = StringKnowledgeSource(
content=content, metadata={"preference": "personal"}
)
search_tool = WebsiteSearchTool()
class TripAgents:
def city_selection_agent(self):
return Agent(
role="City Selection Expert",
goal="Select the best city based on weather, season, and prices",
backstory="An expert in analyzing travel data to pick ideal destinations",
tools=[
search_tool,
],
verbose=True,
)
def local_expert(self):
return Agent(
role="Local Expert at this city",
goal="Provide the BEST insights about the selected city",
backstory="""A knowledgeable local guide with extensive information
about the city, it's attractions and customs""",
tools=[search_tool],
verbose=True,
)
class TripTasks:
def identify_task(self, agent, origin, cities, interests, range):
return Task(
description=dedent(
f"""
Analyze and select the best city for the trip based
on specific criteria such as weather patterns, seasonal
events, and travel costs. This task involves comparing
multiple cities, considering factors like current weather
conditions, upcoming cultural or seasonal events, and
overall travel expenses.
Your final answer must be a detailed
report on the chosen city, and everything you found out
about it, including the actual flight costs, weather
forecast and attractions.
Traveling from: {origin}
City Options: {cities}
Trip Date: {range}
Traveler Interests: {interests}
"""
),
agent=agent,
expected_output="Detailed report on the chosen city including flight costs, weather forecast, and attractions",
)
def gather_task(self, agent, origin, interests, range):
return Task(
description=dedent(
f"""
As a local expert on this city you must compile an
in-depth guide for someone traveling there and wanting
to have THE BEST trip ever!
Gather information about key attractions, local customs,
special events, and daily activity recommendations.
Find the best spots to go to, the kind of place only a
local would know.
This guide should provide a thorough overview of what
the city has to offer, including hidden gems, cultural
hotspots, must-visit landmarks, weather forecasts, and
high level costs.
The final answer must be a comprehensive city guide,
rich in cultural insights and practical tips,
tailored to enhance the travel experience.
Trip Date: {range}
Traveling from: {origin}
Traveler Interests: {interests}
"""
),
agent=agent,
expected_output="Comprehensive city guide including hidden gems, cultural hotspots, and practical travel tips",
)
class TripCrew:
def __init__(self, origin, cities, date_range, interests):
self.cities = cities
self.origin = origin
self.interests = interests
self.date_range = date_range
def run(self):
agents = TripAgents()
tasks = TripTasks()
city_selector_agent = agents.city_selection_agent()
local_expert_agent = agents.local_expert()
identify_task = tasks.identify_task(
city_selector_agent,
self.origin,
self.cities,
self.interests,
self.date_range,
)
gather_task = tasks.gather_task(
local_expert_agent, self.origin, self.interests, self.date_range
)
crew = Crew(
agents=[city_selector_agent, local_expert_agent],
tasks=[identify_task, gather_task],
verbose=True,
memory=True,
knowledge={
"sources": [string_source],
"metadata": {"preference": "personal"},
},
)
result = crew.kickoff()
return result
trip_crew = TripCrew("California", "Tokyo", "Dec 12 - Dec 20", "sports")
result = trip_crew.run()
print(result)
```
Refer to [MLflow Tracing Documentation](https://mlflow.org/docs/latest/llms/tracing/index.html) for more configurations and use cases.
Now traces for your crewAI agents are captured by MLflow.
Let's visit MLflow tracking server to view the traces and get insights into your Agents.
Open `127.0.0.1:5000` on your browser to visit MLflow tracking server.
# Using Multimodal Agents
Source: https://docs.crewai.com/how-to/multimodal-agents
Learn how to enable and use multimodal capabilities in your agents for processing images and other non-text content within the CrewAI framework.
## Using Multimodal Agents
CrewAI supports multimodal agents that can process both text and non-text content like images. This guide will show you how to enable and use multimodal capabilities in your agents.
### Enabling Multimodal Capabilities
To create a multimodal agent, simply set the `multimodal` parameter to `True` when initializing your agent:
```python
from crewai import Agent
agent = Agent(
role="Image Analyst",
goal="Analyze and extract insights from images",
backstory="An expert in visual content interpretation with years of experience in image analysis",
multimodal=True # This enables multimodal capabilities
)
```
When you set `multimodal=True`, the agent is automatically configured with the necessary tools for handling non-text content, including the `AddImageTool`.
### Working with Images
The multimodal agent comes pre-configured with the `AddImageTool`, which allows it to process images. You don't need to manually add this tool - it's automatically included when you enable multimodal capabilities.
Here's a complete example showing how to use a multimodal agent to analyze an image:
```python
from crewai import Agent, Task, Crew
# Create a multimodal agent
image_analyst = Agent(
role="Product Analyst",
goal="Analyze product images and provide detailed descriptions",
backstory="Expert in visual product analysis with deep knowledge of design and features",
multimodal=True
)
# Create a task for image analysis
task = Task(
description="Analyze the product image at https://example.com/product.jpg and provide a detailed description",
expected_output="A detailed description of the product image",
agent=image_analyst
)
# Create and run the crew
crew = Crew(
agents=[image_analyst],
tasks=[task]
)
result = crew.kickoff()
```
### Advanced Usage with Context
You can provide additional context or specific questions about the image when creating tasks for multimodal agents. The task description can include specific aspects you want the agent to focus on:
```python
from crewai import Agent, Task, Crew
# Create a multimodal agent for detailed analysis
expert_analyst = Agent(
role="Visual Quality Inspector",
goal="Perform detailed quality analysis of product images",
backstory="Senior quality control expert with expertise in visual inspection",
multimodal=True # AddImageTool is automatically included
)
# Create a task with specific analysis requirements
inspection_task = Task(
description="""
Analyze the product image at https://example.com/product.jpg with focus on:
1. Quality of materials
2. Manufacturing defects
3. Compliance with standards
Provide a detailed report highlighting any issues found.
""",
expected_output="A detailed report highlighting any issues found",
agent=expert_analyst
)
# Create and run the crew
crew = Crew(
agents=[expert_analyst],
tasks=[inspection_task]
)
result = crew.kickoff()
```
### Tool Details
When working with multimodal agents, the `AddImageTool` is automatically configured with the following schema:
```python
class AddImageToolSchema:
image_url: str # Required: The URL or path of the image to process
action: Optional[str] = None # Optional: Additional context or specific questions about the image
```
The multimodal agent will automatically handle the image processing through its built-in tools, allowing it to:
* Access images via URLs or local file paths
* Process image content with optional context or specific questions
* Provide analysis and insights based on the visual information and task requirements
### Best Practices
When working with multimodal agents, keep these best practices in mind:
1. **Image Access**
* Ensure your images are accessible via URLs that the agent can reach
* For local images, consider hosting them temporarily or using absolute file paths
* Verify that image URLs are valid and accessible before running tasks
2. **Task Description**
* Be specific about what aspects of the image you want the agent to analyze
* Include clear questions or requirements in the task description
* Consider using the optional `action` parameter for focused analysis
3. **Resource Management**
* Image processing may require more computational resources than text-only tasks
* Some language models may require base64 encoding for image data
* Consider batch processing for multiple images to optimize performance
4. **Environment Setup**
* Verify that your environment has the necessary dependencies for image processing
* Ensure your language model supports multimodal capabilities
* Test with small images first to validate your setup
5. **Error Handling**
* Implement proper error handling for image loading failures
* Have fallback strategies for when image processing fails
* Monitor and log image processing operations for debugging
# OpenLIT Integration
Source: https://docs.crewai.com/how-to/openlit-observability
Quickly start monitoring your Agents in just a single line of code with OpenTelemetry.
# OpenLIT Overview
[OpenLIT](https://github.com/openlit/openlit?src=crewai-docs) is an open-source tool that makes it simple to monitor the performance of AI agents, LLMs, VectorDBs, and GPUs with just **one** line of code.
It provides OpenTelemetry-native tracing and metrics to track important parameters like cost, latency, interactions and task sequences.
This setup enables you to track hyperparameters and monitor for performance issues, helping you find ways to enhance and fine-tune your agents over time.
### Features
* **Analytics Dashboard**: Monitor your Agents health and performance with detailed dashboards that track metrics, costs, and user interactions.
* **OpenTelemetry-native Observability SDK**: Vendor-neutral SDKs to send traces and metrics to your existing observability tools like Grafana, DataDog and more.
* **Cost Tracking for Custom and Fine-Tuned Models**: Tailor cost estimations for specific models using custom pricing files for precise budgeting.
* **Exceptions Monitoring Dashboard**: Quickly spot and resolve issues by tracking common exceptions and errors with a monitoring dashboard.
* **Compliance and Security**: Detect potential threats such as profanity and PII leaks.
* **Prompt Injection Detection**: Identify potential code injection and secret leaks.
* **API Keys and Secrets Management**: Securely handle your LLM API keys and secrets centrally, avoiding insecure practices.
* **Prompt Management**: Manage and version Agent prompts using PromptHub for consistent and easy access across Agents.
* **Model Playground** Test and compare different models for your CrewAI agents before deployment.
## Setup Instructions
```shell
git clone git@github.com:openlit/openlit.git
```
From the root directory of the [OpenLIT Repo](https://github.com/openlit/openlit), Run the below command:
```shell
docker compose up -d
```
```shell
pip install openlit
```
Add the following two lines to your application code:
```python
import openlit
openlit.init(otlp_endpoint="http://127.0.0.1:4318")
```
Example Usage for monitoring a CrewAI Agent:
```python
from crewai import Agent, Task, Crew, Process
import openlit
openlit.init(disable_metrics=True)
# Define your agents
researcher = Agent(
role="Researcher",
goal="Conduct thorough research and analysis on AI and AI agents",
backstory="You're an expert researcher, specialized in technology, software engineering, AI, and startups. You work as a freelancer and are currently researching for a new client.",
allow_delegation=False,
llm='command-r'
)
# Define your task
task = Task(
description="Generate a list of 5 interesting ideas for an article, then write one captivating paragraph for each idea that showcases the potential of a full article on this topic. Return the list of ideas with their paragraphs and your notes.",
expected_output="5 bullet points, each with a paragraph and accompanying notes.",
)
# Define the manager agent
manager = Agent(
role="Project Manager",
goal="Efficiently manage the crew and ensure high-quality task completion",
backstory="You're an experienced project manager, skilled in overseeing complex projects and guiding teams to success. Your role is to coordinate the efforts of the crew members, ensuring that each task is completed on time and to the highest standard.",
allow_delegation=True,
llm='command-r'
)
# Instantiate your crew with a custom manager
crew = Crew(
agents=[researcher],
tasks=[task],
manager_agent=manager,
process=Process.hierarchical,
)
# Start the crew's work
result = crew.kickoff()
print(result)
```
Add the following two lines to your application code:
```python
import openlit
openlit.init()
```
Run the following command to configure the OTEL export endpoint:
```shell
export OTEL_EXPORTER_OTLP_ENDPOINT = "http://127.0.0.1:4318"
```
Example Usage for monitoring a CrewAI Async Agent:
```python
import asyncio
from crewai import Crew, Agent, Task
import openlit
openlit.init(otlp_endpoint="http://127.0.0.1:4318")
# Create an agent with code execution enabled
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True,
llm="command-r"
)
# Create a task that requires code execution
data_analysis_task = Task(
description="Analyze the given dataset and calculate the average age of participants. Ages: {ages}",
agent=coding_agent,
expected_output="5 bullet points, each with a paragraph and accompanying notes.",
)
# Create a crew and add the task
analysis_crew = Crew(
agents=[coding_agent],
tasks=[data_analysis_task]
)
# Async function to kickoff the crew asynchronously
async def async_crew_execution():
result = await analysis_crew.kickoff_async(inputs={"ages": [25, 30, 35, 40, 45]})
print("Crew Result:", result)
# Run the async function
asyncio.run(async_crew_execution())
```
Refer to OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
With the Agent Observability data now being collected and sent to OpenLIT, the next step is to visualize and analyze this data to get insights into your Agent's performance, behavior, and identify areas of improvement.
Just head over to OpenLIT at `127.0.0.1:3000` on your browser to start exploring. You can login using the default credentials
* **Email**: `user@openlit.io`
* **Password**: `openlituser`
# Opik Integration
Source: https://docs.crewai.com/how-to/opik-observability
Learn how to use Comet Opik to debug, evaluate, and monitor your CrewAI applications with comprehensive tracing, automated evaluations, and production-ready dashboards.
# Opik Overview
With [Comet Opik](https://www.comet.com/docs/opik/), debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Opik provides comprehensive support for every stage of your CrewAI application development:
* **Log Traces and Spans**: Automatically track LLM calls and application logic to debug and analyze development and production systems. Manually or programmatically annotate, view, and compare responses across projects.
* **Evaluate Your LLM Application's Performance**: Evaluate against a custom test set and run built-in evaluation metrics or define your own metrics in the SDK or UI.
* **Test Within Your CI/CD Pipeline**: Establish reliable performance baselines with Opik's LLM unit tests, built on PyTest. Run online evaluations for continuous monitoring in production.
* **Monitor & Analyze Production Data**: Understand your models' performance on unseen data in production and generate datasets for new dev iterations.
## Setup
Comet provides a hosted version of the Opik platform, or you can run the platform locally.
To use the hosted version, simply [create a free Comet account](https://www.comet.com/signup?utm_medium=github\&utm_source=crewai_docs) and grab you API Key.
To run the Opik platform locally, see our [installation guide](https://www.comet.com/docs/opik/self-host/overview/) for more information.
For this guide we will use CrewAI’s quickstart example.
```shell
pip install crewai crewai-tools opik --upgrade
```
```python
import opik
opik.configure(use_local=False)
```
First, we set up our API keys for our LLM-provider as environment variables:
```python
import os
import getpass
if "OPENAI_API_KEY" not in os.environ:
os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter your OpenAI API key: ")
```
The first step is to create our project. We will use an example from CrewAI’s documentation:
```python
from crewai import Agent, Crew, Task, Process
class YourCrewName:
def agent_one(self) -> Agent:
return Agent(
role="Data Analyst",
goal="Analyze data trends in the market",
backstory="An experienced data analyst with a background in economics",
verbose=True,
)
def agent_two(self) -> Agent:
return Agent(
role="Market Researcher",
goal="Gather information on market dynamics",
backstory="A diligent researcher with a keen eye for detail",
verbose=True,
)
def task_one(self) -> Task:
return Task(
name="Collect Data Task",
description="Collect recent market data and identify trends.",
expected_output="A report summarizing key trends in the market.",
agent=self.agent_one(),
)
def task_two(self) -> Task:
return Task(
name="Market Research Task",
description="Research factors affecting market dynamics.",
expected_output="An analysis of factors influencing the market.",
agent=self.agent_two(),
)
def crew(self) -> Crew:
return Crew(
agents=[self.agent_one(), self.agent_two()],
tasks=[self.task_one(), self.task_two()],
process=Process.sequential,
verbose=True,
)
```
Now we can import Opik’s tracker and run our crew:
```python
from opik.integrations.crewai import track_crewai
track_crewai(project_name="crewai-integration-demo")
my_crew = YourCrewName().crew()
result = my_crew.kickoff()
print(result)
```
After running your CrewAI application, visit the Opik app to view:
* LLM traces, spans, and their metadata
* Agent interactions and task execution flow
* Performance metrics like latency and token usage
* Evaluation metrics (built-in or custom)
## Resources
* [🦉 Opik Documentation](https://www.comet.com/docs/opik/)
* [👉 Opik + CrewAI Colab](https://colab.research.google.com/github/comet-ml/opik/blob/main/apps/opik-documentation/documentation/docs/cookbook/crewai.ipynb)
* [🐦 X](https://x.com/cometml)
* [💬 Slack](https://slack.comet.com/)
# Portkey Integration
Source: https://docs.crewai.com/how-to/portkey-observability
How to use Portkey with CrewAI
[Portkey](https://portkey.ai/?utm_source=crewai\&utm_medium=crewai\&utm_campaign=crewai) is a 2-line upgrade to make your CrewAI agents reliable, cost-efficient, and fast.
Portkey adds 4 core production capabilities to any CrewAI agent:
1. Routing to **200+ LLMs**
2. Making each LLM call more robust
3. Full-stack tracing & cost, performance analytics
4. Real-time guardrails to enforce behavior
## Getting Started
```bash
pip install -qU crewai portkey-ai
```
To build CrewAI Agents with Portkey, you'll need two keys:
* **Portkey API Key**: Sign up on the [Portkey app](https://app.portkey.ai/?utm_source=crewai\&utm_medium=crewai\&utm_campaign=crewai) and copy your API key
* **Virtual Key**: Virtual Keys securely manage your LLM API keys in one place. Store your LLM provider API keys securely in Portkey's vault
```python
from crewai import LLM
from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
gpt_llm = LLM(
model="gpt-4",
base_url=PORTKEY_GATEWAY_URL,
api_key="dummy", # We are using Virtual key
extra_headers=createHeaders(
api_key="YOUR_PORTKEY_API_KEY",
virtual_key="YOUR_VIRTUAL_KEY", # Enter your Virtual key from Portkey
)
)
```
```python
from crewai import Agent, Task, Crew
# Define your agents with roles and goals
coder = Agent(
role='Software developer',
goal='Write clear, concise code on demand',
backstory='An expert coder with a keen eye for software trends.',
llm=gpt_llm
)
# Create tasks for your agents
task1 = Task(
description="Define the HTML for making a simple website with heading- Hello World! Portkey is working!",
expected_output="A clear and concise HTML code",
agent=coder
)
# Instantiate your crew
crew = Crew(
agents=[coder],
tasks=[task1],
)
result = crew.kickoff()
print(result)
```
## Key Features
| Feature | Description |
| :------------------------- | :-------------------------------------------------------------------------------------- |
| 🌐 Multi-LLM Support | Access OpenAI, Anthropic, Gemini, Azure, and 250+ providers through a unified interface |
| 🛡️ Production Reliability | Implement retries, timeouts, load balancing, and fallbacks |
| 📊 Advanced Observability | Track 40+ metrics including costs, tokens, latency, and custom metadata |
| 🔍 Comprehensive Logging | Debug with detailed execution traces and function call logs |
| 🚧 Security Controls | Set budget limits and implement role-based access control |
| 🔄 Performance Analytics | Capture and analyze feedback for continuous improvement |
| 💾 Intelligent Caching | Reduce costs and latency with semantic or simple caching |
## Production Features with Portkey Configs
All features mentioned below are through Portkey's Config system. Portkey's Config system allows you to define routing strategies using simple JSON objects in your LLM API calls. You can create and manage Configs directly in your code or through the Portkey Dashboard. Each Config has a unique ID for easy reference.
### 1. Use 250+ LLMs
Access various LLMs like Anthropic, Gemini, Mistral, Azure OpenAI, and more with minimal code changes. Switch between providers or use them together seamlessly. [Learn more about Universal API](https://portkey.ai/docs/product/ai-gateway/universal-api)
Easily switch between different LLM providers:
```python
# Anthropic Configuration
anthropic_llm = LLM(
model="claude-3-5-sonnet-latest",
base_url=PORTKEY_GATEWAY_URL,
api_key="dummy",
extra_headers=createHeaders(
api_key="YOUR_PORTKEY_API_KEY",
virtual_key="YOUR_ANTHROPIC_VIRTUAL_KEY", #You don't need provider when using Virtual keys
trace_id="anthropic_agent"
)
)
# Azure OpenAI Configuration
azure_llm = LLM(
model="gpt-4",
base_url=PORTKEY_GATEWAY_URL,
api_key="dummy",
extra_headers=createHeaders(
api_key="YOUR_PORTKEY_API_KEY",
virtual_key="YOUR_AZURE_VIRTUAL_KEY", #You don't need provider when using Virtual keys
trace_id="azure_agent"
)
)
```
### 2. Caching
Improve response times and reduce costs with two powerful caching modes:
* **Simple Cache**: Perfect for exact matches
* **Semantic Cache**: Matches responses for requests that are semantically similar
[Learn more about Caching](https://portkey.ai/docs/product/ai-gateway/cache-simple-and-semantic)
```py
config = {
"cache": {
"mode": "semantic", # or "simple" for exact matching
}
}
```
### 3. Production Reliability
Portkey provides comprehensive reliability features:
* **Automatic Retries**: Handle temporary failures gracefully
* **Request Timeouts**: Prevent hanging operations
* **Conditional Routing**: Route requests based on specific conditions
* **Fallbacks**: Set up automatic provider failovers
* **Load Balancing**: Distribute requests efficiently
[Learn more about Reliability Features](https://portkey.ai/docs/product/ai-gateway/)
### 4. Metrics
Agent runs are complex. Portkey automatically logs **40+ comprehensive metrics** for your AI agents, including cost, tokens used, latency, etc. Whether you need a broad overview or granular insights into your agent runs, Portkey's customizable filters provide the metrics you need.
* Cost per agent interaction
* Response times and latency
* Token usage and efficiency
* Success/failure rates
* Cache hit rates
### 5. Detailed Logging
Logs are essential for understanding agent behavior, diagnosing issues, and improving performance. They provide a detailed record of agent activities and tool use, which is crucial for debugging and optimizing processes.
Access a dedicated section to view records of agent executions, including parameters, outcomes, function calls, and errors. Filter logs based on multiple parameters such as trace ID, model, tokens used, and metadata.
TracesLogs
### 6. Enterprise Security Features
* Set budget limit and rate limts per Virtual Key (disposable API keys)
* Implement role-based access control
* Track system changes with audit logs
* Configure data retention policies
For detailed information on creating and managing Configs, visit the [Portkey documentation](https://docs.portkey.ai/product/ai-gateway/configs).
## Resources
* [📘 Portkey Documentation](https://docs.portkey.ai)
* [📊 Portkey Dashboard](https://app.portkey.ai/?utm_source=crewai\&utm_medium=crewai\&utm_campaign=crewai)
* [🐦 Twitter](https://twitter.com/portkeyai)
* [💬 Discord Community](https://discord.gg/DD7vgKK299)
# Replay Tasks from Latest Crew Kickoff
Source: https://docs.crewai.com/how-to/replay-tasks-from-latest-crew-kickoff
Replay tasks from the latest crew.kickoff(...)
## Introduction
CrewAI provides the ability to replay from a task specified from the latest crew kickoff. This feature is particularly useful when you've finished a kickoff and may want to retry certain tasks or don't need to refetch data over and your agents already have the context saved from the kickoff execution so you just need to replay the tasks you want to.
You must run `crew.kickoff()` before you can replay a task.
Currently, only the latest kickoff is supported, so if you use `kickoff_for_each`, it will only allow you to replay from the most recent crew run.
Here's an example of how to replay from a task:
### Replaying from Specific Task Using the CLI
To use the replay feature, follow these steps:
To view the latest kickoff task\_ids use:
```shell
crewai log-tasks-outputs
```
Once you have your `task_id` to replay, use:
```shell
crewai replay -t
```
Ensure `crewai` is installed and configured correctly in your development environment.
### Replaying from a Task Programmatically
To replay from a task programmatically, use the following steps:
Specify the `task_id` and input parameters for the replay process.
Execute the replay command within a try-except block to handle potential errors.
```python Code
def replay():
"""
Replay the crew execution from a specific task.
"""
task_id = ''
inputs = {"topic": "CrewAI Training"} # This is optional; you can pass in the inputs you want to replay; otherwise, it uses the previous kickoff's inputs.
try:
YourCrewName_Crew().crew().replay(task_id=task_id, inputs=inputs)
except subprocess.CalledProcessError as e:
raise Exception(f"An error occurred while replaying the crew: {e}")
except Exception as e:
raise Exception(f"An unexpected error occurred: {e}")
```
## Conclusion
With the above enhancements and detailed functionality, replaying specific tasks in CrewAI has been made more efficient and robust.
Ensure you follow the commands and steps precisely to make the most of these features.
# Sequential Processes
Source: https://docs.crewai.com/how-to/sequential-process
A comprehensive guide to utilizing the sequential processes for task execution in CrewAI projects.
## Introduction
CrewAI offers a flexible framework for executing tasks in a structured manner, supporting both sequential and hierarchical processes.
This guide outlines how to effectively implement these processes to ensure efficient task execution and project completion.
## Sequential Process Overview
The sequential process ensures tasks are executed one after the other, following a linear progression.
This approach is ideal for projects requiring tasks to be completed in a specific order.
### Key Features
* **Linear Task Flow**: Ensures orderly progression by handling tasks in a predetermined sequence.
* **Simplicity**: Best suited for projects with clear, step-by-step tasks.
* **Easy Monitoring**: Facilitates easy tracking of task completion and project progress.
## Implementing the Sequential Process
To use the sequential process, assemble your crew and define tasks in the order they need to be executed.
```python Code
from crewai import Crew, Process, Agent, Task, TaskOutput, CrewOutput
# Define your agents
researcher = Agent(
role='Researcher',
goal='Conduct foundational research',
backstory='An experienced researcher with a passion for uncovering insights'
)
analyst = Agent(
role='Data Analyst',
goal='Analyze research findings',
backstory='A meticulous analyst with a knack for uncovering patterns'
)
writer = Agent(
role='Writer',
goal='Draft the final report',
backstory='A skilled writer with a talent for crafting compelling narratives'
)
# Define your tasks
research_task = Task(
description='Gather relevant data...',
agent=researcher,
expected_output='Raw Data'
)
analysis_task = Task(
description='Analyze the data...',
agent=analyst,
expected_output='Data Insights'
)
writing_task = Task(
description='Compose the report...',
agent=writer,
expected_output='Final Report'
)
# Form the crew with a sequential process
report_crew = Crew(
agents=[researcher, analyst, writer],
tasks=[research_task, analysis_task, writing_task],
process=Process.sequential
)
# Execute the crew
result = report_crew.kickoff()
# Accessing the type-safe output
task_output: TaskOutput = result.tasks[0].output
crew_output: CrewOutput = result.output
```
### Note:
Each task in a sequential process **must** have an agent assigned. Ensure that every `Task` includes an `agent` parameter.
### Workflow in Action
1. **Initial Task**: In a sequential process, the first agent completes their task and signals completion.
2. **Subsequent Tasks**: Agents pick up their tasks based on the process type, with outcomes of preceding tasks or directives guiding their execution.
3. **Completion**: The process concludes once the final task is executed, leading to project completion.
## Advanced Features
### Task Delegation
In sequential processes, if an agent has `allow_delegation` set to `True`, they can delegate tasks to other agents in the crew.
This feature is automatically set up when there are multiple agents in the crew.
### Asynchronous Execution
Tasks can be executed asynchronously, allowing for parallel processing when appropriate.
To create an asynchronous task, set `async_execution=True` when defining the task.
### Memory and Caching
CrewAI supports both memory and caching features:
* **Memory**: Enable by setting `memory=True` when creating the Crew. This allows agents to retain information across tasks.
* **Caching**: By default, caching is enabled. Set `cache=False` to disable it.
### Callbacks
You can set callbacks at both the task and step level:
* `task_callback`: Executed after each task completion.
* `step_callback`: Executed after each step in an agent's execution.
### Usage Metrics
CrewAI tracks token usage across all tasks and agents. You can access these metrics after execution.
## Best Practices for Sequential Processes
1. **Order Matters**: Arrange tasks in a logical sequence where each task builds upon the previous one.
2. **Clear Task Descriptions**: Provide detailed descriptions for each task to guide the agents effectively.
3. **Appropriate Agent Selection**: Match agents' skills and roles to the requirements of each task.
4. **Use Context**: Leverage the context from previous tasks to inform subsequent ones.
This updated documentation ensures that details accurately reflect the latest changes in the codebase and clearly describes how to leverage new features and configurations.
The content is kept simple and direct to ensure easy understanding.
# Weave Integration
Source: https://docs.crewai.com/how-to/weave-integration
Learn how to use Weights & Biases (W&B) Weave to track, experiment with, evaluate, and improve your CrewAI applications.
# Weave Overview
[Weights & Biases (W\&B) Weave](https://weave-docs.wandb.ai/) is a framework for tracking, experimenting with, evaluating, deploying, and improving LLM-based applications.
Weave provides comprehensive support for every stage of your CrewAI application development:
* **Tracing & Monitoring**: Automatically track LLM calls and application logic to debug and analyze production systems
* **Systematic Iteration**: Refine and iterate on prompts, datasets, and models
* **Evaluation**: Use custom or pre-built scorers to systematically assess and enhance agent performance
* **Guardrails**: Protect your agents with pre- and post-safeguards for content moderation and prompt safety
Weave automatically captures traces for your CrewAI applications, enabling you to monitor and analyze your agents' performance, interactions, and execution flow. This helps you build better evaluation datasets and optimize your agent workflows.
## Setup Instructions
```shell
pip install crewai weave
```
Sign up for a [Weights & Biases account](https://wandb.ai) if you haven't already. You'll need this to view your traces and metrics.
Add the following code to your application:
```python
import weave
# Initialize Weave with your project name
weave.init(project_name="crewai_demo")
```
After initialization, Weave will provide a URL where you can view your traces and metrics.
```python
from crewai import Agent, Task, Crew, LLM, Process
# Create an LLM with a temperature of 0 to ensure deterministic outputs
llm = LLM(model="gpt-4o", temperature=0)
# Create agents
researcher = Agent(
role='Research Analyst',
goal='Find and analyze the best investment opportunities',
backstory='Expert in financial analysis and market research',
llm=llm,
verbose=True,
allow_delegation=False,
)
writer = Agent(
role='Report Writer',
goal='Write clear and concise investment reports',
backstory='Experienced in creating detailed financial reports',
llm=llm,
verbose=True,
allow_delegation=False,
)
# Create tasks
research_task = Task(
description='Deep research on the {topic}',
expected_output='Comprehensive market data including key players, market size, and growth trends.',
agent=researcher
)
writing_task = Task(
description='Write a detailed report based on the research',
expected_output='The report should be easy to read and understand. Use bullet points where applicable.',
agent=writer
)
# Create a crew
crew = Crew(
agents=[researcher, writer],
tasks=[research_task, writing_task],
verbose=True,
process=Process.sequential,
)
# Run the crew
result = crew.kickoff(inputs={"topic": "AI in material science"})
print(result)
```
After running your CrewAI application, visit the Weave URL provided during initialization to view:
* LLM calls and their metadata
* Agent interactions and task execution flow
* Performance metrics like latency and token usage
* Any errors or issues that occurred during execution
## Features
* Weave automatically captures all CrewAI operations: agent interactions and task executions; LLM calls with metadata and token usage; tool usage and results.
* The integration supports all CrewAI execution methods: `kickoff()`, `kickoff_for_each()`, `kickoff_async()`, and `kickoff_for_each_async()`.
* Automatic tracing of all [crewAI-tools](https://github.com/crewAIInc/crewAI-tools).
* Flow feature support with decorator patching (`@start`, `@listen`, `@router`, `@or_`, `@and_`).
* Track custom guardrails passed to CrewAI `Task` with `@weave.op()`.
For detailed information on what's supported, visit the [Weave CrewAI documentation](https://weave-docs.wandb.ai/guides/integrations/crewai/#getting-started-with-flow).
## Resources
* [📘 Weave Documentation](https://weave-docs.wandb.ai)
* [📊 Example Weave x CrewAI dashboard](https://wandb.ai/ayut/crewai_demo/weave/traces?cols=%7B%22wb_run_id%22%3Afalse%2C%22attributes.weave.client_version%22%3Afalse%2C%22attributes.weave.os_name%22%3Afalse%2C%22attributes.weave.os_release%22%3Afalse%2C%22attributes.weave.os_version%22%3Afalse%2C%22attributes.weave.source%22%3Afalse%2C%22attributes.weave.sys_version%22%3Afalse%7D\&peekPath=%2Fayut%2Fcrewai_demo%2Fcalls%2F0195c838-38cb-71a2-8a15-651ecddf9d89)
* [🐦 X](https://x.com/weave_wb)
# Installation
Source: https://docs.crewai.com/installation
Get started with CrewAI - Install, configure, and build your first AI crew
## Video Tutorial
Watch this video tutorial for a step-by-step demonstration of the installation process:
## Text Tutorial
**Python Version Requirements**
CrewAI requires `Python >=3.10 and <3.13`. Here's how to check your version:
```bash
python3 --version
```
If you need to update Python, visit [python.org/downloads](https://python.org/downloads)
CrewAI uses the `uv` as its dependency management and package handling tool. It simplifies project setup and execution, offering a seamless experience.
If you haven't installed `uv` yet, follow **step 1** to quickly get it set up on your system, else you can skip to **step 2**.
* **On macOS/Linux:**
Use `curl` to download the script and execute it with `sh`:
```shell
curl -LsSf https://astral.sh/uv/install.sh | sh
```
If your system doesn't have `curl`, you can use `wget`:
```shell
wget -qO- https://astral.sh/uv/install.sh | sh
```
* **On Windows:**
Use `irm` to download the script and `iex` to execute it:
```shell
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
```
If you run into any issues, refer to [UV's installation guide](https://docs.astral.sh/uv/getting-started/installation/) for more information.
* Run the following command to install `crewai` CLI:
```shell
uv tool install crewai
```
If you encounter a `PATH` warning, run this command to update your shell:
```shell
uv tool update-shell
```
* To verify that `crewai` is installed, run:
```shell
uv tool list
```
* You should see something like:
```shell
crewai v0.102.0
- crewai
```
* If you need to update `crewai`, run:
```shell
uv tool install crewai --upgrade
```
Installation successful! You're ready to create your first crew! 🎉
# Creating a CrewAI Project
We recommend using the `YAML` template scaffolding for a structured approach to defining agents and tasks. Here's how to get started:
* Run the `crewai` CLI command:
```shell
crewai create crew
```
* This creates a new project with the following structure:
```
my_project/
├── .gitignore
├── knowledge/
├── pyproject.toml
├── README.md
├── .env
└── src/
└── my_project/
├── __init__.py
├── main.py
├── crew.py
├── tools/
│ ├── custom_tool.py
│ └── __init__.py
└── config/
├── agents.yaml
└── tasks.yaml
```
* Your project will contain these essential files:
| File | Purpose |
| ------------- | ---------------------------------------- |
| `agents.yaml` | Define your AI agents and their roles |
| `tasks.yaml` | Set up agent tasks and workflows |
| `.env` | Store API keys and environment variables |
| `main.py` | Project entry point and execution flow |
| `crew.py` | Crew orchestration and coordination |
| `tools/` | Directory for custom agent tools |
| `knowledge/` | Directory for knowledge base |
* Start by editing `agents.yaml` and `tasks.yaml` to define your crew's behavior.
* Keep sensitive information like API keys in `.env`.
* Before you run your crew, make sure to run:
```bash
crewai install
```
* If you need to install additional packages, use:
```shell
uv add
```
* To run your crew, execute the following command in the root of your project:
```bash
crewai run
```
## Enterprise Installation Options
For teams and organizations, CrewAI offers enterprise deployment options that eliminate setup complexity:
### CrewAI Enterprise (SaaS)
* Zero installation required - just sign up for free at [app.crewai.com](https://app.crewai.com)
* Automatic updates and maintenance
* Managed infrastructure and scaling
* Build Crews with no Code
### CrewAI Factory (Self-hosted)
* Containerized deployment for your infrastructure
* Supports any hyperscaler including on prem depployments
* Integration with your existing security systems
Learn about CrewAI's enterprise offerings and schedule a demo
## Next Steps
Follow our quickstart guide to create your first CrewAI agent and get hands-on experience.
Connect with other developers, get help, and share your CrewAI experiences.
# Introduction
Source: https://docs.crewai.com/introduction
Build AI agent teams that work together to tackle complex tasks
# What is CrewAI?
**CrewAI is a lean, lightning-fast Python framework built entirely from scratch—completely independent of LangChain or other agent frameworks.**
CrewAI empowers developers with both high-level simplicity and precise low-level control, ideal for creating autonomous AI agents tailored to any scenario:
* **[CrewAI Crews](/guides/crews/first-crew)**: Optimize for autonomy and collaborative intelligence, enabling you to create AI teams where each agent has specific roles, tools, and goals.
* **[CrewAI Flows](/guides/flows/first-flow)**: Enable granular, event-driven control, single LLM calls for precise task orchestration and supports Crews natively.
With over 100,000 developers certified through our community courses, CrewAI is rapidly becoming the standard for enterprise-ready AI automation.
## How Crews Work
Just like a company has departments (Sales, Engineering, Marketing) working together under leadership to achieve business goals, CrewAI helps you create an organization of AI agents with specialized roles collaborating to accomplish complex tasks.
| Component | Description | Key Features |
| :------------ | :------------------------: | :-------------------------------------------------------------------------------------------------------------------------------- |
| **Crew** | The top-level organization | • Manages AI agent teams • Oversees workflows • Ensures collaboration • Delivers outcomes |
| **AI Agents** | Specialized team members | • Have specific roles (researcher, writer) • Use designated tools • Can delegate tasks • Make autonomous decisions |
| **Process** | Workflow management system | • Defines collaboration patterns • Controls task assignments • Manages interactions • Ensures efficient execution |
| **Tasks** | Individual assignments | • Have clear objectives • Use specific tools • Feed into larger process • Produce actionable results |
### How It All Works Together
1. The **Crew** organizes the overall operation
2. **AI Agents** work on their specialized tasks
3. The **Process** ensures smooth collaboration
4. **Tasks** get completed to achieve the goal
## Key Features
Create specialized agents with defined roles, expertise, and goals - from researchers to analysts to writers
Equip agents with custom tools and APIs to interact with external services and data sources
Agents work together, sharing insights and coordinating tasks to achieve complex objectives
Define sequential or parallel workflows, with agents automatically handling task dependencies
## How Flows Work
While Crews excel at autonomous collaboration, Flows provide structured automations, offering granular control over workflow execution. Flows ensure tasks are executed reliably, securely, and efficiently, handling conditional logic, loops, and dynamic state management with precision. Flows integrate seamlessly with Crews, enabling you to balance high autonomy with exacting control.
| Component | Description | Key Features |
| :--------------- | :-------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Flow** | Structured workflow orchestration | • Manages execution paths • Handles state transitions • Controls task sequencing • Ensures reliable execution |
| **Events** | Triggers for workflow actions | • Initiate specific processes • Enable dynamic responses • Support conditional branching • Allow for real-time adaptation |
| **States** | Workflow execution contexts | • Maintain execution data • Enable persistence • Support resumability • Ensure execution integrity |
| **Crew Support** | Enhances workflow automation | • Injects pockets of agency when needed • Complements structured workflows • Balances automation with intelligence • Enables adaptive decision-making |
### Key Capabilities
Define precise execution paths responding dynamically to events
Manage workflow states and conditional execution securely and efficiently
Effortlessly combine with Crews for enhanced autonomy and intelligence
Ensure predictable outcomes with explicit control flow and error handling
## When to Use Crews vs. Flows
Understanding when to use [Crews](/guides/crews/first-crew) versus [Flows](/guides/flows/first-flow) is key to maximizing the potential of CrewAI in your applications.
| Use Case | Recommended Approach | Why? |
| :---------------------- | :-------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------ |
| **Open-ended research** | [Crews](/guides/crews/first-crew) | When tasks require creative thinking, exploration, and adaptation |
| **Content generation** | [Crews](/guides/crews/first-crew) | For collaborative creation of articles, reports, or marketing materials |
| **Decision workflows** | [Flows](/guides/flows/first-flow) | When you need predictable, auditable decision paths with precise control |
| **API orchestration** | [Flows](/guides/flows/first-flow) | For reliable integration with multiple external services in a specific sequence |
| **Hybrid applications** | Combined approach | Use [Flows](/guides/flows/first-flow) to orchestrate overall process with [Crews](/guides/crews/first-crew) handling complex subtasks |
### Decision Framework
* **Choose [Crews](/guides/crews/first-crew) when:** You need autonomous problem-solving, creative collaboration, or exploratory tasks
* **Choose [Flows](/guides/flows/first-flow) when:** You require deterministic outcomes, auditability, or precise control over execution
* **Combine both when:** Your application needs both structured processes and pockets of autonomous intelligence
## Why Choose CrewAI?
* 🧠 **Autonomous Operation**: Agents make intelligent decisions based on their roles and available tools
* 📝 **Natural Interaction**: Agents communicate and collaborate like human team members
* 🛠️ **Extensible Design**: Easy to add new tools, roles, and capabilities
* 🚀 **Production Ready**: Built for reliability and scalability in real-world applications
* 🔒 **Security-Focused**: Designed with enterprise security requirements in mind
* 💰 **Cost-Efficient**: Optimized to minimize token usage and API calls
## Ready to Start Building?
Step-by-step tutorial to create a collaborative AI team that works together to solve complex problems.
Learn how to create structured, event-driven workflows with precise control over execution.
Get started with CrewAI in your development environment.
Follow our quickstart guide to create your first CrewAI agent and get hands-on experience.
Connect with other developers, get help, and share your CrewAI experiences.
# Quickstart
Source: https://docs.crewai.com/quickstart
Build your first AI agent with CrewAI in under 5 minutes.
## Build your first CrewAI Agent
Let's create a simple crew that will help us `research` and `report` on the `latest AI developments` for a given topic or subject.
Before we proceed, make sure you have finished installing CrewAI.
If you haven't installed them yet, you can do so by following the [installation guide](/installation).
Follow the steps below to get Crewing! 🚣♂️
Create a new crew project by running the following command in your terminal.
This will create a new directory called `latest-ai-development` with the basic structure for your crew.
```shell Terminal
crewai create crew latest-ai-development
```
```shell Terminal
cd latest-ai-development
```
You can also modify the agents as needed to fit your use case or copy and paste as is to your project.
Any variable interpolated in your `agents.yaml` and `tasks.yaml` files like `{topic}` will be replaced by the value of the variable in the `main.py` file.
```yaml agents.yaml
# src/latest_ai_development/config/agents.yaml
researcher:
role: >
{topic} Senior Data Researcher
goal: >
Uncover cutting-edge developments in {topic}
backstory: >
You're a seasoned researcher with a knack for uncovering the latest
developments in {topic}. Known for your ability to find the most relevant
information and present it in a clear and concise manner.
reporting_analyst:
role: >
{topic} Reporting Analyst
goal: >
Create detailed reports based on {topic} data analysis and research findings
backstory: >
You're a meticulous analyst with a keen eye for detail. You're known for
your ability to turn complex data into clear and concise reports, making
it easy for others to understand and act on the information you provide.
```
````yaml tasks.yaml
# src/latest_ai_development/config/tasks.yaml
research_task:
description: >
Conduct a thorough research about {topic}
Make sure you find any interesting and relevant information given
the current year is 2025.
expected_output: >
A list with 10 bullet points of the most relevant information about {topic}
agent: researcher
reporting_task:
description: >
Review the context you got and expand each topic into a full section for a report.
Make sure the report is detailed and contains any and all relevant information.
expected_output: >
A fully fledge reports with the mains topics, each with a full section of information.
Formatted as markdown without '```'
agent: reporting_analyst
output_file: report.md
````
```python crew.py
# src/latest_ai_development/crew.py
from crewai import Agent, Crew, Process, Task
from crewai.project import CrewBase, agent, crew, task
from crewai_tools import SerperDevTool
from crewai.agents.agent_builder.base_agent import BaseAgent
from typing import List
@CrewBase
class LatestAiDevelopmentCrew():
"""LatestAiDevelopment crew"""
agents: List[BaseAgent]
tasks: List[Task]
@agent
def researcher(self) -> Agent:
return Agent(
config=self.agents_config['researcher'], # type: ignore[index]
verbose=True,
tools=[SerperDevTool()]
)
@agent
def reporting_analyst(self) -> Agent:
return Agent(
config=self.agents_config['reporting_analyst'], # type: ignore[index]
verbose=True
)
@task
def research_task(self) -> Task:
return Task(
config=self.tasks_config['research_task'], # type: ignore[index]
)
@task
def reporting_task(self) -> Task:
return Task(
config=self.tasks_config['reporting_task'], # type: ignore[index]
output_file='output/report.md' # This is the file that will be contain the final report.
)
@crew
def crew(self) -> Crew:
"""Creates the LatestAiDevelopment crew"""
return Crew(
agents=self.agents, # Automatically created by the @agent decorator
tasks=self.tasks, # Automatically created by the @task decorator
process=Process.sequential,
verbose=True,
)
```
```python crew.py
# src/latest_ai_development/crew.py
from crewai import Agent, Crew, Process, Task
from crewai.project import CrewBase, agent, crew, task, before_kickoff, after_kickoff
from crewai_tools import SerperDevTool
@CrewBase
class LatestAiDevelopmentCrew():
"""LatestAiDevelopment crew"""
@before_kickoff
def before_kickoff_function(self, inputs):
print(f"Before kickoff function with inputs: {inputs}")
return inputs # You can return the inputs or modify them as needed
@after_kickoff
def after_kickoff_function(self, result):
print(f"After kickoff function with result: {result}")
return result # You can return the result or modify it as needed
# ... remaining code
```
For example, you can pass the `topic` input to your crew to customize the research and reporting.
```python main.py
#!/usr/bin/env python
# src/latest_ai_development/main.py
import sys
from latest_ai_development.crew import LatestAiDevelopmentCrew
def run():
"""
Run the crew.
"""
inputs = {
'topic': 'AI Agents'
}
LatestAiDevelopmentCrew().crew().kickoff(inputs=inputs)
```
Before running your crew, make sure you have the following keys set as environment variables in your `.env` file:
* An [OpenAI API key](https://platform.openai.com/account/api-keys) (or other LLM API key): `OPENAI_API_KEY=sk-...`
* A [Serper.dev](https://serper.dev/) API key: `SERPER_API_KEY=YOUR_KEY_HERE`
* Lock the dependencies and install them by using the CLI command:
```shell Terminal
crewai install
```
* If you have additional packages that you want to install, you can do so by running:
```shell Terminal
uv add
```
* To run your crew, execute the following command in the root of your project:
```bash Terminal
crewai run
```
For CrewAI Enterprise users, you can create the same crew without writing code:
1. Log in to your CrewAI Enterprise account (create a free account at [app.crewai.com](https://app.crewai.com))
2. Open Crew Studio
3. Type what is the automation you're tryign to build
4. Create your tasks visually and connect them in sequence
5. Configure your inputs and click "Download Code" or "Deploy"
Start your free account at CrewAI Enterprise
You should see the output in the console and the `report.md` file should be created in the root of your project with the final report.
Here's an example of what the report should look like:
```markdown output/report.md
# Comprehensive Report on the Rise and Impact of AI Agents in 2025
## 1. Introduction to AI Agents
In 2025, Artificial Intelligence (AI) agents are at the forefront of innovation across various industries. As intelligent systems that can perform tasks typically requiring human cognition, AI agents are paving the way for significant advancements in operational efficiency, decision-making, and overall productivity within sectors like Human Resources (HR) and Finance. This report aims to detail the rise of AI agents, their frameworks, applications, and potential implications on the workforce.
## 2. Benefits of AI Agents
AI agents bring numerous advantages that are transforming traditional work environments. Key benefits include:
- **Task Automation**: AI agents can carry out repetitive tasks such as data entry, scheduling, and payroll processing without human intervention, greatly reducing the time and resources spent on these activities.
- **Improved Efficiency**: By quickly processing large datasets and performing analyses that would take humans significantly longer, AI agents enhance operational efficiency. This allows teams to focus on strategic tasks that require higher-level thinking.
- **Enhanced Decision-Making**: AI agents can analyze trends and patterns in data, provide insights, and even suggest actions, helping stakeholders make informed decisions based on factual data rather than intuition alone.
## 3. Popular AI Agent Frameworks
Several frameworks have emerged to facilitate the development of AI agents, each with its own unique features and capabilities. Some of the most popular frameworks include:
- **Autogen**: A framework designed to streamline the development of AI agents through automation of code generation.
- **Semantic Kernel**: Focuses on natural language processing and understanding, enabling agents to comprehend user intentions better.
- **Promptflow**: Provides tools for developers to create conversational agents that can navigate complex interactions seamlessly.
- **Langchain**: Specializes in leveraging various APIs to ensure agents can access and utilize external data effectively.
- **CrewAI**: Aimed at collaborative environments, CrewAI strengthens teamwork by facilitating communication through AI-driven insights.
- **MemGPT**: Combines memory-optimized architectures with generative capabilities, allowing for more personalized interactions with users.
These frameworks empower developers to build versatile and intelligent agents that can engage users, perform advanced analytics, and execute various tasks aligned with organizational goals.
## 4. AI Agents in Human Resources
AI agents are revolutionizing HR practices by automating and optimizing key functions:
- **Recruiting**: AI agents can screen resumes, schedule interviews, and even conduct initial assessments, thus accelerating the hiring process while minimizing biases.
- **Succession Planning**: AI systems analyze employee performance data and potential, helping organizations identify future leaders and plan appropriate training.
- **Employee Engagement**: Chatbots powered by AI can facilitate feedback loops between employees and management, promoting an open culture and addressing concerns promptly.
As AI continues to evolve, HR departments leveraging these agents can realize substantial improvements in both efficiency and employee satisfaction.
## 5. AI Agents in Finance
The finance sector is seeing extensive integration of AI agents that enhance financial practices:
- **Expense Tracking**: Automated systems manage and monitor expenses, flagging anomalies and offering recommendations based on spending patterns.
- **Risk Assessment**: AI models assess credit risk and uncover potential fraud by analyzing transaction data and behavioral patterns.
- **Investment Decisions**: AI agents provide stock predictions and analytics based on historical data and current market conditions, empowering investors with informative insights.
The incorporation of AI agents into finance is fostering a more responsive and risk-aware financial landscape.
## 6. Market Trends and Investments
The growth of AI agents has attracted significant investment, especially amidst the rising popularity of chatbots and generative AI technologies. Companies and entrepreneurs are eager to explore the potential of these systems, recognizing their ability to streamline operations and improve customer engagement.
Conversely, corporations like Microsoft are taking strides to integrate AI agents into their product offerings, with enhancements to their Copilot 365 applications. This strategic move emphasizes the importance of AI literacy in the modern workplace and indicates the stabilizing of AI agents as essential business tools.
## 7. Future Predictions and Implications
Experts predict that AI agents will transform essential aspects of work life. As we look toward the future, several anticipated changes include:
- Enhanced integration of AI agents across all business functions, creating interconnected systems that leverage data from various departmental silos for comprehensive decision-making.
- Continued advancement of AI technologies, resulting in smarter, more adaptable agents capable of learning and evolving from user interactions.
- Increased regulatory scrutiny to ensure ethical use, especially concerning data privacy and employee surveillance as AI agents become more prevalent.
To stay competitive and harness the full potential of AI agents, organizations must remain vigilant about latest developments in AI technology and consider continuous learning and adaptation in their strategic planning.
## 8. Conclusion
The emergence of AI agents is undeniably reshaping the workplace landscape in 5. With their ability to automate tasks, enhance efficiency, and improve decision-making, AI agents are critical in driving operational success. Organizations must embrace and adapt to AI developments to thrive in an increasingly digital business environment.
```
Congratulations!
You have successfully set up your crew project and are ready to start building your own agentic workflows!
### Note on Consistency in Naming
The names you use in your YAML files (`agents.yaml` and `tasks.yaml`) should match the method names in your Python code.
For example, you can reference the agent for specific tasks from `tasks.yaml` file.
This naming consistency allows CrewAI to automatically link your configurations with your code; otherwise, your task won't recognize the reference properly.
#### Example References
Note how we use the same name for the agent in the `agents.yaml` (`email_summarizer`) file as the method name in the `crew.py` (`email_summarizer`) file.
```yaml agents.yaml
email_summarizer:
role: >
Email Summarizer
goal: >
Summarize emails into a concise and clear summary
backstory: >
You will create a 5 bullet point summary of the report
llm: openai/gpt-4o
```
Note how we use the same name for the task in the `tasks.yaml` (`email_summarizer_task`) file as the method name in the `crew.py` (`email_summarizer_task`) file.
```yaml tasks.yaml
email_summarizer_task:
description: >
Summarize the email into a 5 bullet point summary
expected_output: >
A 5 bullet point summary of the email
agent: email_summarizer
context:
- reporting_task
- research_task
```
## Deploying Your Project
The easiest way to deploy your crew is through [CrewAI Enterprise](http://app.crewai.com), where you can deploy your crew in a few clicks.
Get started with CrewAI Enterprise and deploy your crew in a production environment with just a few clicks.
Join our open source community to discuss ideas, share your projects, and connect with other CrewAI developers.
# Telemetry
Source: https://docs.crewai.com/telemetry
Understanding the telemetry data collected by CrewAI and how it contributes to the enhancement of the library.
## Telemetry
By default, we collect no data that would be considered personal information under GDPR and other privacy regulations.
We do collect Tool's names and Agent's roles, so be advised not to include any personal information in the tool's names or the Agent's roles.
Because no personal information is collected, it's not necessary to worry about data residency.
When `share_crew` is enabled, additional data is collected which may contain personal information if included by the user.
Users should exercise caution when enabling this feature to ensure compliance with privacy regulations.
CrewAI utilizes anonymous telemetry to gather usage statistics with the primary goal of enhancing the library.
Our focus is on improving and developing the features, integrations, and tools most utilized by our users.
It's pivotal to understand that by default, **NO personal data is collected** concerning prompts, task descriptions, agents' backstories or goals,
usage of tools, API calls, responses, any data processed by the agents, or secrets and environment variables.
When the `share_crew` feature is enabled, detailed data including task descriptions, agents' backstories or goals, and other specific attributes are collected
to provide deeper insights. This expanded data collection may include personal information if users have incorporated it into their crews or tasks.
Users should carefully consider the content of their crews and tasks before enabling `share_crew`.
Users can disable telemetry by setting the environment variable `CREWAI_DISABLE_TELEMETRY` to `true` or by setting `OTEL_SDK_DISABLED` to `true` (note that the latter disables all OpenTelemetry instrumentation globally).
### Examples:
```python
# Disable CrewAI telemetry only
os.environ['CREWAI_DISABLE_TELEMETRY'] = 'true'
# Disable all OpenTelemetry (including CrewAI)
os.environ['OTEL_SDK_DISABLED'] = 'true'
```
### Data Explanation:
| Defaulted | Data | Reason and Specifics |
| --------- | ---------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yes | CrewAI and Python Version | Tracks software versions. Example: CrewAI v1.2.3, Python 3.8.10. No personal data. |
| Yes | Crew Metadata | Includes: randomly generated key and ID, process type (e.g., 'sequential', 'parallel'), boolean flag for memory usage (true/false), count of tasks, count of agents. All non-personal. |
| Yes | Agent Data | Includes: randomly generated key and ID, role name (should not include personal info), boolean settings (verbose, delegation enabled, code execution allowed), max iterations, max RPM, max retry limit, LLM info (see LLM Attributes), list of tool names (should not include personal info). No personal data. |
| Yes | Task Metadata | Includes: randomly generated key and ID, boolean execution settings (async\_execution, human\_input), associated agent's role and key, list of tool names. All non-personal. |
| Yes | Tool Usage Statistics | Includes: tool name (should not include personal info), number of usage attempts (integer), LLM attributes used. No personal data. |
| Yes | Test Execution Data | Includes: crew's randomly generated key and ID, number of iterations, model name used, quality score (float), execution time (in seconds). All non-personal. |
| Yes | Task Lifecycle Data | Includes: creation and execution start/end times, crew and task identifiers. Stored as spans with timestamps. No personal data. |
| Yes | LLM Attributes | Includes: name, model\_name, model, top\_k, temperature, and class name of the LLM. All technical, non-personal data. |
| Yes | Crew Deployment attempt using crewAI CLI | Includes: The fact a deploy is being made and crew id, and if it's trying to pull logs, no other data. |
| No | Agent's Expanded Data | Includes: goal description, backstory text, i18n prompt file identifier. Users should ensure no personal info is included in text fields. |
| No | Detailed Task Information | Includes: task description, expected output description, context references. Users should ensure no personal info is included in these fields. |
| No | Environment Information | Includes: platform, release, system, version, and CPU count. Example: 'Windows 10', 'x86\_64'. No personal data. |
| No | Crew and Task Inputs and Outputs | Includes: input parameters and output results as non-identifiable data. Users should ensure no personal info is included. |
| No | Comprehensive Crew Execution Data | Includes: detailed logs of crew operations, all agents and tasks data, final output. All non-personal and technical in nature. |
"No" in the "Defaulted" column indicates that this data is only collected when `share_crew` is set to `true`.
### Opt-In Further Telemetry Sharing
Users can choose to share their complete telemetry data by enabling the `share_crew` attribute to `True` in their crew configurations.
Enabling `share_crew` results in the collection of detailed crew and task execution data, including `goal`, `backstory`, `context`, and `output` of tasks.
This enables a deeper insight into usage patterns.
If you enable `share_crew`, the collected data may include personal information if it has been incorporated into crew configurations, task descriptions, or outputs.
Users should carefully review their data and ensure compliance with GDPR and other applicable privacy regulations before enabling this feature.
# AI Mind Tool
Source: https://docs.crewai.com/tools/aimindtool
The `AIMindTool` is designed to query data sources in natural language.
# `AIMindTool`
## Description
The `AIMindTool` is a wrapper around [AI-Minds](https://mindsdb.com/minds) provided by [MindsDB](https://mindsdb.com/). It allows you to query data sources in natural language by simply configuring their connection parameters. This tool is useful when you need answers to questions from your data stored in various data sources including PostgreSQL, MySQL, MariaDB, ClickHouse, Snowflake, and Google BigQuery.
Minds are AI systems that work similarly to large language models (LLMs) but go beyond by answering any question from any data. This is accomplished by:
* Selecting the most relevant data for an answer using parametric search
* Understanding the meaning and providing responses within the correct context through semantic search
* Delivering precise answers by analyzing data and using machine learning (ML) models
## Installation
To incorporate this tool into your project, you need to install the Minds SDK:
```shell
uv add minds-sdk
```
## Steps to Get Started
To effectively use the `AIMindTool`, follow these steps:
1. **Package Installation**: Confirm that the `crewai[tools]` and `minds-sdk` packages are installed in your Python environment.
2. **API Key Acquisition**: Sign up for a Minds account [here](https://mdb.ai/register), and obtain an API key.
3. **Environment Configuration**: Store your obtained API key in an environment variable named `MINDS_API_KEY` to facilitate its use by the tool.
## Example
The following example demonstrates how to initialize the tool and execute a query:
```python Code
from crewai_tools import AIMindTool
# Initialize the AIMindTool
aimind_tool = AIMindTool(
datasources=[
{
"description": "house sales data",
"engine": "postgres",
"connection_data": {
"user": "demo_user",
"password": "demo_password",
"host": "samples.mindsdb.com",
"port": 5432,
"database": "demo",
"schema": "demo_data"
},
"tables": ["house_sales"]
}
]
)
# Run a natural language query
result = aimind_tool.run("How many 3 bedroom houses were sold in 2008?")
print(result)
```
## Parameters
The `AIMindTool` accepts the following parameters:
* **api\_key**: Optional. Your Minds API key. If not provided, it will be read from the `MINDS_API_KEY` environment variable.
* **datasources**: A list of dictionaries, each containing the following keys:
* **description**: A description of the data contained in the datasource.
* **engine**: The engine (or type) of the datasource.
* **connection\_data**: A dictionary containing the connection parameters for the datasource.
* **tables**: A list of tables that the data source will use. This is optional and can be omitted if all tables in the data source are to be used.
A list of supported data sources and their connection parameters can be found [here](https://docs.mdb.ai/docs/data_sources).
## Agent Integration Example
Here's how to integrate the `AIMindTool` with a CrewAI agent:
```python Code
from crewai import Agent
from crewai.project import agent
from crewai_tools import AIMindTool
# Initialize the tool
aimind_tool = AIMindTool(
datasources=[
{
"description": "sales data",
"engine": "postgres",
"connection_data": {
"user": "your_user",
"password": "your_password",
"host": "your_host",
"port": 5432,
"database": "your_db",
"schema": "your_schema"
},
"tables": ["sales"]
}
]
)
# Define an agent with the AIMindTool
@agent
def data_analyst(self) -> Agent:
return Agent(
config=self.agents_config["data_analyst"],
allow_delegation=False,
tools=[aimind_tool]
)
```
## Conclusion
The `AIMindTool` provides a powerful way to query your data sources using natural language, making it easier to extract insights without writing complex SQL queries. By connecting to various data sources and leveraging AI-Minds technology, this tool enables agents to access and analyze data efficiently.
# Apify Actors
Source: https://docs.crewai.com/tools/apifyactorstool
`ApifyActorsTool` lets you call Apify Actors to provide your CrewAI workflows with web scraping, crawling, data extraction, and web automation capabilities.
# `ApifyActorsTool`
Integrate [Apify Actors](https://apify.com/actors) into your CrewAI workflows.
## Description
The `ApifyActorsTool` connects [Apify Actors](https://apify.com/actors), cloud-based programs for web scraping and automation, to your CrewAI workflows.
Use any of the 4,000+ Actors on [Apify Store](https://apify.com/store) for use cases such as extracting data from social media, search engines, online maps, e-commerce sites, travel portals, or general websites.
For details, see the [Apify CrewAI integration](https://docs.apify.com/platform/integrations/crewai) in Apify documentation.
## Steps to get started
Install `crewai[tools]` and `langchain-apify` using pip: `pip install 'crewai[tools]' langchain-apify`.
Sign up to [Apify Console](https://console.apify.com/) and get your [Apify API token](https://console.apify.com/settings/integrations)..
Set your Apify API token as the `APIFY_API_TOKEN` environment variable to enable the tool's functionality.
## Usage example
Use the `ApifyActorsTool` manually to run the [RAG Web Browser Actor](https://apify.com/apify/rag-web-browser) to perform a web search:
```python
from crewai_tools import ApifyActorsTool
# Initialize the tool with an Apify Actor
tool = ApifyActorsTool(actor_name="apify/rag-web-browser")
# Run the tool with input parameters
results = tool.run(run_input={"query": "What is CrewAI?", "maxResults": 5})
# Process the results
for result in results:
print(f"URL: {result['metadata']['url']}")
print(f"Content: {result.get('markdown', 'N/A')[:100]}...")
```
### Expected output
Here is the output from running the code above:
```text
URL: https://www.example.com/crewai-intro
Content: CrewAI is a framework for building AI-powered workflows...
URL: https://docs.crewai.com/
Content: Official documentation for CrewAI...
```
The `ApifyActorsTool` automatically fetches the Actor definition and input schema from Apify using the provided `actor_name` and then constructs the tool description and argument schema. This means you need to specify only a valid `actor_name`, and the tool handles the rest when used with agents—no need to specify the `run_input`. Here's how it works:
```python
from crewai import Agent
from crewai_tools import ApifyActorsTool
rag_browser = ApifyActorsTool(actor_name="apify/rag-web-browser")
agent = Agent(
role="Research Analyst",
goal="Find and summarize information about specific topics",
backstory="You are an experienced researcher with attention to detail",
tools=[rag_browser],
)
```
You can run other Actors from [Apify Store](https://apify.com/store) simply by changing the `actor_name` and, when using it manually, adjusting the `run_input` based on the Actor input schema.
For an example of usage with agents, see the [CrewAI Actor template](https://apify.com/templates/python-crewai).
## Configuration
The `ApifyActorsTool` requires these inputs to work:
* **`actor_name`**
The ID of the Apify Actor to run, e.g., `"apify/rag-web-browser"`. Browse all Actors on [Apify Store](https://apify.com/store).
* **`run_input`**
A dictionary of input parameters for the Actor when running the tool manually.
* For example, for the `apify/rag-web-browser` Actor: `{"query": "search term", "maxResults": 5}`
* See the Actor's [input schema](https://apify.com/apify/rag-web-browser/input-schema) for the list of input parameters.
## Resources
* **[Apify](https://apify.com/)**: Explore the Apify platform.
* **[How to build an AI agent on Apify](https://blog.apify.com/how-to-build-an-ai-agent/)** - A complete step-by-step guide to creating, publishing, and monetizing AI agents on the Apify platform.
* **[RAG Web Browser Actor](https://apify.com/apify/rag-web-browser)**: A popular Actor for web search for LLMs.
* **[CrewAI Integration Guide](https://docs.apify.com/platform/integrations/crewai)**: Follow the official guide for integrating Apify and CrewAI.
# Bedrock Invoke Agent Tool
Source: https://docs.crewai.com/tools/bedrockinvokeagenttool
Enables CrewAI agents to invoke Amazon Bedrock Agents and leverage their capabilities within your workflows
# `BedrockInvokeAgentTool`
The `BedrockInvokeAgentTool` enables CrewAI agents to invoke Amazon Bedrock Agents and leverage their capabilities within your workflows.
## Installation
```bash
uv pip install 'crewai[tools]'
```
## Requirements
* AWS credentials configured (either through environment variables or AWS CLI)
* `boto3` and `python-dotenv` packages
* Access to Amazon Bedrock Agents
## Usage
Here's how to use the tool with a CrewAI agent:
```python {2, 4-8}
from crewai import Agent, Task, Crew
from crewai_tools.aws.bedrock.agents.invoke_agent_tool import BedrockInvokeAgentTool
# Initialize the tool
agent_tool = BedrockInvokeAgentTool(
agent_id="your-agent-id",
agent_alias_id="your-agent-alias-id"
)
# Create a CrewAI agent that uses the tool
aws_expert = Agent(
role='AWS Service Expert',
goal='Help users understand AWS services and quotas',
backstory='I am an expert in AWS services and can provide detailed information about them.',
tools=[agent_tool],
verbose=True
)
# Create a task for the agent
quota_task = Task(
description="Find out the current service quotas for EC2 in us-west-2 and explain any recent changes.",
agent=aws_expert
)
# Create a crew with the agent
crew = Crew(
agents=[aws_expert],
tasks=[quota_task],
verbose=2
)
# Run the crew
result = crew.kickoff()
print(result)
```
## Tool Arguments
| Argument | Type | Required | Default | Description |
| :------------------- | :----- | :------- | :-------- | :------------------------------------------ |
| **agent\_id** | `str` | Yes | None | The unique identifier of the Bedrock agent |
| **agent\_alias\_id** | `str` | Yes | None | The unique identifier of the agent alias |
| **session\_id** | `str` | No | timestamp | The unique identifier of the session |
| **enable\_trace** | `bool` | No | False | Whether to enable trace for debugging |
| **end\_session** | `bool` | No | False | Whether to end the session after invocation |
| **description** | `str` | No | None | Custom description for the tool |
## Environment Variables
```bash
BEDROCK_AGENT_ID=your-agent-id # Alternative to passing agent_id
BEDROCK_AGENT_ALIAS_ID=your-agent-alias-id # Alternative to passing agent_alias_id
AWS_REGION=your-aws-region # Defaults to us-west-2
AWS_ACCESS_KEY_ID=your-access-key # Required for AWS authentication
AWS_SECRET_ACCESS_KEY=your-secret-key # Required for AWS authentication
```
## Advanced Usage
### Multi-Agent Workflow with Session Management
```python {2, 4-22}
from crewai import Agent, Task, Crew, Process
from crewai_tools.aws.bedrock.agents.invoke_agent_tool import BedrockInvokeAgentTool
# Initialize tools with session management
initial_tool = BedrockInvokeAgentTool(
agent_id="your-agent-id",
agent_alias_id="your-agent-alias-id",
session_id="custom-session-id"
)
followup_tool = BedrockInvokeAgentTool(
agent_id="your-agent-id",
agent_alias_id="your-agent-alias-id",
session_id="custom-session-id"
)
final_tool = BedrockInvokeAgentTool(
agent_id="your-agent-id",
agent_alias_id="your-agent-alias-id",
session_id="custom-session-id",
end_session=True
)
# Create agents for different stages
researcher = Agent(
role='AWS Service Researcher',
goal='Gather information about AWS services',
backstory='I am specialized in finding detailed AWS service information.',
tools=[initial_tool]
)
analyst = Agent(
role='Service Compatibility Analyst',
goal='Analyze service compatibility and requirements',
backstory='I analyze AWS services for compatibility and integration possibilities.',
tools=[followup_tool]
)
summarizer = Agent(
role='Technical Documentation Writer',
goal='Create clear technical summaries',
backstory='I specialize in creating clear, concise technical documentation.',
tools=[final_tool]
)
# Create tasks
research_task = Task(
description="Find all available AWS services in us-west-2 region.",
agent=researcher
)
analysis_task = Task(
description="Analyze which services support IPv6 and their implementation requirements.",
agent=analyst
)
summary_task = Task(
description="Create a summary of IPv6-compatible services and their key features.",
agent=summarizer
)
# Create a crew with the agents and tasks
crew = Crew(
agents=[researcher, analyst, summarizer],
tasks=[research_task, analysis_task, summary_task],
process=Process.sequential,
verbose=2
)
# Run the crew
result = crew.kickoff()
```
## Use Cases
### Hybrid Multi-Agent Collaborations
* Create workflows where CrewAI agents collaborate with managed Bedrock agents running as services in AWS
* Enable scenarios where sensitive data processing happens within your AWS environment while other agents operate externally
* Bridge on-premises CrewAI agents with cloud-based Bedrock agents for distributed intelligence workflows
### Data Sovereignty and Compliance
* Keep data-sensitive agentic workflows within your AWS environment while allowing external CrewAI agents to orchestrate tasks
* Maintain compliance with data residency requirements by processing sensitive information only within your AWS account
* Enable secure multi-agent collaborations where some agents cannot access your organization's private data
### Seamless AWS Service Integration
* Access any AWS service through Amazon Bedrock Actions without writing complex integration code
* Enable CrewAI agents to interact with AWS services through natural language requests
* Leverage pre-built Bedrock agent capabilities to interact with AWS services like Bedrock Knowledge Bases, Lambda, and more
### Scalable Hybrid Agent Architectures
* Offload computationally intensive tasks to managed Bedrock agents while lightweight tasks run in CrewAI
* Scale agent processing by distributing workloads between local CrewAI agents and cloud-based Bedrock agents
### Cross-Organizational Agent Collaboration
* Enable secure collaboration between your organization's CrewAI agents and partner organizations' Bedrock agents
* Create workflows where external expertise from Bedrock agents can be incorporated without exposing sensitive data
* Build agent ecosystems that span organizational boundaries while maintaining security and data control
# Bedrock Knowledge Base Retriever
Source: https://docs.crewai.com/tools/bedrockkbretriever
Retrieve information from Amazon Bedrock Knowledge Bases using natural language queries
# `BedrockKBRetrieverTool`
The `BedrockKBRetrieverTool` enables CrewAI agents to retrieve information from Amazon Bedrock Knowledge Bases using natural language queries.
## Installation
```bash
uv pip install 'crewai[tools]'
```
## Requirements
* AWS credentials configured (either through environment variables or AWS CLI)
* `boto3` and `python-dotenv` packages
* Access to Amazon Bedrock Knowledge Base
## Usage
Here's how to use the tool with a CrewAI agent:
```python {2, 4-17}
from crewai import Agent, Task, Crew
from crewai_tools.aws.bedrock.knowledge_base.retriever_tool import BedrockKBRetrieverTool
# Initialize the tool
kb_tool = BedrockKBRetrieverTool(
knowledge_base_id="your-kb-id",
number_of_results=5
)
# Create a CrewAI agent that uses the tool
researcher = Agent(
role='Knowledge Base Researcher',
goal='Find information about company policies',
backstory='I am a researcher specialized in retrieving and analyzing company documentation.',
tools=[kb_tool],
verbose=True
)
# Create a task for the agent
research_task = Task(
description="Find our company's remote work policy and summarize the key points.",
agent=researcher
)
# Create a crew with the agent
crew = Crew(
agents=[researcher],
tasks=[research_task],
verbose=2
)
# Run the crew
result = crew.kickoff()
print(result)
```
## Tool Arguments
| Argument | Type | Required | Default | Description |
| :--------------------------- | :----- | :------- | :------ | :------------------------------------------------------------------------- |
| **knowledge\_base\_id** | `str` | Yes | None | The unique identifier of the knowledge base (0-10 alphanumeric characters) |
| **number\_of\_results** | `int` | No | 5 | Maximum number of results to return |
| **retrieval\_configuration** | `dict` | No | None | Custom configurations for the knowledge base query |
| **guardrail\_configuration** | `dict` | No | None | Content filtering settings |
| **next\_token** | `str` | No | None | Token for pagination |
## Environment Variables
```bash
BEDROCK_KB_ID=your-knowledge-base-id # Alternative to passing knowledge_base_id
AWS_REGION=your-aws-region # Defaults to us-east-1
AWS_ACCESS_KEY_ID=your-access-key # Required for AWS authentication
AWS_SECRET_ACCESS_KEY=your-secret-key # Required for AWS authentication
```
## Response Format
The tool returns results in JSON format:
```json
{
"results": [
{
"content": "Retrieved text content",
"content_type": "text",
"source_type": "S3",
"source_uri": "s3://bucket/document.pdf",
"score": 0.95,
"metadata": {
"additional": "metadata"
}
}
],
"nextToken": "pagination-token",
"guardrailAction": "NONE"
}
```
## Advanced Usage
### Custom Retrieval Configuration
```python
kb_tool = BedrockKBRetrieverTool(
knowledge_base_id="your-kb-id",
retrieval_configuration={
"vectorSearchConfiguration": {
"numberOfResults": 10,
"overrideSearchType": "HYBRID"
}
}
)
policy_expert = Agent(
role='Policy Expert',
goal='Analyze company policies in detail',
backstory='I am an expert in corporate policy analysis with deep knowledge of regulatory requirements.',
tools=[kb_tool]
)
```
## Supported Data Sources
* Amazon S3
* Confluence
* Salesforce
* SharePoint
* Web pages
* Custom document locations
* Amazon Kendra
* SQL databases
## Use Cases
### Enterprise Knowledge Integration
* Enable CrewAI agents to access your organization's proprietary knowledge without exposing sensitive data
* Allow agents to make decisions based on your company's specific policies, procedures, and documentation
* Create agents that can answer questions based on your internal documentation while maintaining data security
### Specialized Domain Knowledge
* Connect CrewAI agents to domain-specific knowledge bases (legal, medical, technical) without retraining models
* Leverage existing knowledge repositories that are already maintained in your AWS environment
* Combine CrewAI's reasoning with domain-specific information from your knowledge bases
### Data-Driven Decision Making
* Ground CrewAI agent responses in your actual company data rather than general knowledge
* Ensure agents provide recommendations based on your specific business context and documentation
* Reduce hallucinations by retrieving factual information from your knowledge bases
### Scalable Information Access
* Access terabytes of organizational knowledge without embedding it all into your models
* Dynamically query only the relevant information needed for specific tasks
* Leverage AWS's scalable infrastructure to handle large knowledge bases efficiently
### Compliance and Governance
* Ensure CrewAI agents provide responses that align with your company's approved documentation
* Create auditable trails of information sources used by your agents
* Maintain control over what information sources your agents can access
# Brave Search
Source: https://docs.crewai.com/tools/bravesearchtool
The `BraveSearchTool` is designed to search the internet using the Brave Search API.
# `BraveSearchTool`
## Description
This tool is designed to perform web searches using the Brave Search API. It allows you to search the internet with a specified query and retrieve relevant results. The tool supports customizable result counts and country-specific searches.
## Installation
To incorporate this tool into your project, follow the installation instructions below:
```shell
pip install 'crewai[tools]'
```
## Steps to Get Started
To effectively use the `BraveSearchTool`, follow these steps:
1. **Package Installation**: Confirm that the `crewai[tools]` package is installed in your Python environment.
2. **API Key Acquisition**: Acquire a Brave Search API key by registering at [Brave Search API](https://api.search.brave.com/app/keys).
3. **Environment Configuration**: Store your obtained API key in an environment variable named `BRAVE_API_KEY` to facilitate its use by the tool.
## Example
The following example demonstrates how to initialize the tool and execute a search with a given query:
```python Code
from crewai_tools import BraveSearchTool
# Initialize the tool for internet searching capabilities
tool = BraveSearchTool()
# Execute a search
results = tool.run(search_query="CrewAI agent framework")
print(results)
```
## Parameters
The `BraveSearchTool` accepts the following parameters:
* **search\_query**: Mandatory. The search query you want to use to search the internet.
* **country**: Optional. Specify the country for the search results. Default is empty string.
* **n\_results**: Optional. Number of search results to return. Default is `10`.
* **save\_file**: Optional. Whether to save the search results to a file. Default is `False`.
## Example with Parameters
Here is an example demonstrating how to use the tool with additional parameters:
```python Code
from crewai_tools import BraveSearchTool
# Initialize the tool with custom parameters
tool = BraveSearchTool(
country="US",
n_results=5,
save_file=True
)
# Execute a search
results = tool.run(search_query="Latest AI developments")
print(results)
```
## Agent Integration Example
Here's how to integrate the `BraveSearchTool` with a CrewAI agent:
```python Code
from crewai import Agent
from crewai.project import agent
from crewai_tools import BraveSearchTool
# Initialize the tool
brave_search_tool = BraveSearchTool()
# Define an agent with the BraveSearchTool
@agent
def researcher(self) -> Agent:
return Agent(
config=self.agents_config["researcher"],
allow_delegation=False,
tools=[brave_search_tool]
)
```
## Conclusion
By integrating the `BraveSearchTool` into Python projects, users gain the ability to conduct real-time, relevant searches across the internet directly from their applications. The tool provides a simple interface to the powerful Brave Search API, making it easy to retrieve and process search results programmatically. By adhering to the setup and usage guidelines provided, incorporating this tool into projects is streamlined and straightforward.
# Browserbase Web Loader
Source: https://docs.crewai.com/tools/browserbaseloadtool
Browserbase is a developer platform to reliably run, manage, and monitor headless browsers.
# `BrowserbaseLoadTool`
## Description
[Browserbase](https://browserbase.com) is a developer platform to reliably run, manage, and monitor headless browsers.
Power your AI data retrievals with:
* [Serverless Infrastructure](https://docs.browserbase.com/under-the-hood) providing reliable browsers to extract data from complex UIs
* [Stealth Mode](https://docs.browserbase.com/features/stealth-mode) with included fingerprinting tactics and automatic captcha solving
* [Session Debugger](https://docs.browserbase.com/features/sessions) to inspect your Browser Session with networks timeline and logs
* [Live Debug](https://docs.browserbase.com/guides/session-debug-connection/browser-remote-control) to quickly debug your automation
## Installation
* Get an API key and Project ID from [browserbase.com](https://browserbase.com) and set it in environment variables (`BROWSERBASE_API_KEY`, `BROWSERBASE_PROJECT_ID`).
* Install the [Browserbase SDK](http://github.com/browserbase/python-sdk) along with `crewai[tools]` package:
```shell
pip install browserbase 'crewai[tools]'
```
## Example
Utilize the BrowserbaseLoadTool as follows to allow your agent to load websites:
```python Code
from crewai_tools import BrowserbaseLoadTool
# Initialize the tool with the Browserbase API key and Project ID
tool = BrowserbaseLoadTool()
```
## Arguments
The following parameters can be used to customize the `BrowserbaseLoadTool`'s behavior:
| Argument | Type | Description |
| :---------------- | :------- | :------------------------------------------------------------------------------------ |
| **api\_key** | `string` | *Optional*. Browserbase API key. Default is `BROWSERBASE_API_KEY` env variable. |
| **project\_id** | `string` | *Optional*. Browserbase Project ID. Default is `BROWSERBASE_PROJECT_ID` env variable. |
| **text\_content** | `bool` | *Optional*. Retrieve only text content. Default is `False`. |
| **session\_id** | `string` | *Optional*. Provide an existing Session ID. |
| **proxy** | `bool` | *Optional*. Enable/Disable Proxies. Default is `False`. |
# Code Docs RAG Search
Source: https://docs.crewai.com/tools/codedocssearchtool
The `CodeDocsSearchTool` is a powerful RAG (Retrieval-Augmented Generation) tool designed for semantic searches within code documentation.
# `CodeDocsSearchTool`
**Experimental**: We are still working on improving tools, so there might be unexpected behavior or changes in the future.
## Description
The CodeDocsSearchTool is a powerful RAG (Retrieval-Augmented Generation) tool designed for semantic searches within code documentation.
It enables users to efficiently find specific information or topics within code documentation. By providing a `docs_url` during initialization,
the tool narrows down the search to that particular documentation site. Alternatively, without a specific `docs_url`,
it searches across a wide array of code documentation known or discovered throughout its execution, making it versatile for various documentation search needs.
## Installation
To start using the CodeDocsSearchTool, first, install the crewai\_tools package via pip:
```shell
pip install 'crewai[tools]'
```
## Example
Utilize the CodeDocsSearchTool as follows to conduct searches within code documentation:
```python Code
from crewai_tools import CodeDocsSearchTool
# To search any code documentation content
# if the URL is known or discovered during its execution:
tool = CodeDocsSearchTool()
# OR
# To specifically focus your search on a given documentation site
# by providing its URL:
tool = CodeDocsSearchTool(docs_url='https://docs.example.com/reference')
```
Substitute '[https://docs.example.com/reference](https://docs.example.com/reference)' with your target documentation URL
and 'How to use search tool' with the search query relevant to your needs.
## Arguments
The following parameters can be used to customize the `CodeDocsSearchTool`'s behavior:
| Argument | Type | Description |
| :------------ | :------- | :---------------------------------------------------------------------- |
| **docs\_url** | `string` | *Optional*. Specifies the URL of the code documentation to be searched. |
## Custom model and embeddings
By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
```python Code
tool = CodeDocsSearchTool(
config=dict(
llm=dict(
provider="ollama", # or google, openai, anthropic, llama2, ...
config=dict(
model="llama2",
# temperature=0.5,
# top_p=1,
# stream=true,
),
),
embedder=dict(
provider="google", # or openai, ollama, ...
config=dict(
model="models/embedding-001",
task_type="retrieval_document",
# title="Embeddings",
),
),
)
)
```
# Code Interpreter
Source: https://docs.crewai.com/tools/codeinterpretertool
The `CodeInterpreterTool` is a powerful tool designed for executing Python 3 code within a secure, isolated environment.
# `CodeInterpreterTool`
## Description
The `CodeInterpreterTool` enables CrewAI agents to execute Python 3 code that they generate autonomously. The code is run in a secure, isolated Docker container, ensuring safety regardless of the content. This functionality is particularly valuable as it allows agents to create code, execute it, obtain the results, and utilize that information to inform subsequent decisions and actions.
## Requirements
* Docker must be installed and running on your system. If you don't have it, you can install it from [here](https://docs.docker.com/get-docker/).
## Installation
To use this tool, you need to install the CrewAI tools package:
```shell
pip install 'crewai[tools]'
```
## Example
The following example demonstrates how to use the `CodeInterpreterTool` with a CrewAI agent:
```python Code
from crewai import Agent, Task, Crew, Process
from crewai_tools import CodeInterpreterTool
# Initialize the tool
code_interpreter = CodeInterpreterTool()
# Define an agent that uses the tool
programmer_agent = Agent(
role="Python Programmer",
goal="Write and execute Python code to solve problems",
backstory="An expert Python programmer who can write efficient code to solve complex problems.",
tools=[code_interpreter],
verbose=True,
)
# Example task to generate and execute code
coding_task = Task(
description="Write a Python function to calculate the Fibonacci sequence up to the 10th number and print the result.",
expected_output="The Fibonacci sequence up to the 10th number.",
agent=programmer_agent,
)
# Create and run the crew
crew = Crew(
agents=[programmer_agent],
tasks=[coding_task],
verbose=True,
process=Process.sequential,
)
result = crew.kickoff()
```
You can also enable code execution directly when creating an agent:
```python Code
from crewai import Agent
# Create an agent with code execution enabled
programmer_agent = Agent(
role="Python Programmer",
goal="Write and execute Python code to solve problems",
backstory="An expert Python programmer who can write efficient code to solve complex problems.",
allow_code_execution=True, # This automatically adds the CodeInterpreterTool
verbose=True,
)
```
## Parameters
The `CodeInterpreterTool` accepts the following parameters during initialization:
* **user\_dockerfile\_path**: Optional. Path to a custom Dockerfile to use for the code interpreter container.
* **user\_docker\_base\_url**: Optional. URL to the Docker daemon to use for running the container.
* **unsafe\_mode**: Optional. Whether to run code directly on the host machine instead of in a Docker container. Default is `False`. Use with caution!
When using the tool with an agent, the agent will need to provide:
* **code**: Required. The Python 3 code to execute.
* **libraries\_used**: Required. A list of libraries used in the code that need to be installed.
## Agent Integration Example
Here's a more detailed example of how to integrate the `CodeInterpreterTool` with a CrewAI agent:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools import CodeInterpreterTool
# Initialize the tool
code_interpreter = CodeInterpreterTool()
# Define an agent that uses the tool
data_analyst = Agent(
role="Data Analyst",
goal="Analyze data using Python code",
backstory="""You are an expert data analyst who specializes in using Python
to analyze and visualize data. You can write efficient code to process
large datasets and extract meaningful insights.""",
tools=[code_interpreter],
verbose=True,
)
# Create a task for the agent
analysis_task = Task(
description="""
Write Python code to:
1. Generate a random dataset of 100 points with x and y coordinates
2. Calculate the correlation coefficient between x and y
3. Create a scatter plot of the data
4. Print the correlation coefficient and save the plot as 'scatter.png'
Make sure to handle any necessary imports and print the results.
""",
expected_output="The correlation coefficient and confirmation that the scatter plot has been saved.",
agent=data_analyst,
)
# Run the task
crew = Crew(
agents=[data_analyst],
tasks=[analysis_task],
verbose=True,
process=Process.sequential,
)
result = crew.kickoff()
```
## Implementation Details
The `CodeInterpreterTool` uses Docker to create a secure environment for code execution:
```python Code
class CodeInterpreterTool(BaseTool):
name: str = "Code Interpreter"
description: str = "Interprets Python3 code strings with a final print statement."
args_schema: Type[BaseModel] = CodeInterpreterSchema
default_image_tag: str = "code-interpreter:latest"
def _run(self, **kwargs) -> str:
code = kwargs.get("code", self.code)
libraries_used = kwargs.get("libraries_used", [])
if self.unsafe_mode:
return self.run_code_unsafe(code, libraries_used)
else:
return self.run_code_in_docker(code, libraries_used)
```
The tool performs the following steps:
1. Verifies that the Docker image exists or builds it if necessary
2. Creates a Docker container with the current working directory mounted
3. Installs any required libraries specified by the agent
4. Executes the Python code in the container
5. Returns the output of the code execution
6. Cleans up by stopping and removing the container
## Security Considerations
By default, the `CodeInterpreterTool` runs code in an isolated Docker container, which provides a layer of security. However, there are still some security considerations to keep in mind:
1. The Docker container has access to the current working directory, so sensitive files could potentially be accessed.
2. The `unsafe_mode` parameter allows code to be executed directly on the host machine, which should only be used in trusted environments.
3. Be cautious when allowing agents to install arbitrary libraries, as they could potentially include malicious code.
## Conclusion
The `CodeInterpreterTool` provides a powerful way for CrewAI agents to execute Python code in a relatively secure environment. By enabling agents to write and run code, it significantly expands their problem-solving capabilities, especially for tasks involving data analysis, calculations, or other computational work. This tool is particularly useful for agents that need to perform complex operations that are more efficiently expressed in code than in natural language.
# Composio Tool
Source: https://docs.crewai.com/tools/composiotool
Composio provides 250+ production-ready tools for AI agents with flexible authentication management.
# `ComposioToolSet`
## Description
Composio is an integration platform that allows you to connect your AI agents to 250+ tools. Key features include:
* **Enterprise-Grade Authentication**: Built-in support for OAuth, API Keys, JWT with automatic token refresh
* **Full Observability**: Detailed tool usage logs, execution timestamps, and more
## Installation
To incorporate Composio tools into your project, follow the instructions below:
```shell
pip install composio-crewai
pip install crewai
```
After the installation is complete, either run `composio login` or export your composio API key as `COMPOSIO_API_KEY`. Get your Composio API key from [here](https://app.composio.dev)
## Example
The following example demonstrates how to initialize the tool and execute a github action:
1. Initialize Composio toolset
```python Code
from composio_crewai import ComposioToolSet, App, Action
from crewai import Agent, Task, Crew
toolset = ComposioToolSet()
```
2. Connect your GitHub account
```shell CLI
composio add github
```
```python Code
request = toolset.initiate_connection(app=App.GITHUB)
print(f"Open this URL to authenticate: {request.redirectUrl}")
```
3. Get Tools
* Retrieving all the tools from an app (not recommended for production):
```python Code
tools = toolset.get_tools(apps=[App.GITHUB])
```
* Filtering tools based on tags:
```python Code
tag = "users"
filtered_action_enums = toolset.find_actions_by_tags(
App.GITHUB,
tags=[tag],
)
tools = toolset.get_tools(actions=filtered_action_enums)
```
* Filtering tools based on use case:
```python Code
use_case = "Star a repository on GitHub"
filtered_action_enums = toolset.find_actions_by_use_case(
App.GITHUB, use_case=use_case, advanced=False
)
tools = toolset.get_tools(actions=filtered_action_enums)
```
Set `advanced` to True to get actions for complex use cases
* Using specific tools:
In this demo, we will use the `GITHUB_STAR_A_REPOSITORY_FOR_THE_AUTHENTICATED_USER` action from the GitHub app.
```python Code
tools = toolset.get_tools(
actions=[Action.GITHUB_STAR_A_REPOSITORY_FOR_THE_AUTHENTICATED_USER]
)
```
Learn more about filtering actions [here](https://docs.composio.dev/patterns/tools/use-tools/use-specific-actions)
4. Define agent
```python Code
crewai_agent = Agent(
role="GitHub Agent",
goal="You take action on GitHub using GitHub APIs",
backstory="You are AI agent that is responsible for taking actions on GitHub on behalf of users using GitHub APIs",
verbose=True,
tools=tools,
llm= # pass an llm
)
```
5. Execute task
```python Code
task = Task(
description="Star a repo composiohq/composio on GitHub",
agent=crewai_agent,
expected_output="Status of the operation",
)
crew = Crew(agents=[crewai_agent], tasks=[task])
crew.kickoff()
```
* More detailed list of tools can be found [here](https://app.composio.dev)
# CSV RAG Search
Source: https://docs.crewai.com/tools/csvsearchtool
The `CSVSearchTool` is a powerful RAG (Retrieval-Augmented Generation) tool designed for semantic searches within a CSV file's content.
# `CSVSearchTool`
**Experimental**: We are still working on improving tools, so there might be unexpected behavior or changes in the future.
## Description
This tool is used to perform a RAG (Retrieval-Augmented Generation) search within a CSV file's content. It allows users to semantically search for queries in the content of a specified CSV file.
This feature is particularly useful for extracting information from large CSV datasets where traditional search methods might be inefficient. All tools with "Search" in their name, including CSVSearchTool,
are RAG tools designed for searching different sources of data.
## Installation
Install the crewai\_tools package
```shell
pip install 'crewai[tools]'
```
## Example
```python Code
from crewai_tools import CSVSearchTool
# Initialize the tool with a specific CSV file.
# This setup allows the agent to only search the given CSV file.
tool = CSVSearchTool(csv='path/to/your/csvfile.csv')
# OR
# Initialize the tool without a specific CSV file.
# Agent will need to provide the CSV path at runtime.
tool = CSVSearchTool()
```
## Arguments
The following parameters can be used to customize the `CSVSearchTool`'s behavior:
| Argument | Type | Description |
| :------- | :------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **csv** | `string` | *Optional*. The path to the CSV file you want to search. This is a mandatory argument if the tool was initialized without a specific CSV file; otherwise, it is optional. |
## Custom model and embeddings
By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
```python Code
tool = CSVSearchTool(
config=dict(
llm=dict(
provider="ollama", # or google, openai, anthropic, llama2, ...
config=dict(
model="llama2",
# temperature=0.5,
# top_p=1,
# stream=true,
),
),
embedder=dict(
provider="google", # or openai, ollama, ...
config=dict(
model="models/embedding-001",
task_type="retrieval_document",
# title="Embeddings",
),
),
)
)
```
# DALL-E Tool
Source: https://docs.crewai.com/tools/dalletool
The `DallETool` is a powerful tool designed for generating images from textual descriptions.
# `DallETool`
## Description
This tool is used to give the Agent the ability to generate images using the DALL-E model. It is a transformer-based model that generates images from textual descriptions.
This tool allows the Agent to generate images based on the text input provided by the user.
## Installation
Install the crewai\_tools package
```shell
pip install 'crewai[tools]'
```
## Example
Remember that when using this tool, the text must be generated by the Agent itself. The text must be a description of the image you want to generate.
```python Code
from crewai_tools import DallETool
Agent(
...
tools=[DallETool()],
)
```
If needed you can also tweak the parameters of the DALL-E model by passing them as arguments to the `DallETool` class. For example:
```python Code
from crewai_tools import DallETool
dalle_tool = DallETool(model="dall-e-3",
size="1024x1024",
quality="standard",
n=1)
Agent(
...
tools=[dalle_tool]
)
```
The parameters are based on the `client.images.generate` method from the OpenAI API. For more information on the parameters,
please refer to the [OpenAI API documentation](https://platform.openai.com/docs/guides/images/introduction?lang=python).
# Directory Read
Source: https://docs.crewai.com/tools/directoryreadtool
The `DirectoryReadTool` is a powerful utility designed to provide a comprehensive listing of directory contents.
# `DirectoryReadTool`
We are still working on improving tools, so there might be unexpected behavior or changes in the future.
## Description
The DirectoryReadTool is a powerful utility designed to provide a comprehensive listing of directory contents.
It can recursively navigate through the specified directory, offering users a detailed enumeration of all files, including those within subdirectories.
This tool is crucial for tasks that require a thorough inventory of directory structures or for validating the organization of files within directories.
## Installation
To utilize the DirectoryReadTool in your project, install the `crewai_tools` package. If this package is not yet part of your environment, you can install it using pip with the command below:
```shell
pip install 'crewai[tools]'
```
This command installs the latest version of the `crewai_tools` package, granting access to the DirectoryReadTool among other utilities.
## Example
Employing the DirectoryReadTool is straightforward. The following code snippet demonstrates how to set it up and use the tool to list the contents of a specified directory:
```python Code
from crewai_tools import DirectoryReadTool
# Initialize the tool so the agent can read any directory's content
# it learns about during execution
tool = DirectoryReadTool()
# OR
# Initialize the tool with a specific directory,
# so the agent can only read the content of the specified directory
tool = DirectoryReadTool(directory='/path/to/your/directory')
```
## Arguments
The following parameters can be used to customize the `DirectoryReadTool`'s behavior:
| Argument | Type | Description |
| :------------ | :------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **directory** | `string` | *Optional*. An argument that specifies the path to the directory whose contents you wish to list. It accepts both absolute and relative paths, guiding the tool to the desired directory for content listing. |
# Directory RAG Search
Source: https://docs.crewai.com/tools/directorysearchtool
The `DirectorySearchTool` is a powerful RAG (Retrieval-Augmented Generation) tool designed for semantic searches within a directory's content.
# `DirectorySearchTool`
**Experimental**: The DirectorySearchTool is under continuous development. Features and functionalities might evolve, and unexpected behavior may occur as we refine the tool.
## Description
The DirectorySearchTool enables semantic search within the content of specified directories, leveraging the Retrieval-Augmented Generation (RAG) methodology for efficient navigation through files. Designed for flexibility, it allows users to dynamically specify search directories at runtime or set a fixed directory during initial setup.
## Installation
To use the DirectorySearchTool, begin by installing the crewai\_tools package. Execute the following command in your terminal:
```shell
pip install 'crewai[tools]'
```
## Initialization and Usage
Import the DirectorySearchTool from the `crewai_tools` package to start. You can initialize the tool without specifying a directory, enabling the setting of the search directory at runtime. Alternatively, the tool can be initialized with a predefined directory.
```python Code
from crewai_tools import DirectorySearchTool
# For dynamic directory specification at runtime
tool = DirectorySearchTool()
# For fixed directory searches
tool = DirectorySearchTool(directory='/path/to/directory')
```
## Arguments
* `directory`: A string argument that specifies the search directory. This is optional during initialization but required for searches if not set initially.
## Custom Model and Embeddings
The DirectorySearchTool uses OpenAI for embeddings and summarization by default. Customization options for these settings include changing the model provider and configuration, enhancing flexibility for advanced users.
```python Code
tool = DirectorySearchTool(
config=dict(
llm=dict(
provider="ollama", # Options include ollama, google, anthropic, llama2, and more
config=dict(
model="llama2",
# Additional configurations here
),
),
embedder=dict(
provider="google", # or openai, ollama, ...
config=dict(
model="models/embedding-001",
task_type="retrieval_document",
# title="Embeddings",
),
),
)
)
```
# DOCX RAG Search
Source: https://docs.crewai.com/tools/docxsearchtool
The `DOCXSearchTool` is a RAG tool designed for semantic searching within DOCX documents.
# `DOCXSearchTool`
We are still working on improving tools, so there might be unexpected behavior or changes in the future.
## Description
The `DOCXSearchTool` is a RAG tool designed for semantic searching within DOCX documents.
It enables users to effectively search and extract relevant information from DOCX files using query-based searches.
This tool is invaluable for data analysis, information management, and research tasks,
streamlining the process of finding specific information within large document collections.
## Installation
Install the crewai\_tools package by running the following command in your terminal:
```shell
pip install 'crewai[tools]'
```
## Example
The following example demonstrates initializing the DOCXSearchTool to search within any DOCX file's content or with a specific DOCX file path.
```python Code
from crewai_tools import DOCXSearchTool
# Initialize the tool to search within any DOCX file's content
tool = DOCXSearchTool()
# OR
# Initialize the tool with a specific DOCX file,
# so the agent can only search the content of the specified DOCX file
tool = DOCXSearchTool(docx='path/to/your/document.docx')
```
## Arguments
The following parameters can be used to customize the `DOCXSearchTool`'s behavior:
| Argument | Type | Description |
| :------- | :------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **docx** | `string` | *Optional*. An argument that specifies the path to the DOCX file you want to search. If not provided during initialization, the tool allows for later specification of any DOCX file's content path for searching. |
## Custom model and embeddings
By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
```python Code
tool = DOCXSearchTool(
config=dict(
llm=dict(
provider="ollama", # or google, openai, anthropic, llama2, ...
config=dict(
model="llama2",
# temperature=0.5,
# top_p=1,
# stream=true,
),
),
embedder=dict(
provider="google", # or openai, ollama, ...
config=dict(
model="models/embedding-001",
task_type="retrieval_document",
# title="Embeddings",
),
),
)
)
```
# EXA Search Web Loader
Source: https://docs.crewai.com/tools/exasearchtool
The `EXASearchTool` is designed to perform a semantic search for a specified query from a text's content across the internet.
# `EXASearchTool`
## Description
The EXASearchTool is designed to perform a semantic search for a specified query from a text's content across the internet.
It utilizes the [exa.ai](https://exa.ai/) API to fetch and display the most relevant search results based on the query provided by the user.
## Installation
To incorporate this tool into your project, follow the installation instructions below:
```shell
pip install 'crewai[tools]'
```
## Example
The following example demonstrates how to initialize the tool and execute a search with a given query:
```python Code
from crewai_tools import EXASearchTool
# Initialize the tool for internet searching capabilities
tool = EXASearchTool()
```
## Steps to Get Started
To effectively use the EXASearchTool, follow these steps:
Confirm that the `crewai[tools]` package is installed in your Python environment.
Acquire a [exa.ai](https://exa.ai/) API key by registering for a free account at [exa.ai](https://exa.ai/).
Store your obtained API key in an environment variable named `EXA_API_KEY` to facilitate its use by the tool.
## Conclusion
By integrating the `EXASearchTool` into Python projects, users gain the ability to conduct real-time, relevant searches across the internet directly from their applications.
By adhering to the setup and usage guidelines provided, incorporating this tool into projects is streamlined and straightforward.
# File Read
Source: https://docs.crewai.com/tools/filereadtool
The `FileReadTool` is designed to read files from the local file system.
# `FileReadTool`
We are still working on improving tools, so there might be unexpected behavior or changes in the future.
## Description
The FileReadTool conceptually represents a suite of functionalities within the crewai\_tools package aimed at facilitating file reading and content retrieval.
This suite includes tools for processing batch text files, reading runtime configuration files, and importing data for analytics.
It supports a variety of text-based file formats such as `.txt`, `.csv`, `.json`, and more. Depending on the file type, the suite offers specialized functionality,
such as converting JSON content into a Python dictionary for ease of use.
## Installation
To utilize the functionalities previously attributed to the FileReadTool, install the crewai\_tools package:
```shell
pip install 'crewai[tools]'
```
## Usage Example
To get started with the FileReadTool:
```python Code
from crewai_tools import FileReadTool
# Initialize the tool to read any files the agents knows or lean the path for
file_read_tool = FileReadTool()
# OR
# Initialize the tool with a specific file path, so the agent can only read the content of the specified file
file_read_tool = FileReadTool(file_path='path/to/your/file.txt')
```
## Arguments
* `file_path`: The path to the file you want to read. It accepts both absolute and relative paths. Ensure the file exists and you have the necessary permissions to access it.
# File Write
Source: https://docs.crewai.com/tools/filewritetool
The `FileWriterTool` is designed to write content to files.
# `FileWriterTool`
## Description
The `FileWriterTool` is a component of the crewai\_tools package, designed to simplify the process of writing content to files with cross-platform compatibility (Windows, Linux, macOS).
It is particularly useful in scenarios such as generating reports, saving logs, creating configuration files, and more.
This tool handles path differences across operating systems, supports UTF-8 encoding, and automatically creates directories if they don't exist, making it easier to organize your output reliably across different platforms.
## Installation
Install the crewai\_tools package to use the `FileWriterTool` in your projects:
```shell
pip install 'crewai[tools]'
```
## Example
To get started with the `FileWriterTool`:
```python Code
from crewai_tools import FileWriterTool
# Initialize the tool
file_writer_tool = FileWriterTool()
# Write content to a file in a specified directory
result = file_writer_tool._run('example.txt', 'This is a test content.', 'test_directory')
print(result)
```
## Arguments
* `filename`: The name of the file you want to create or overwrite.
* `content`: The content to write into the file.
* `directory` (optional): The path to the directory where the file will be created. Defaults to the current directory (`.`). If the directory does not exist, it will be created.
## Conclusion
By integrating the `FileWriterTool` into your crews, the agents can reliably write content to files across different operating systems.
This tool is essential for tasks that require saving output data, creating structured file systems, and handling cross-platform file operations.
It's particularly recommended for Windows users who may encounter file writing issues with standard Python file operations.
By adhering to the setup and usage guidelines provided, incorporating this tool into projects is straightforward and ensures consistent file writing behavior across all platforms.
# Firecrawl Crawl Website
Source: https://docs.crewai.com/tools/firecrawlcrawlwebsitetool
The `FirecrawlCrawlWebsiteTool` is designed to crawl and convert websites into clean markdown or structured data.
# `FirecrawlCrawlWebsiteTool`
## Description
[Firecrawl](https://firecrawl.dev) is a platform for crawling and convert any website into clean markdown or structured data.
## Installation
* Get an API key from [firecrawl.dev](https://firecrawl.dev) and set it in environment variables (`FIRECRAWL_API_KEY`).
* Install the [Firecrawl SDK](https://github.com/mendableai/firecrawl) along with `crewai[tools]` package:
```shell
pip install firecrawl-py 'crewai[tools]'
```
## Example
Utilize the FirecrawlScrapeFromWebsiteTool as follows to allow your agent to load websites:
```python Code
from crewai_tools import FirecrawlCrawlWebsiteTool
tool = FirecrawlCrawlWebsiteTool(url='firecrawl.dev')
```
## Arguments
* `api_key`: Optional. Specifies Firecrawl API key. Defaults is the `FIRECRAWL_API_KEY` environment variable.
* `url`: The base URL to start crawling from.
* `page_options`: Optional.
* `onlyMainContent`: Optional. Only return the main content of the page excluding headers, navs, footers, etc.
* `includeHtml`: Optional. Include the raw HTML content of the page. Will output a html key in the response.
* `crawler_options`: Optional. Options for controlling the crawling behavior.
* `includes`: Optional. URL patterns to include in the crawl.
* `exclude`: Optional. URL patterns to exclude from the crawl.
* `generateImgAltText`: Optional. Generate alt text for images using LLMs (requires a paid plan).
* `returnOnlyUrls`: Optional. If true, returns only the URLs as a list in the crawl status. Note: the response will be a list of URLs inside the data, not a list of documents.
* `maxDepth`: Optional. Maximum depth to crawl. Depth 1 is the base URL, depth 2 includes the base URL and its direct children, and so on.
* `mode`: Optional. The crawling mode to use. Fast mode crawls 4x faster on websites without a sitemap but may not be as accurate and shouldn't be used on heavily JavaScript-rendered websites.
* `limit`: Optional. Maximum number of pages to crawl.
* `timeout`: Optional. Timeout in milliseconds for the crawling operation.
# Firecrawl Scrape Website
Source: https://docs.crewai.com/tools/firecrawlscrapewebsitetool
The `FirecrawlScrapeWebsiteTool` is designed to scrape websites and convert them into clean markdown or structured data.
# `FirecrawlScrapeWebsiteTool`
## Description
[Firecrawl](https://firecrawl.dev) is a platform for crawling and convert any website into clean markdown or structured data.
## Installation
* Get an API key from [firecrawl.dev](https://firecrawl.dev) and set it in environment variables (`FIRECRAWL_API_KEY`).
* Install the [Firecrawl SDK](https://github.com/mendableai/firecrawl) along with `crewai[tools]` package:
```shell
pip install firecrawl-py 'crewai[tools]'
```
## Example
Utilize the FirecrawlScrapeWebsiteTool as follows to allow your agent to load websites:
```python Code
from crewai_tools import FirecrawlScrapeWebsiteTool
tool = FirecrawlScrapeWebsiteTool(url='firecrawl.dev')
```
## Arguments
* `api_key`: Optional. Specifies Firecrawl API key. Defaults is the `FIRECRAWL_API_KEY` environment variable.
* `url`: The URL to scrape.
* `page_options`: Optional.
* `onlyMainContent`: Optional. Only return the main content of the page excluding headers, navs, footers, etc.
* `includeHtml`: Optional. Include the raw HTML content of the page. Will output a html key in the response.
* `extractor_options`: Optional. Options for LLM-based extraction of structured information from the page content
* `mode`: The extraction mode to use, currently supports 'llm-extraction'
* `extractionPrompt`: Optional. A prompt describing what information to extract from the page
* `extractionSchema`: Optional. The schema for the data to be extracted
* `timeout`: Optional. Timeout in milliseconds for the request
# Firecrawl Search
Source: https://docs.crewai.com/tools/firecrawlsearchtool
The `FirecrawlSearchTool` is designed to search websites and convert them into clean markdown or structured data.
# `FirecrawlSearchTool`
## Description
[Firecrawl](https://firecrawl.dev) is a platform for crawling and convert any website into clean markdown or structured data.
## Installation
* Get an API key from [firecrawl.dev](https://firecrawl.dev) and set it in environment variables (`FIRECRAWL_API_KEY`).
* Install the [Firecrawl SDK](https://github.com/mendableai/firecrawl) along with `crewai[tools]` package:
```shell
pip install firecrawl-py 'crewai[tools]'
```
## Example
Utilize the FirecrawlSearchTool as follows to allow your agent to load websites:
```python Code
from crewai_tools import FirecrawlSearchTool
tool = FirecrawlSearchTool(query='what is firecrawl?')
```
## Arguments
* `api_key`: Optional. Specifies Firecrawl API key. Defaults is the `FIRECRAWL_API_KEY` environment variable.
* `query`: The search query string to be used for searching.
* `page_options`: Optional. Options for result formatting.
* `onlyMainContent`: Optional. Only return the main content of the page excluding headers, navs, footers, etc.
* `includeHtml`: Optional. Include the raw HTML content of the page. Will output a html key in the response.
* `fetchPageContent`: Optional. Fetch the full content of the page.
* `search_options`: Optional. Options for controlling the crawling behavior.
* `limit`: Optional. Maximum number of pages to crawl.
# Github Search
Source: https://docs.crewai.com/tools/githubsearchtool
The `GithubSearchTool` is designed to search websites and convert them into clean markdown or structured data.
# `GithubSearchTool`
We are still working on improving tools, so there might be unexpected behavior or changes in the future.
## Description
The GithubSearchTool is a Retrieval-Augmented Generation (RAG) tool specifically designed for conducting semantic searches within GitHub repositories. Utilizing advanced semantic search capabilities, it sifts through code, pull requests, issues, and repositories, making it an essential tool for developers, researchers, or anyone in need of precise information from GitHub.
## Installation
To use the GithubSearchTool, first ensure the crewai\_tools package is installed in your Python environment:
```shell
pip install 'crewai[tools]'
```
This command installs the necessary package to run the GithubSearchTool along with any other tools included in the crewai\_tools package.
## Example
Here’s how you can use the GithubSearchTool to perform semantic searches within a GitHub repository:
```python Code
from crewai_tools import GithubSearchTool
# Initialize the tool for semantic searches within a specific GitHub repository
tool = GithubSearchTool(
github_repo='https://github.com/example/repo',
gh_token='your_github_personal_access_token',
content_types=['code', 'issue'] # Options: code, repo, pr, issue
)
# OR
# Initialize the tool for semantic searches within a specific GitHub repository, so the agent can search any repository if it learns about during its execution
tool = GithubSearchTool(
gh_token='your_github_personal_access_token',
content_types=['code', 'issue'] # Options: code, repo, pr, issue
)
```
## Arguments
* `github_repo` : The URL of the GitHub repository where the search will be conducted. This is a mandatory field and specifies the target repository for your search.
* `gh_token` : Your GitHub Personal Access Token (PAT) required for authentication. You can create one in your GitHub account settings under Developer Settings > Personal Access Tokens.
* `content_types` : Specifies the types of content to include in your search. You must provide a list of content types from the following options: `code` for searching within the code,
`repo` for searching within the repository's general information, `pr` for searching within pull requests, and `issue` for searching within issues.
This field is mandatory and allows tailoring the search to specific content types within the GitHub repository.
## Custom model and embeddings
By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
```python Code
tool = GithubSearchTool(
config=dict(
llm=dict(
provider="ollama", # or google, openai, anthropic, llama2, ...
config=dict(
model="llama2",
# temperature=0.5,
# top_p=1,
# stream=true,
),
),
embedder=dict(
provider="google", # or openai, ollama, ...
config=dict(
model="models/embedding-001",
task_type="retrieval_document",
# title="Embeddings",
),
),
)
)
```
# Hyperbrowser Load Tool
Source: https://docs.crewai.com/tools/hyperbrowserloadtool
The `HyperbrowserLoadTool` enables web scraping and crawling using Hyperbrowser.
# `HyperbrowserLoadTool`
## Description
The `HyperbrowserLoadTool` enables web scraping and crawling using [Hyperbrowser](https://hyperbrowser.ai), a platform for running and scaling headless browsers. This tool allows you to scrape a single page or crawl an entire site, returning the content in properly formatted markdown or HTML.
Key Features:
* Instant Scalability - Spin up hundreds of browser sessions in seconds without infrastructure headaches
* Simple Integration - Works seamlessly with popular tools like Puppeteer and Playwright
* Powerful APIs - Easy to use APIs for scraping/crawling any site
* Bypass Anti-Bot Measures - Built-in stealth mode, ad blocking, automatic CAPTCHA solving, and rotating proxies
## Installation
To use this tool, you need to install the Hyperbrowser SDK:
```shell
uv add hyperbrowser
```
## Steps to Get Started
To effectively use the `HyperbrowserLoadTool`, follow these steps:
1. **Sign Up**: Head to [Hyperbrowser](https://app.hyperbrowser.ai/) to sign up and generate an API key.
2. **API Key**: Set the `HYPERBROWSER_API_KEY` environment variable or pass it directly to the tool constructor.
3. **Install SDK**: Install the Hyperbrowser SDK using the command above.
## Example
The following example demonstrates how to initialize the tool and use it to scrape a website:
```python Code
from crewai_tools import HyperbrowserLoadTool
from crewai import Agent
# Initialize the tool with your API key
tool = HyperbrowserLoadTool(api_key="your_api_key") # Or use environment variable
# Define an agent that uses the tool
@agent
def web_researcher(self) -> Agent:
'''
This agent uses the HyperbrowserLoadTool to scrape websites
and extract information.
'''
return Agent(
config=self.agents_config["web_researcher"],
tools=[tool]
)
```
## Parameters
The `HyperbrowserLoadTool` accepts the following parameters:
### Constructor Parameters
* **api\_key**: Optional. Your Hyperbrowser API key. If not provided, it will be read from the `HYPERBROWSER_API_KEY` environment variable.
### Run Parameters
* **url**: Required. The website URL to scrape or crawl.
* **operation**: Optional. The operation to perform on the website. Either 'scrape' or 'crawl'. Default is 'scrape'.
* **params**: Optional. Additional parameters for the scrape or crawl operation.
## Supported Parameters
For detailed information on all supported parameters, visit:
* [Scrape Parameters](https://docs.hyperbrowser.ai/reference/sdks/python/scrape#start-scrape-job-and-wait)
* [Crawl Parameters](https://docs.hyperbrowser.ai/reference/sdks/python/crawl#start-crawl-job-and-wait)
## Return Format
The tool returns content in the following format:
* For **scrape** operations: The content of the page in markdown or HTML format.
* For **crawl** operations: The content of each page separated by dividers, including the URL of each page.
## Conclusion
The `HyperbrowserLoadTool` provides a powerful way to scrape and crawl websites, handling complex scenarios like anti-bot measures, CAPTCHAs, and more. By leveraging Hyperbrowser's platform, this tool enables agents to access and extract web content efficiently.
# JSON RAG Search
Source: https://docs.crewai.com/tools/jsonsearchtool
The `JSONSearchTool` is designed to search JSON files and return the most relevant results.
# `JSONSearchTool`
The JSONSearchTool is currently in an experimental phase. This means the tool
is under active development, and users might encounter unexpected behavior or
changes. We highly encourage feedback on any issues or suggestions for
improvements.
## Description
The JSONSearchTool is designed to facilitate efficient and precise searches within JSON file contents. It utilizes a RAG (Retrieve and Generate) search mechanism, allowing users to specify a JSON path for targeted searches within a particular JSON file. This capability significantly improves the accuracy and relevance of search results.
## Installation
To install the JSONSearchTool, use the following pip command:
```shell
pip install 'crewai[tools]'
```
## Usage Examples
Here are updated examples on how to utilize the JSONSearchTool effectively for searching within JSON files. These examples take into account the current implementation and usage patterns identified in the codebase.
```python Code
from crewai_tools import JSONSearchTool
# General JSON content search
# This approach is suitable when the JSON path is either known beforehand or can be dynamically identified.
tool = JSONSearchTool()
# Restricting search to a specific JSON file
# Use this initialization method when you want to limit the search scope to a specific JSON file.
tool = JSONSearchTool(json_path='./path/to/your/file.json')
```
## Arguments
* `json_path` (str, optional): Specifies the path to the JSON file to be searched. This argument is not required if the tool is initialized for a general search. When provided, it confines the search to the specified JSON file.
## Configuration Options
The JSONSearchTool supports extensive customization through a configuration dictionary. This allows users to select different models for embeddings and summarization based on their requirements.
```python Code
tool = JSONSearchTool(
config={
"llm": {
"provider": "ollama", # Other options include google, openai, anthropic, llama2, etc.
"config": {
"model": "llama2",
# Additional optional configurations can be specified here.
# temperature=0.5,
# top_p=1,
# stream=true,
},
},
"embedding_model": {
"provider": "google", # or openai, ollama, ...
"config": {
"model": "models/embedding-001",
"task_type": "retrieval_document",
# Further customization options can be added here.
},
},
}
)
```
# Linkup Search Tool
Source: https://docs.crewai.com/tools/linkupsearchtool
The `LinkupSearchTool` enables querying the Linkup API for contextual information.
# `LinkupSearchTool`
## Description
The `LinkupSearchTool` provides the ability to query the Linkup API for contextual information and retrieve structured results. This tool is ideal for enriching workflows with up-to-date and reliable information from Linkup, allowing agents to access relevant data during their tasks.
## Installation
To use this tool, you need to install the Linkup SDK:
```shell
uv add linkup-sdk
```
## Steps to Get Started
To effectively use the `LinkupSearchTool`, follow these steps:
1. **API Key**: Obtain a Linkup API key.
2. **Environment Setup**: Set up your environment with the API key.
3. **Install SDK**: Install the Linkup SDK using the command above.
## Example
The following example demonstrates how to initialize the tool and use it in an agent:
```python Code
from crewai_tools import LinkupSearchTool
from crewai import Agent
import os
# Initialize the tool with your API key
linkup_tool = LinkupSearchTool(api_key=os.getenv("LINKUP_API_KEY"))
# Define an agent that uses the tool
@agent
def researcher(self) -> Agent:
'''
This agent uses the LinkupSearchTool to retrieve contextual information
from the Linkup API.
'''
return Agent(
config=self.agents_config["researcher"],
tools=[linkup_tool]
)
```
## Parameters
The `LinkupSearchTool` accepts the following parameters:
### Constructor Parameters
* **api\_key**: Required. Your Linkup API key.
### Run Parameters
* **query**: Required. The search term or phrase.
* **depth**: Optional. The search depth. Default is "standard".
* **output\_type**: Optional. The type of output. Default is "searchResults".
## Advanced Usage
You can customize the search parameters for more specific results:
```python Code
# Perform a search with custom parameters
results = linkup_tool.run(
query="Women Nobel Prize Physics",
depth="deep",
output_type="searchResults"
)
```
## Return Format
The tool returns results in the following format:
```json
{
"success": true,
"results": [
{
"name": "Result Title",
"url": "https://example.com/result",
"content": "Content of the result..."
},
// Additional results...
]
}
```
If an error occurs, the response will be:
```json
{
"success": false,
"error": "Error message"
}
```
## Error Handling
The tool gracefully handles API errors and provides structured feedback. If the API request fails, the tool will return a dictionary with `success: false` and an error message.
## Conclusion
The `LinkupSearchTool` provides a seamless way to integrate Linkup's contextual information retrieval capabilities into your CrewAI agents. By leveraging this tool, agents can access relevant and up-to-date information to enhance their decision-making and task execution.
# LlamaIndex Tool
Source: https://docs.crewai.com/tools/llamaindextool
The `LlamaIndexTool` is a wrapper for LlamaIndex tools and query engines.
# `LlamaIndexTool`
## Description
The `LlamaIndexTool` is designed to be a general wrapper around LlamaIndex tools and query engines, enabling you to leverage LlamaIndex resources in terms of RAG/agentic pipelines as tools to plug into CrewAI agents. This tool allows you to seamlessly integrate LlamaIndex's powerful data processing and retrieval capabilities into your CrewAI workflows.
## Installation
To use this tool, you need to install LlamaIndex:
```shell
uv add llama-index
```
## Steps to Get Started
To effectively use the `LlamaIndexTool`, follow these steps:
1. **Install LlamaIndex**: Install the LlamaIndex package using the command above.
2. **Set Up LlamaIndex**: Follow the [LlamaIndex documentation](https://docs.llamaindex.ai/) to set up a RAG/agent pipeline.
3. **Create a Tool or Query Engine**: Create a LlamaIndex tool or query engine that you want to use with CrewAI.
## Example
The following examples demonstrate how to initialize the tool from different LlamaIndex components:
### From a LlamaIndex Tool
```python Code
from crewai_tools import LlamaIndexTool
from crewai import Agent
from llama_index.core.tools import FunctionTool
# Example 1: Initialize from FunctionTool
def search_data(query: str) -> str:
"""Search for information in the data."""
# Your implementation here
return f"Results for: {query}"
# Create a LlamaIndex FunctionTool
og_tool = FunctionTool.from_defaults(
search_data,
name="DataSearchTool",
description="Search for information in the data"
)
# Wrap it with LlamaIndexTool
tool = LlamaIndexTool.from_tool(og_tool)
# Define an agent that uses the tool
@agent
def researcher(self) -> Agent:
'''
This agent uses the LlamaIndexTool to search for information.
'''
return Agent(
config=self.agents_config["researcher"],
tools=[tool]
)
```
### From LlamaHub Tools
```python Code
from crewai_tools import LlamaIndexTool
from llama_index.tools.wolfram_alpha import WolframAlphaToolSpec
# Initialize from LlamaHub Tools
wolfram_spec = WolframAlphaToolSpec(app_id="your_app_id")
wolfram_tools = wolfram_spec.to_tool_list()
tools = [LlamaIndexTool.from_tool(t) for t in wolfram_tools]
```
### From a LlamaIndex Query Engine
```python Code
from crewai_tools import LlamaIndexTool
from llama_index.core import VectorStoreIndex
from llama_index.core.readers import SimpleDirectoryReader
# Load documents
documents = SimpleDirectoryReader("./data").load_data()
# Create an index
index = VectorStoreIndex.from_documents(documents)
# Create a query engine
query_engine = index.as_query_engine()
# Create a LlamaIndexTool from the query engine
query_tool = LlamaIndexTool.from_query_engine(
query_engine,
name="Company Data Query Tool",
description="Use this tool to lookup information in company documents"
)
```
## Class Methods
The `LlamaIndexTool` provides two main class methods for creating instances:
### from\_tool
Creates a `LlamaIndexTool` from a LlamaIndex tool.
```python Code
@classmethod
def from_tool(cls, tool: Any, **kwargs: Any) -> "LlamaIndexTool":
# Implementation details
```
### from\_query\_engine
Creates a `LlamaIndexTool` from a LlamaIndex query engine.
```python Code
@classmethod
def from_query_engine(
cls,
query_engine: Any,
name: Optional[str] = None,
description: Optional[str] = None,
return_direct: bool = False,
**kwargs: Any,
) -> "LlamaIndexTool":
# Implementation details
```
## Parameters
The `from_query_engine` method accepts the following parameters:
* **query\_engine**: Required. The LlamaIndex query engine to wrap.
* **name**: Optional. The name of the tool.
* **description**: Optional. The description of the tool.
* **return\_direct**: Optional. Whether to return the response directly. Default is `False`.
## Conclusion
The `LlamaIndexTool` provides a powerful way to integrate LlamaIndex's capabilities into CrewAI agents. By wrapping LlamaIndex tools and query engines, it enables agents to leverage sophisticated data retrieval and processing functionalities, enhancing their ability to work with complex information sources.
# MDX RAG Search
Source: https://docs.crewai.com/tools/mdxsearchtool
The `MDXSearchTool` is designed to search MDX files and return the most relevant results.
# `MDXSearchTool`
The MDXSearchTool is in continuous development. Features may be added or removed, and functionality could change unpredictably as we refine the tool.
## Description
The MDX Search Tool is a component of the `crewai_tools` package aimed at facilitating advanced markdown language extraction. It enables users to effectively search and extract relevant information from MD files using query-based searches. This tool is invaluable for data analysis, information management, and research tasks, streamlining the process of finding specific information within large document collections.
## Installation
Before using the MDX Search Tool, ensure the `crewai_tools` package is installed. If it is not, you can install it with the following command:
```shell
pip install 'crewai[tools]'
```
## Usage Example
To use the MDX Search Tool, you must first set up the necessary environment variables. Then, integrate the tool into your crewAI project to begin your market research. Below is a basic example of how to do this:
```python Code
from crewai_tools import MDXSearchTool
# Initialize the tool to search any MDX content it learns about during execution
tool = MDXSearchTool()
# OR
# Initialize the tool with a specific MDX file path for an exclusive search within that document
tool = MDXSearchTool(mdx='path/to/your/document.mdx')
```
## Parameters
* mdx: **Optional**. Specifies the MDX file path for the search. It can be provided during initialization.
## Customization of Model and Embeddings
The tool defaults to using OpenAI for embeddings and summarization. For customization, utilize a configuration dictionary as shown below:
```python Code
tool = MDXSearchTool(
config=dict(
llm=dict(
provider="ollama", # Options include google, openai, anthropic, llama2, etc.
config=dict(
model="llama2",
# Optional parameters can be included here.
# temperature=0.5,
# top_p=1,
# stream=true,
),
),
embedder=dict(
provider="google", # or openai, ollama, ...
config=dict(
model="models/embedding-001",
task_type="retrieval_document",
# Optional title for the embeddings can be added here.
# title="Embeddings",
),
),
)
)
```
# MultiOn Tool
Source: https://docs.crewai.com/tools/multiontool
The `MultiOnTool` empowers CrewAI agents with the capability to navigate and interact with the web through natural language instructions.
# `MultiOnTool`
## Description
The `MultiOnTool` is designed to wrap [MultiOn's](https://docs.multion.ai/welcome) web browsing capabilities, enabling CrewAI agents to control web browsers using natural language instructions. This tool facilitates seamless web browsing, making it an essential asset for projects requiring dynamic web data interaction and automation of web-based tasks.
## Installation
To use this tool, you need to install the MultiOn package:
```shell
uv add multion
```
You'll also need to install the MultiOn browser extension and enable API usage.
## Steps to Get Started
To effectively use the `MultiOnTool`, follow these steps:
1. **Install CrewAI**: Ensure that the `crewai[tools]` package is installed in your Python environment.
2. **Install and use MultiOn**: Follow [MultiOn documentation](https://docs.multion.ai/learn/browser-extension) for installing the MultiOn Browser Extension.
3. **Enable API Usage**: Click on the MultiOn extension in the extensions folder of your browser (not the hovering MultiOn icon on the web page) to open the extension configurations. Click the API Enabled toggle to enable the API.
## Example
The following example demonstrates how to initialize the tool and execute a web browsing task:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools import MultiOnTool
# Initialize the tool
multion_tool = MultiOnTool(api_key="YOUR_MULTION_API_KEY", local=False)
# Define an agent that uses the tool
browser_agent = Agent(
role="Browser Agent",
goal="Control web browsers using natural language",
backstory="An expert browsing agent.",
tools=[multion_tool],
verbose=True,
)
# Example task to search and summarize news
browse_task = Task(
description="Summarize the top 3 trending AI News headlines",
expected_output="A summary of the top 3 trending AI News headlines",
agent=browser_agent,
)
# Create and run the crew
crew = Crew(agents=[browser_agent], tasks=[browse_task])
result = crew.kickoff()
```
## Parameters
The `MultiOnTool` accepts the following parameters during initialization:
* **api\_key**: Optional. Specifies the MultiOn API key. If not provided, it will look for the `MULTION_API_KEY` environment variable.
* **local**: Optional. Set to `True` to run the agent locally on your browser. Make sure the MultiOn browser extension is installed and API Enabled is checked. Default is `False`.
* **max\_steps**: Optional. Sets the maximum number of steps the MultiOn agent can take for a command. Default is `3`.
## Usage
When using the `MultiOnTool`, the agent will provide natural language instructions that the tool translates into web browsing actions. The tool returns the results of the browsing session along with a status.
```python Code
# Example of using the tool with an agent
browser_agent = Agent(
role="Web Browser Agent",
goal="Search for and summarize information from the web",
backstory="An expert at finding and extracting information from websites.",
tools=[multion_tool],
verbose=True,
)
# Create a task for the agent
search_task = Task(
description="Search for the latest AI news on TechCrunch and summarize the top 3 headlines",
expected_output="A summary of the top 3 AI news headlines from TechCrunch",
agent=browser_agent,
)
# Run the task
crew = Crew(agents=[browser_agent], tasks=[search_task])
result = crew.kickoff()
```
If the status returned is `CONTINUE`, the agent should be instructed to reissue the same instruction to continue execution.
## Implementation Details
The `MultiOnTool` is implemented as a subclass of `BaseTool` from CrewAI. It wraps the MultiOn client to provide web browsing capabilities:
```python Code
class MultiOnTool(BaseTool):
"""Tool to wrap MultiOn Browse Capabilities."""
name: str = "Multion Browse Tool"
description: str = """Multion gives the ability for LLMs to control web browsers using natural language instructions.
If the status is 'CONTINUE', reissue the same instruction to continue execution
"""
# Implementation details...
def _run(self, cmd: str, *args: Any, **kwargs: Any) -> str:
"""
Run the Multion client with the given command.
Args:
cmd (str): The detailed and specific natural language instruction for web browsing
*args (Any): Additional arguments to pass to the Multion client
**kwargs (Any): Additional keyword arguments to pass to the Multion client
"""
# Implementation details...
```
## Conclusion
The `MultiOnTool` provides a powerful way to integrate web browsing capabilities into CrewAI agents. By enabling agents to interact with websites through natural language instructions, it opens up a wide range of possibilities for web-based tasks, from data collection and research to automated interactions with web services.
# MySQL RAG Search
Source: https://docs.crewai.com/tools/mysqltool
The `MySQLSearchTool` is designed to search MySQL databases and return the most relevant results.
# `MySQLSearchTool`
## Description
This tool is designed to facilitate semantic searches within MySQL database tables. Leveraging the RAG (Retrieve and Generate) technology,
the MySQLSearchTool provides users with an efficient means of querying database table content, specifically tailored for MySQL databases.
It simplifies the process of finding relevant data through semantic search queries, making it an invaluable resource for users needing
to perform advanced queries on extensive datasets within a MySQL database.
## Installation
To install the `crewai_tools` package and utilize the MySQLSearchTool, execute the following command in your terminal:
```shell
pip install 'crewai[tools]'
```
## Example
Below is an example showcasing how to use the MySQLSearchTool to conduct a semantic search on a table within a MySQL database:
```python Code
from crewai_tools import MySQLSearchTool
# Initialize the tool with the database URI and the target table name
tool = MySQLSearchTool(
db_uri='mysql://user:password@localhost:3306/mydatabase',
table_name='employees'
)
```
## Arguments
The MySQLSearchTool requires the following arguments for its operation:
* `db_uri`: A string representing the URI of the MySQL database to be queried. This argument is mandatory and must include the necessary authentication details and the location of the database.
* `table_name`: A string specifying the name of the table within the database on which the semantic search will be performed. This argument is mandatory.
## Custom model and embeddings
By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
```python Code
tool = MySQLSearchTool(
config=dict(
llm=dict(
provider="ollama", # or google, openai, anthropic, llama2, ...
config=dict(
model="llama2",
# temperature=0.5,
# top_p=1,
# stream=true,
),
),
embedder=dict(
provider="google",
config=dict(
model="models/embedding-001",
task_type="retrieval_document",
# title="Embeddings",
),
),
)
)
```
# NL2SQL Tool
Source: https://docs.crewai.com/tools/nl2sqltool
The `NL2SQLTool` is designed to convert natural language to SQL queries.
# `NL2SQLTool`
## Description
This tool is used to convert natural language to SQL queries. When passsed to the agent it will generate queries and then use them to interact with the database.
This enables multiple workflows like having an Agent to access the database fetch information based on the goal and then use the information to generate a response, report or any other output.
Along with that proivdes the ability for the Agent to update the database based on its goal.
**Attention**: Make sure that the Agent has access to a Read-Replica or that is okay for the Agent to run insert/update queries on the database.
## Requirements
* SqlAlchemy
* Any DB compatible library (e.g. psycopg2, mysql-connector-python)
## Installation
Install the crewai\_tools package
```shell
pip install 'crewai[tools]'
```
## Usage
In order to use the NL2SQLTool, you need to pass the database URI to the tool. The URI should be in the format `dialect+driver://username:password@host:port/database`.
```python Code
from crewai_tools import NL2SQLTool
# psycopg2 was installed to run this example with PostgreSQL
nl2sql = NL2SQLTool(db_uri="postgresql://example@localhost:5432/test_db")
@agent
def researcher(self) -> Agent:
return Agent(
config=self.agents_config["researcher"],
allow_delegation=False,
tools=[nl2sql]
)
```
## Example
The primary task goal was:
"Retrieve the average, maximum, and minimum monthly revenue for each city, but only include cities that have more than one user. Also, count the number of user in each city and
sort the results by the average monthly revenue in descending order"
So the Agent tried to get information from the DB, the first one is wrong so the Agent tries again and gets the correct information and passes to the next agent.
The second task goal was:
"Review the data and create a detailed report, and then create the table on the database with the fields based on the data provided.
Include information on the average, maximum, and minimum monthly revenue for each city, but only include cities that have more than one user. Also, count the number of users in each city and sort the results by the average monthly revenue in descending order."
Now things start to get interesting, the Agent generates the SQL query to not only create the table but also insert the data into the table. And in the end the Agent still returns the final report which is exactly what was in the database.
This is a simple example of how the NL2SQLTool can be used to interact with the database and generate reports based on the data in the database.
The Tool provides endless possibilities on the logic of the Agent and how it can interact with the database.
```md
DB -> Agent -> ... -> Agent -> DB
```
# Patronus Evaluation Tools
Source: https://docs.crewai.com/tools/patronustools
The Patronus evaluation tools enable CrewAI agents to evaluate and score model inputs and outputs using the Patronus AI platform.
# `Patronus Evaluation Tools`
## Description
The [Patronus evaluation tools](https://patronus.ai) are designed to enable CrewAI agents to evaluate and score model inputs and outputs using the Patronus AI platform. These tools provide different levels of control over the evaluation process, from allowing agents to select the most appropriate evaluator and criteria to using predefined criteria or custom local evaluators.
There are three main Patronus evaluation tools:
1. **PatronusEvalTool**: Allows agents to select the most appropriate evaluator and criteria for the evaluation task.
2. **PatronusPredefinedCriteriaEvalTool**: Uses predefined evaluator and criteria specified by the user.
3. **PatronusLocalEvaluatorTool**: Uses custom function evaluators defined by the user.
## Installation
To use these tools, you need to install the Patronus package:
```shell
uv add patronus
```
You'll also need to set up your Patronus API key as an environment variable:
```shell
export PATRONUS_API_KEY="your_patronus_api_key"
```
## Steps to Get Started
To effectively use the Patronus evaluation tools, follow these steps:
1. **Install Patronus**: Install the Patronus package using the command above.
2. **Set Up API Key**: Set your Patronus API key as an environment variable.
3. **Choose the Right Tool**: Select the appropriate Patronus evaluation tool based on your needs.
4. **Configure the Tool**: Configure the tool with the necessary parameters.
## Examples
### Using PatronusEvalTool
The following example demonstrates how to use the `PatronusEvalTool`, which allows agents to select the most appropriate evaluator and criteria:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools import PatronusEvalTool
# Initialize the tool
patronus_eval_tool = PatronusEvalTool()
# Define an agent that uses the tool
coding_agent = Agent(
role="Coding Agent",
goal="Generate high quality code and verify that the output is code",
backstory="An experienced coder who can generate high quality python code.",
tools=[patronus_eval_tool],
verbose=True,
)
# Example task to generate and evaluate code
generate_code_task = Task(
description="Create a simple program to generate the first N numbers in the Fibonacci sequence. Select the most appropriate evaluator and criteria for evaluating your output.",
expected_output="Program that generates the first N numbers in the Fibonacci sequence.",
agent=coding_agent,
)
# Create and run the crew
crew = Crew(agents=[coding_agent], tasks=[generate_code_task])
result = crew.kickoff()
```
### Using PatronusPredefinedCriteriaEvalTool
The following example demonstrates how to use the `PatronusPredefinedCriteriaEvalTool`, which uses predefined evaluator and criteria:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools import PatronusPredefinedCriteriaEvalTool
# Initialize the tool with predefined criteria
patronus_eval_tool = PatronusPredefinedCriteriaEvalTool(
evaluators=[{"evaluator": "judge", "criteria": "contains-code"}]
)
# Define an agent that uses the tool
coding_agent = Agent(
role="Coding Agent",
goal="Generate high quality code",
backstory="An experienced coder who can generate high quality python code.",
tools=[patronus_eval_tool],
verbose=True,
)
# Example task to generate code
generate_code_task = Task(
description="Create a simple program to generate the first N numbers in the Fibonacci sequence.",
expected_output="Program that generates the first N numbers in the Fibonacci sequence.",
agent=coding_agent,
)
# Create and run the crew
crew = Crew(agents=[coding_agent], tasks=[generate_code_task])
result = crew.kickoff()
```
### Using PatronusLocalEvaluatorTool
The following example demonstrates how to use the `PatronusLocalEvaluatorTool`, which uses custom function evaluators:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools import PatronusLocalEvaluatorTool
from patronus import Client, EvaluationResult
import random
# Initialize the Patronus client
client = Client()
# Register a custom evaluator
@client.register_local_evaluator("random_evaluator")
def random_evaluator(**kwargs):
score = random.random()
return EvaluationResult(
score_raw=score,
pass_=score >= 0.5,
explanation="example explanation",
)
# Initialize the tool with the custom evaluator
patronus_eval_tool = PatronusLocalEvaluatorTool(
patronus_client=client,
evaluator="random_evaluator",
evaluated_model_gold_answer="example label",
)
# Define an agent that uses the tool
coding_agent = Agent(
role="Coding Agent",
goal="Generate high quality code",
backstory="An experienced coder who can generate high quality python code.",
tools=[patronus_eval_tool],
verbose=True,
)
# Example task to generate code
generate_code_task = Task(
description="Create a simple program to generate the first N numbers in the Fibonacci sequence.",
expected_output="Program that generates the first N numbers in the Fibonacci sequence.",
agent=coding_agent,
)
# Create and run the crew
crew = Crew(agents=[coding_agent], tasks=[generate_code_task])
result = crew.kickoff()
```
## Parameters
### PatronusEvalTool
The `PatronusEvalTool` does not require any parameters during initialization. It automatically fetches available evaluators and criteria from the Patronus API.
### PatronusPredefinedCriteriaEvalTool
The `PatronusPredefinedCriteriaEvalTool` accepts the following parameters during initialization:
* **evaluators**: Required. A list of dictionaries containing the evaluator and criteria to use. For example: `[{"evaluator": "judge", "criteria": "contains-code"}]`.
### PatronusLocalEvaluatorTool
The `PatronusLocalEvaluatorTool` accepts the following parameters during initialization:
* **patronus\_client**: Required. The Patronus client instance.
* **evaluator**: Optional. The name of the registered local evaluator to use. Default is an empty string.
* **evaluated\_model\_gold\_answer**: Optional. The gold answer to use for evaluation. Default is an empty string.
## Usage
When using the Patronus evaluation tools, you provide the model input, output, and context, and the tool returns the evaluation results from the Patronus API.
For the `PatronusEvalTool` and `PatronusPredefinedCriteriaEvalTool`, the following parameters are required when calling the tool:
* **evaluated\_model\_input**: The agent's task description in simple text.
* **evaluated\_model\_output**: The agent's output of the task.
* **evaluated\_model\_retrieved\_context**: The agent's context.
For the `PatronusLocalEvaluatorTool`, the same parameters are required, but the evaluator and gold answer are specified during initialization.
## Conclusion
The Patronus evaluation tools provide a powerful way to evaluate and score model inputs and outputs using the Patronus AI platform. By enabling agents to evaluate their own outputs or the outputs of other agents, these tools can help improve the quality and reliability of CrewAI workflows.
# PDF RAG Search
Source: https://docs.crewai.com/tools/pdfsearchtool
The `PDFSearchTool` is designed to search PDF files and return the most relevant results.
# `PDFSearchTool`
We are still working on improving tools, so there might be unexpected behavior or changes in the future.
## Description
The PDFSearchTool is a RAG tool designed for semantic searches within PDF content. It allows for inputting a search query and a PDF document, leveraging advanced search techniques to find relevant content efficiently.
This capability makes it especially useful for extracting specific information from large PDF files quickly.
## Installation
To get started with the PDFSearchTool, first, ensure the crewai\_tools package is installed with the following command:
```shell
pip install 'crewai[tools]'
```
## Example
Here's how to use the PDFSearchTool to search within a PDF document:
```python Code
from crewai_tools import PDFSearchTool
# Initialize the tool allowing for any PDF content search if the path is provided during execution
tool = PDFSearchTool()
# OR
# Initialize the tool with a specific PDF path for exclusive search within that document
tool = PDFSearchTool(pdf='path/to/your/document.pdf')
```
## Arguments
* `pdf`: **Optional** The PDF path for the search. Can be provided at initialization or within the `run` method's arguments. If provided at initialization, the tool confines its search to the specified document.
## Custom model and embeddings
By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
```python Code
tool = PDFSearchTool(
config=dict(
llm=dict(
provider="ollama", # or google, openai, anthropic, llama2, ...
config=dict(
model="llama2",
# temperature=0.5,
# top_p=1,
# stream=true,
),
),
embedder=dict(
provider="google", # or openai, ollama, ...
config=dict(
model="models/embedding-001",
task_type="retrieval_document",
# title="Embeddings",
),
),
)
)
```
# PG RAG Search
Source: https://docs.crewai.com/tools/pgsearchtool
The `PGSearchTool` is designed to search PostgreSQL databases and return the most relevant results.
# `PGSearchTool`
The PGSearchTool is currently under development. This document outlines the intended functionality and interface.
As development progresses, please be aware that some features may not be available or could change.
## Description
The PGSearchTool is envisioned as a powerful tool for facilitating semantic searches within PostgreSQL database tables. By leveraging advanced Retrieve and Generate (RAG) technology,
it aims to provide an efficient means for querying database table content, specifically tailored for PostgreSQL databases.
The tool's goal is to simplify the process of finding relevant data through semantic search queries, offering a valuable resource for users needing to conduct advanced queries on
extensive datasets within a PostgreSQL environment.
## Installation
The `crewai_tools` package, which will include the PGSearchTool upon its release, can be installed using the following command:
```shell
pip install 'crewai[tools]'
```
The PGSearchTool is not yet available in the current version of the `crewai_tools` package. This installation command will be updated once the tool is released.
## Example Usage
Below is a proposed example showcasing how to use the PGSearchTool for conducting a semantic search on a table within a PostgreSQL database:
```python Code
from crewai_tools import PGSearchTool
# Initialize the tool with the database URI and the target table name
tool = PGSearchTool(
db_uri='postgresql://user:password@localhost:5432/mydatabase',
table_name='employees'
)
```
## Arguments
The PGSearchTool is designed to require the following arguments for its operation:
| Argument | Type | Description |
| :-------------- | :------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **db\_uri** | `string` | **Mandatory**. A string representing the URI of the PostgreSQL database to be queried. This argument will be mandatory and must include the necessary authentication details and the location of the database. |
| **table\_name** | `string` | **Mandatory**. A string specifying the name of the table within the database on which the semantic search will be performed. This argument will also be mandatory. |
## Custom Model and Embeddings
The tool intends to use OpenAI for both embeddings and summarization by default. Users will have the option to customize the model using a config dictionary as follows:
```python Code
tool = PGSearchTool(
config=dict(
llm=dict(
provider="ollama", # or google, openai, anthropic, llama2, ...
config=dict(
model="llama2",
# temperature=0.5,
# top_p=1,
# stream=true,
),
),
embedder=dict(
provider="google", # or openai, ollama, ...
config=dict(
model="models/embedding-001",
task_type="retrieval_document",
# title="Embeddings",
),
),
)
)
```
# Qdrant Vector Search Tool
Source: https://docs.crewai.com/tools/qdrantvectorsearchtool
Semantic search capabilities for CrewAI agents using Qdrant vector database
# `QdrantVectorSearchTool`
The Qdrant Vector Search Tool enables semantic search capabilities in your CrewAI agents by leveraging [Qdrant](https://qdrant.tech/), a vector similarity search engine. This tool allows your agents to search through documents stored in a Qdrant collection using semantic similarity.
## Installation
Install the required packages:
```bash
uv add qdrant-client
```
## Basic Usage
Here's a minimal example of how to use the tool:
```python
from crewai import Agent
from crewai_tools import QdrantVectorSearchTool
# Initialize the tool
qdrant_tool = QdrantVectorSearchTool(
qdrant_url="your_qdrant_url",
qdrant_api_key="your_qdrant_api_key",
collection_name="your_collection"
)
# Create an agent that uses the tool
agent = Agent(
role="Research Assistant",
goal="Find relevant information in documents",
tools=[qdrant_tool]
)
# The tool will automatically use OpenAI embeddings
# and return the 3 most relevant results with scores > 0.35
```
## Complete Working Example
Here's a complete example showing how to:
1. Extract text from a PDF
2. Generate embeddings using OpenAI
3. Store in Qdrant
4. Create a CrewAI agentic RAG workflow for semantic search
```python
import os
import uuid
import pdfplumber
from openai import OpenAI
from dotenv import load_dotenv
from crewai import Agent, Task, Crew, Process, LLM
from crewai_tools import QdrantVectorSearchTool
from qdrant_client import QdrantClient
from qdrant_client.models import PointStruct, Distance, VectorParams
# Load environment variables
load_dotenv()
# Initialize OpenAI client
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
# Extract text from PDF
def extract_text_from_pdf(pdf_path):
text = []
with pdfplumber.open(pdf_path) as pdf:
for page in pdf.pages:
page_text = page.extract_text()
if page_text:
text.append(page_text.strip())
return text
# Generate OpenAI embeddings
def get_openai_embedding(text):
response = client.embeddings.create(
input=text,
model="text-embedding-3-small"
)
return response.data[0].embedding
# Store text and embeddings in Qdrant
def load_pdf_to_qdrant(pdf_path, qdrant, collection_name):
# Extract text from PDF
text_chunks = extract_text_from_pdf(pdf_path)
# Create Qdrant collection
if qdrant.collection_exists(collection_name):
qdrant.delete_collection(collection_name)
qdrant.create_collection(
collection_name=collection_name,
vectors_config=VectorParams(size=1536, distance=Distance.COSINE)
)
# Store embeddings
points = []
for chunk in text_chunks:
embedding = get_openai_embedding(chunk)
points.append(PointStruct(
id=str(uuid.uuid4()),
vector=embedding,
payload={"text": chunk}
))
qdrant.upsert(collection_name=collection_name, points=points)
# Initialize Qdrant client and load data
qdrant = QdrantClient(
url=os.getenv("QDRANT_URL"),
api_key=os.getenv("QDRANT_API_KEY")
)
collection_name = "example_collection"
pdf_path = "path/to/your/document.pdf"
load_pdf_to_qdrant(pdf_path, qdrant, collection_name)
# Initialize Qdrant search tool
qdrant_tool = QdrantVectorSearchTool(
qdrant_url=os.getenv("QDRANT_URL"),
qdrant_api_key=os.getenv("QDRANT_API_KEY"),
collection_name=collection_name,
limit=3,
score_threshold=0.35
)
# Create CrewAI agents
search_agent = Agent(
role="Senior Semantic Search Agent",
goal="Find and analyze documents based on semantic search",
backstory="""You are an expert research assistant who can find relevant
information using semantic search in a Qdrant database.""",
tools=[qdrant_tool],
verbose=True
)
answer_agent = Agent(
role="Senior Answer Assistant",
goal="Generate answers to questions based on the context provided",
backstory="""You are an expert answer assistant who can generate
answers to questions based on the context provided.""",
tools=[qdrant_tool],
verbose=True
)
# Define tasks
search_task = Task(
description="""Search for relevant documents about the {query}.
Your final answer should include:
- The relevant information found
- The similarity scores of the results
- The metadata of the relevant documents""",
agent=search_agent
)
answer_task = Task(
description="""Given the context and metadata of relevant documents,
generate a final answer based on the context.""",
agent=answer_agent
)
# Run CrewAI workflow
crew = Crew(
agents=[search_agent, answer_agent],
tasks=[search_task, answer_task],
process=Process.sequential,
verbose=True
)
result = crew.kickoff(
inputs={"query": "What is the role of X in the document?"}
)
print(result)
```
## Tool Parameters
### Required Parameters
* `qdrant_url` (str): The URL of your Qdrant server
* `qdrant_api_key` (str): API key for authentication with Qdrant
* `collection_name` (str): Name of the Qdrant collection to search
### Optional Parameters
* `limit` (int): Maximum number of results to return (default: 3)
* `score_threshold` (float): Minimum similarity score threshold (default: 0.35)
* `custom_embedding_fn` (Callable\[\[str], list\[float]]): Custom function for text vectorization
## Search Parameters
The tool accepts these parameters in its schema:
* `query` (str): The search query to find similar documents
* `filter_by` (str, optional): Metadata field to filter on
* `filter_value` (str, optional): Value to filter by
## Return Format
The tool returns results in JSON format:
```json
[
{
"metadata": {
// Any metadata stored with the document
},
"context": "The actual text content of the document",
"distance": 0.95 // Similarity score
}
]
```
## Default Embedding
By default, the tool uses OpenAI's `text-embedding-3-small` model for vectorization. This requires:
* OpenAI API key set in environment: `OPENAI_API_KEY`
## Custom Embeddings
Instead of using the default embedding model, you might want to use your own embedding function in cases where you:
1. Want to use a different embedding model (e.g., Cohere, HuggingFace, Ollama models)
2. Need to reduce costs by using open-source embedding models
3. Have specific requirements for vector dimensions or embedding quality
4. Want to use domain-specific embeddings (e.g., for medical or legal text)
Here's an example using a HuggingFace model:
```python
from transformers import AutoTokenizer, AutoModel
import torch
# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
model = AutoModel.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
def custom_embeddings(text: str) -> list[float]:
# Tokenize and get model outputs
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
outputs = model(**inputs)
# Use mean pooling to get text embedding
embeddings = outputs.last_hidden_state.mean(dim=1)
# Convert to list of floats and return
return embeddings[0].tolist()
# Use custom embeddings with the tool
tool = QdrantVectorSearchTool(
qdrant_url="your_url",
qdrant_api_key="your_key",
collection_name="your_collection",
custom_embedding_fn=custom_embeddings # Pass your custom function
)
```
## Error Handling
The tool handles these specific errors:
* Raises ImportError if `qdrant-client` is not installed (with option to auto-install)
* Raises ValueError if `QDRANT_URL` is not set
* Prompts to install `qdrant-client` if missing using `uv add qdrant-client`
## Environment Variables
Required environment variables:
```bash
export QDRANT_URL="your_qdrant_url" # If not provided in constructor
export QDRANT_API_KEY="your_api_key" # If not provided in constructor
export OPENAI_API_KEY="your_openai_key" # If using default embeddings
```
# RAG Tool
Source: https://docs.crewai.com/tools/ragtool
The `RagTool` is a dynamic knowledge base tool for answering questions using Retrieval-Augmented Generation.
# `RagTool`
## Description
The `RagTool` is designed to answer questions by leveraging the power of Retrieval-Augmented Generation (RAG) through EmbedChain.
It provides a dynamic knowledge base that can be queried to retrieve relevant information from various data sources.
This tool is particularly useful for applications that require access to a vast array of information and need to provide contextually relevant answers.
## Example
The following example demonstrates how to initialize the tool and use it with different data sources:
```python Code
from crewai_tools import RagTool
# Create a RAG tool with default settings
rag_tool = RagTool()
# Add content from a file
rag_tool.add(data_type="file", path="path/to/your/document.pdf")
# Add content from a web page
rag_tool.add(data_type="web_page", url="https://example.com")
# Define an agent with the RagTool
@agent
def knowledge_expert(self) -> Agent:
'''
This agent uses the RagTool to answer questions about the knowledge base.
'''
return Agent(
config=self.agents_config["knowledge_expert"],
allow_delegation=False,
tools=[rag_tool]
)
```
## Supported Data Sources
The `RagTool` can be used with a wide variety of data sources, including:
* 📰 PDF files
* 📊 CSV files
* 📃 JSON files
* 📝 Text
* 📁 Directories/Folders
* 🌐 HTML Web pages
* 📽️ YouTube Channels
* 📺 YouTube Videos
* 📚 Documentation websites
* 📝 MDX files
* 📄 DOCX files
* 🧾 XML files
* 📬 Gmail
* 📝 GitHub repositories
* 🐘 PostgreSQL databases
* 🐬 MySQL databases
* 🤖 Slack conversations
* 💬 Discord messages
* 🗨️ Discourse forums
* 📝 Substack newsletters
* 🐝 Beehiiv content
* 💾 Dropbox files
* 🖼️ Images
* ⚙️ Custom data sources
## Parameters
The `RagTool` accepts the following parameters:
* **summarize**: Optional. Whether to summarize the retrieved content. Default is `False`.
* **adapter**: Optional. A custom adapter for the knowledge base. If not provided, an EmbedchainAdapter will be used.
* **config**: Optional. Configuration for the underlying EmbedChain App.
## Adding Content
You can add content to the knowledge base using the `add` method:
```python Code
# Add a PDF file
rag_tool.add(data_type="file", path="path/to/your/document.pdf")
# Add a web page
rag_tool.add(data_type="web_page", url="https://example.com")
# Add a YouTube video
rag_tool.add(data_type="youtube_video", url="https://www.youtube.com/watch?v=VIDEO_ID")
# Add a directory of files
rag_tool.add(data_type="directory", path="path/to/your/directory")
```
## Agent Integration Example
Here's how to integrate the `RagTool` with a CrewAI agent:
```python Code
from crewai import Agent
from crewai.project import agent
from crewai_tools import RagTool
# Initialize the tool and add content
rag_tool = RagTool()
rag_tool.add(data_type="web_page", url="https://docs.crewai.com")
rag_tool.add(data_type="file", path="company_data.pdf")
# Define an agent with the RagTool
@agent
def knowledge_expert(self) -> Agent:
return Agent(
config=self.agents_config["knowledge_expert"],
allow_delegation=False,
tools=[rag_tool]
)
```
## Advanced Configuration
You can customize the behavior of the `RagTool` by providing a configuration dictionary:
```python Code
from crewai_tools import RagTool
# Create a RAG tool with custom configuration
config = {
"app": {
"name": "custom_app",
},
"llm": {
"provider": "openai",
"config": {
"model": "gpt-4",
}
},
"embedding_model": {
"provider": "openai",
"config": {
"model": "text-embedding-ada-002"
}
}
}
rag_tool = RagTool(config=config, summarize=True)
```
## Conclusion
The `RagTool` provides a powerful way to create and query knowledge bases from various data sources. By leveraging Retrieval-Augmented Generation, it enables agents to access and retrieve relevant information efficiently, enhancing their ability to provide accurate and contextually appropriate responses.
# S3 Reader Tool
Source: https://docs.crewai.com/tools/s3readertool
The `S3ReaderTool` enables CrewAI agents to read files from Amazon S3 buckets.
# `S3ReaderTool`
## Description
The `S3ReaderTool` is designed to read files from Amazon S3 buckets. This tool allows CrewAI agents to access and retrieve content stored in S3, making it ideal for workflows that require reading data, configuration files, or any other content stored in AWS S3 storage.
## Installation
To use this tool, you need to install the required dependencies:
```shell
uv add boto3
```
## Steps to Get Started
To effectively use the `S3ReaderTool`, follow these steps:
1. **Install Dependencies**: Install the required packages using the command above.
2. **Configure AWS Credentials**: Set up your AWS credentials as environment variables.
3. **Initialize the Tool**: Create an instance of the tool.
4. **Specify S3 Path**: Provide the S3 path to the file you want to read.
## Example
The following example demonstrates how to use the `S3ReaderTool` to read a file from an S3 bucket:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools.aws.s3 import S3ReaderTool
# Initialize the tool
s3_reader_tool = S3ReaderTool()
# Define an agent that uses the tool
file_reader_agent = Agent(
role="File Reader",
goal="Read files from S3 buckets",
backstory="An expert in retrieving and processing files from cloud storage.",
tools=[s3_reader_tool],
verbose=True,
)
# Example task to read a configuration file
read_task = Task(
description="Read the configuration file from {my_bucket} and summarize its contents.",
expected_output="A summary of the configuration file contents.",
agent=file_reader_agent,
)
# Create and run the crew
crew = Crew(agents=[file_reader_agent], tasks=[read_task])
result = crew.kickoff(inputs={"my_bucket": "s3://my-bucket/config/app-config.json"})
```
## Parameters
The `S3ReaderTool` accepts the following parameter when used by an agent:
* **file\_path**: Required. The S3 file path in the format `s3://bucket-name/file-name`.
## AWS Credentials
The tool requires AWS credentials to access S3 buckets. You can configure these credentials using environment variables:
* **CREW\_AWS\_REGION**: The AWS region where your S3 bucket is located. Default is `us-east-1`.
* **CREW\_AWS\_ACCESS\_KEY\_ID**: Your AWS access key ID.
* **CREW\_AWS\_SEC\_ACCESS\_KEY**: Your AWS secret access key.
## Usage
When using the `S3ReaderTool` with an agent, the agent will need to provide the S3 file path:
```python Code
# Example of using the tool with an agent
file_reader_agent = Agent(
role="File Reader",
goal="Read files from S3 buckets",
backstory="An expert in retrieving and processing files from cloud storage.",
tools=[s3_reader_tool],
verbose=True,
)
# Create a task for the agent to read a specific file
read_config_task = Task(
description="Read the application configuration file from {my_bucket} and extract the database connection settings.",
expected_output="The database connection settings from the configuration file.",
agent=file_reader_agent,
)
# Run the task
crew = Crew(agents=[file_reader_agent], tasks=[read_config_task])
result = crew.kickoff(inputs={"my_bucket": "s3://my-bucket/config/app-config.json"})
```
## Error Handling
The `S3ReaderTool` includes error handling for common S3 issues:
* Invalid S3 path format
* Missing or inaccessible files
* Permission issues
* AWS credential problems
When an error occurs, the tool will return an error message that includes details about the issue.
## Implementation Details
The `S3ReaderTool` uses the AWS SDK for Python (boto3) to interact with S3:
```python Code
class S3ReaderTool(BaseTool):
name: str = "S3 Reader Tool"
description: str = "Reads a file from Amazon S3 given an S3 file path"
def _run(self, file_path: str) -> str:
try:
bucket_name, object_key = self._parse_s3_path(file_path)
s3 = boto3.client(
's3',
region_name=os.getenv('CREW_AWS_REGION', 'us-east-1'),
aws_access_key_id=os.getenv('CREW_AWS_ACCESS_KEY_ID'),
aws_secret_access_key=os.getenv('CREW_AWS_SEC_ACCESS_KEY')
)
# Read file content from S3
response = s3.get_object(Bucket=bucket_name, Key=object_key)
file_content = response['Body'].read().decode('utf-8')
return file_content
except ClientError as e:
return f"Error reading file from S3: {str(e)}"
```
## Conclusion
The `S3ReaderTool` provides a straightforward way to read files from Amazon S3 buckets. By enabling agents to access content stored in S3, it facilitates workflows that require cloud-based file access. This tool is particularly useful for data processing, configuration management, and any task that involves retrieving information from AWS S3 storage.
# S3 Writer Tool
Source: https://docs.crewai.com/tools/s3writertool
The `S3WriterTool` enables CrewAI agents to write content to files in Amazon S3 buckets.
# `S3WriterTool`
## Description
The `S3WriterTool` is designed to write content to files in Amazon S3 buckets. This tool allows CrewAI agents to create or update files in S3, making it ideal for workflows that require storing data, saving configuration files, or persisting any other content to AWS S3 storage.
## Installation
To use this tool, you need to install the required dependencies:
```shell
uv add boto3
```
## Steps to Get Started
To effectively use the `S3WriterTool`, follow these steps:
1. **Install Dependencies**: Install the required packages using the command above.
2. **Configure AWS Credentials**: Set up your AWS credentials as environment variables.
3. **Initialize the Tool**: Create an instance of the tool.
4. **Specify S3 Path and Content**: Provide the S3 path where you want to write the file and the content to be written.
## Example
The following example demonstrates how to use the `S3WriterTool` to write content to a file in an S3 bucket:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools.aws.s3 import S3WriterTool
# Initialize the tool
s3_writer_tool = S3WriterTool()
# Define an agent that uses the tool
file_writer_agent = Agent(
role="File Writer",
goal="Write content to files in S3 buckets",
backstory="An expert in storing and managing files in cloud storage.",
tools=[s3_writer_tool],
verbose=True,
)
# Example task to write a report
write_task = Task(
description="Generate a summary report of the quarterly sales data and save it to {my_bucket}.",
expected_output="Confirmation that the report was successfully saved to S3.",
agent=file_writer_agent,
)
# Create and run the crew
crew = Crew(agents=[file_writer_agent], tasks=[write_task])
result = crew.kickoff(inputs={"my_bucket": "s3://my-bucket/reports/quarterly-summary.txt"})
```
## Parameters
The `S3WriterTool` accepts the following parameters when used by an agent:
* **file\_path**: Required. The S3 file path in the format `s3://bucket-name/file-name`.
* **content**: Required. The content to write to the file.
## AWS Credentials
The tool requires AWS credentials to access S3 buckets. You can configure these credentials using environment variables:
* **CREW\_AWS\_REGION**: The AWS region where your S3 bucket is located. Default is `us-east-1`.
* **CREW\_AWS\_ACCESS\_KEY\_ID**: Your AWS access key ID.
* **CREW\_AWS\_SEC\_ACCESS\_KEY**: Your AWS secret access key.
## Usage
When using the `S3WriterTool` with an agent, the agent will need to provide both the S3 file path and the content to write:
```python Code
# Example of using the tool with an agent
file_writer_agent = Agent(
role="File Writer",
goal="Write content to files in S3 buckets",
backstory="An expert in storing and managing files in cloud storage.",
tools=[s3_writer_tool],
verbose=True,
)
# Create a task for the agent to write a specific file
write_config_task = Task(
description="""
Create a configuration file with the following database settings:
- host: db.example.com
- port: 5432
- username: app_user
- password: secure_password
Save this configuration as JSON to {my_bucket}.
""",
expected_output="Confirmation that the configuration file was successfully saved to S3.",
agent=file_writer_agent,
)
# Run the task
crew = Crew(agents=[file_writer_agent], tasks=[write_config_task])
result = crew.kickoff(inputs={"my_bucket": "s3://my-bucket/config/db-config.json"})
```
## Error Handling
The `S3WriterTool` includes error handling for common S3 issues:
* Invalid S3 path format
* Permission issues (e.g., no write access to the bucket)
* AWS credential problems
* Bucket does not exist
When an error occurs, the tool will return an error message that includes details about the issue.
## Implementation Details
The `S3WriterTool` uses the AWS SDK for Python (boto3) to interact with S3:
```python Code
class S3WriterTool(BaseTool):
name: str = "S3 Writer Tool"
description: str = "Writes content to a file in Amazon S3 given an S3 file path"
def _run(self, file_path: str, content: str) -> str:
try:
bucket_name, object_key = self._parse_s3_path(file_path)
s3 = boto3.client(
's3',
region_name=os.getenv('CREW_AWS_REGION', 'us-east-1'),
aws_access_key_id=os.getenv('CREW_AWS_ACCESS_KEY_ID'),
aws_secret_access_key=os.getenv('CREW_AWS_SEC_ACCESS_KEY')
)
s3.put_object(Bucket=bucket_name, Key=object_key, Body=content.encode('utf-8'))
return f"Successfully wrote content to {file_path}"
except ClientError as e:
return f"Error writing file to S3: {str(e)}"
```
## Conclusion
The `S3WriterTool` provides a straightforward way to write content to files in Amazon S3 buckets. By enabling agents to create and update files in S3, it facilitates workflows that require cloud-based file storage. This tool is particularly useful for data persistence, configuration management, report generation, and any task that involves storing information in AWS S3 storage.
# Scrape Element From Website Tool
Source: https://docs.crewai.com/tools/scrapeelementfromwebsitetool
The `ScrapeElementFromWebsiteTool` enables CrewAI agents to extract specific elements from websites using CSS selectors.
# `ScrapeElementFromWebsiteTool`
## Description
The `ScrapeElementFromWebsiteTool` is designed to extract specific elements from websites using CSS selectors. This tool allows CrewAI agents to scrape targeted content from web pages, making it useful for data extraction tasks where only specific parts of a webpage are needed.
## Installation
To use this tool, you need to install the required dependencies:
```shell
uv add requests beautifulsoup4
```
## Steps to Get Started
To effectively use the `ScrapeElementFromWebsiteTool`, follow these steps:
1. **Install Dependencies**: Install the required packages using the command above.
2. **Identify CSS Selectors**: Determine the CSS selectors for the elements you want to extract from the website.
3. **Initialize the Tool**: Create an instance of the tool with the necessary parameters.
## Example
The following example demonstrates how to use the `ScrapeElementFromWebsiteTool` to extract specific elements from a website:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools import ScrapeElementFromWebsiteTool
# Initialize the tool
scrape_tool = ScrapeElementFromWebsiteTool()
# Define an agent that uses the tool
web_scraper_agent = Agent(
role="Web Scraper",
goal="Extract specific information from websites",
backstory="An expert in web scraping who can extract targeted content from web pages.",
tools=[scrape_tool],
verbose=True,
)
# Example task to extract headlines from a news website
scrape_task = Task(
description="Extract the main headlines from the CNN homepage. Use the CSS selector '.headline' to target the headline elements.",
expected_output="A list of the main headlines from CNN.",
agent=web_scraper_agent,
)
# Create and run the crew
crew = Crew(agents=[web_scraper_agent], tasks=[scrape_task])
result = crew.kickoff()
```
You can also initialize the tool with predefined parameters:
```python Code
# Initialize the tool with predefined parameters
scrape_tool = ScrapeElementFromWebsiteTool(
website_url="https://www.example.com",
css_element=".main-content"
)
```
## Parameters
The `ScrapeElementFromWebsiteTool` accepts the following parameters during initialization:
* **website\_url**: Optional. The URL of the website to scrape. If provided during initialization, the agent won't need to specify it when using the tool.
* **css\_element**: Optional. The CSS selector for the elements to extract. If provided during initialization, the agent won't need to specify it when using the tool.
* **cookies**: Optional. A dictionary containing cookies to be sent with the request. This can be useful for websites that require authentication.
## Usage
When using the `ScrapeElementFromWebsiteTool` with an agent, the agent will need to provide the following parameters (unless they were specified during initialization):
* **website\_url**: The URL of the website to scrape.
* **css\_element**: The CSS selector for the elements to extract.
The tool will return the text content of all elements matching the CSS selector, joined by newlines.
```python Code
# Example of using the tool with an agent
web_scraper_agent = Agent(
role="Web Scraper",
goal="Extract specific elements from websites",
backstory="An expert in web scraping who can extract targeted content using CSS selectors.",
tools=[scrape_tool],
verbose=True,
)
# Create a task for the agent to extract specific elements
extract_task = Task(
description="""
Extract all product titles from the featured products section on example.com.
Use the CSS selector '.product-title' to target the title elements.
""",
expected_output="A list of product titles from the website",
agent=web_scraper_agent,
)
# Run the task through a crew
crew = Crew(agents=[web_scraper_agent], tasks=[extract_task])
result = crew.kickoff()
```
## Implementation Details
The `ScrapeElementFromWebsiteTool` uses the `requests` library to fetch the web page and `BeautifulSoup` to parse the HTML and extract the specified elements:
```python Code
class ScrapeElementFromWebsiteTool(BaseTool):
name: str = "Read a website content"
description: str = "A tool that can be used to read a website content."
# Implementation details...
def _run(self, **kwargs: Any) -> Any:
website_url = kwargs.get("website_url", self.website_url)
css_element = kwargs.get("css_element", self.css_element)
page = requests.get(
website_url,
headers=self.headers,
cookies=self.cookies if self.cookies else {},
)
parsed = BeautifulSoup(page.content, "html.parser")
elements = parsed.select(css_element)
return "\n".join([element.get_text() for element in elements])
```
## Conclusion
The `ScrapeElementFromWebsiteTool` provides a powerful way to extract specific elements from websites using CSS selectors. By enabling agents to target only the content they need, it makes web scraping tasks more efficient and focused. This tool is particularly useful for data extraction, content monitoring, and research tasks where specific information needs to be extracted from web pages.
# Scrapegraph Scrape Tool
Source: https://docs.crewai.com/tools/scrapegraphscrapetool
The `ScrapegraphScrapeTool` leverages Scrapegraph AI's SmartScraper API to intelligently extract content from websites.
# `ScrapegraphScrapeTool`
## Description
The `ScrapegraphScrapeTool` is designed to leverage Scrapegraph AI's SmartScraper API to intelligently extract content from websites. This tool provides advanced web scraping capabilities with AI-powered content extraction, making it ideal for targeted data collection and content analysis tasks. Unlike traditional web scrapers, it can understand the context and structure of web pages to extract the most relevant information based on natural language prompts.
## Installation
To use this tool, you need to install the Scrapegraph Python client:
```shell
uv add scrapegraph-py
```
You'll also need to set up your Scrapegraph API key as an environment variable:
```shell
export SCRAPEGRAPH_API_KEY="your_api_key"
```
You can obtain an API key from [Scrapegraph AI](https://scrapegraphai.com).
## Steps to Get Started
To effectively use the `ScrapegraphScrapeTool`, follow these steps:
1. **Install Dependencies**: Install the required package using the command above.
2. **Set Up API Key**: Set your Scrapegraph API key as an environment variable or provide it during initialization.
3. **Initialize the Tool**: Create an instance of the tool with the necessary parameters.
4. **Define Extraction Prompts**: Create natural language prompts to guide the extraction of specific content.
## Example
The following example demonstrates how to use the `ScrapegraphScrapeTool` to extract content from a website:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools import ScrapegraphScrapeTool
# Initialize the tool
scrape_tool = ScrapegraphScrapeTool(api_key="your_api_key")
# Define an agent that uses the tool
web_scraper_agent = Agent(
role="Web Scraper",
goal="Extract specific information from websites",
backstory="An expert in web scraping who can extract targeted content from web pages.",
tools=[scrape_tool],
verbose=True,
)
# Example task to extract product information from an e-commerce site
scrape_task = Task(
description="Extract product names, prices, and descriptions from the featured products section of example.com.",
expected_output="A structured list of product information including names, prices, and descriptions.",
agent=web_scraper_agent,
)
# Create and run the crew
crew = Crew(agents=[web_scraper_agent], tasks=[scrape_task])
result = crew.kickoff()
```
You can also initialize the tool with predefined parameters:
```python Code
# Initialize the tool with predefined parameters
scrape_tool = ScrapegraphScrapeTool(
website_url="https://www.example.com",
user_prompt="Extract all product prices and descriptions",
api_key="your_api_key"
)
```
## Parameters
The `ScrapegraphScrapeTool` accepts the following parameters during initialization:
* **api\_key**: Optional. Your Scrapegraph API key. If not provided, it will look for the `SCRAPEGRAPH_API_KEY` environment variable.
* **website\_url**: Optional. The URL of the website to scrape. If provided during initialization, the agent won't need to specify it when using the tool.
* **user\_prompt**: Optional. Custom instructions for content extraction. If provided during initialization, the agent won't need to specify it when using the tool.
* **enable\_logging**: Optional. Whether to enable logging for the Scrapegraph client. Default is `False`.
## Usage
When using the `ScrapegraphScrapeTool` with an agent, the agent will need to provide the following parameters (unless they were specified during initialization):
* **website\_url**: The URL of the website to scrape.
* **user\_prompt**: Optional. Custom instructions for content extraction. Default is "Extract the main content of the webpage".
The tool will return the extracted content based on the provided prompt.
```python Code
# Example of using the tool with an agent
web_scraper_agent = Agent(
role="Web Scraper",
goal="Extract specific information from websites",
backstory="An expert in web scraping who can extract targeted content from web pages.",
tools=[scrape_tool],
verbose=True,
)
# Create a task for the agent to extract specific content
extract_task = Task(
description="Extract the main heading and summary from example.com",
expected_output="The main heading and summary from the website",
agent=web_scraper_agent,
)
# Run the task
crew = Crew(agents=[web_scraper_agent], tasks=[extract_task])
result = crew.kickoff()
```
## Error Handling
The `ScrapegraphScrapeTool` may raise the following exceptions:
* **ValueError**: When API key is missing or URL format is invalid.
* **RateLimitError**: When API rate limits are exceeded.
* **RuntimeError**: When scraping operation fails (network issues, API errors).
It's recommended to instruct agents to handle potential errors gracefully:
```python Code
# Create a task that includes error handling instructions
robust_extract_task = Task(
description="""
Extract the main heading from example.com.
Be aware that you might encounter errors such as:
- Invalid URL format
- Missing API key
- Rate limit exceeded
- Network or API errors
If you encounter any errors, provide a clear explanation of what went wrong
and suggest possible solutions.
""",
expected_output="Either the extracted heading or a clear error explanation",
agent=web_scraper_agent,
)
```
## Rate Limiting
The Scrapegraph API has rate limits that vary based on your subscription plan. Consider the following best practices:
* Implement appropriate delays between requests when processing multiple URLs.
* Handle rate limit errors gracefully in your application.
* Check your API plan limits on the Scrapegraph dashboard.
## Implementation Details
The `ScrapegraphScrapeTool` uses the Scrapegraph Python client to interact with the SmartScraper API:
```python Code
class ScrapegraphScrapeTool(BaseTool):
"""
A tool that uses Scrapegraph AI to intelligently scrape website content.
"""
# Implementation details...
def _run(self, **kwargs: Any) -> Any:
website_url = kwargs.get("website_url", self.website_url)
user_prompt = (
kwargs.get("user_prompt", self.user_prompt)
or "Extract the main content of the webpage"
)
if not website_url:
raise ValueError("website_url is required")
# Validate URL format
self._validate_url(website_url)
try:
# Make the SmartScraper request
response = self._client.smartscraper(
website_url=website_url,
user_prompt=user_prompt,
)
return response
# Error handling...
```
## Conclusion
The `ScrapegraphScrapeTool` provides a powerful way to extract content from websites using AI-powered understanding of web page structure. By enabling agents to target specific information using natural language prompts, it makes web scraping tasks more efficient and focused. This tool is particularly useful for data extraction, content monitoring, and research tasks where specific information needs to be extracted from web pages.
# Scrape Website
Source: https://docs.crewai.com/tools/scrapewebsitetool
The `ScrapeWebsiteTool` is designed to extract and read the content of a specified website.
# `ScrapeWebsiteTool`
We are still working on improving tools, so there might be unexpected behavior or changes in the future.
## Description
A tool designed to extract and read the content of a specified website. It is capable of handling various types of web pages by making HTTP requests and parsing the received HTML content.
This tool can be particularly useful for web scraping tasks, data collection, or extracting specific information from websites.
## Installation
Install the crewai\_tools package
```shell
pip install 'crewai[tools]'
```
## Example
```python
from crewai_tools import ScrapeWebsiteTool
# To enable scrapping any website it finds during it's execution
tool = ScrapeWebsiteTool()
# Initialize the tool with the website URL,
# so the agent can only scrap the content of the specified website
tool = ScrapeWebsiteTool(website_url='https://www.example.com')
# Extract the text from the site
text = tool.run()
print(text)
```
## Arguments
| Argument | Type | Description |
| :--------------- | :------- | :------------------------------------------------------------------------------------------------------------------------------------------------- |
| **website\_url** | `string` | **Mandatory** website URL to read the file. This is the primary input for the tool, specifying which website's content should be scraped and read. |
# Scrapfly Scrape Website Tool
Source: https://docs.crewai.com/tools/scrapflyscrapetool
The `ScrapflyScrapeWebsiteTool` leverages Scrapfly's web scraping API to extract content from websites in various formats.
# `ScrapflyScrapeWebsiteTool`
## Description
The `ScrapflyScrapeWebsiteTool` is designed to leverage [Scrapfly](https://scrapfly.io/)'s web scraping API to extract content from websites. This tool provides advanced web scraping capabilities with headless browser support, proxies, and anti-bot bypass features. It allows for extracting web page data in various formats, including raw HTML, markdown, and plain text, making it ideal for a wide range of web scraping tasks.
## Installation
To use this tool, you need to install the Scrapfly SDK:
```shell
uv add scrapfly-sdk
```
You'll also need to obtain a Scrapfly API key by registering at [scrapfly.io/register](https://www.scrapfly.io/register/).
## Steps to Get Started
To effectively use the `ScrapflyScrapeWebsiteTool`, follow these steps:
1. **Install Dependencies**: Install the Scrapfly SDK using the command above.
2. **Obtain API Key**: Register at Scrapfly to get your API key.
3. **Initialize the Tool**: Create an instance of the tool with your API key.
4. **Configure Scraping Parameters**: Customize the scraping parameters based on your needs.
## Example
The following example demonstrates how to use the `ScrapflyScrapeWebsiteTool` to extract content from a website:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools import ScrapflyScrapeWebsiteTool
# Initialize the tool
scrape_tool = ScrapflyScrapeWebsiteTool(api_key="your_scrapfly_api_key")
# Define an agent that uses the tool
web_scraper_agent = Agent(
role="Web Scraper",
goal="Extract information from websites",
backstory="An expert in web scraping who can extract content from any website.",
tools=[scrape_tool],
verbose=True,
)
# Example task to extract content from a website
scrape_task = Task(
description="Extract the main content from the product page at https://web-scraping.dev/products and summarize the available products.",
expected_output="A summary of the products available on the website.",
agent=web_scraper_agent,
)
# Create and run the crew
crew = Crew(agents=[web_scraper_agent], tasks=[scrape_task])
result = crew.kickoff()
```
You can also customize the scraping parameters:
```python Code
# Example with custom scraping parameters
web_scraper_agent = Agent(
role="Web Scraper",
goal="Extract information from websites with custom parameters",
backstory="An expert in web scraping who can extract content from any website.",
tools=[scrape_tool],
verbose=True,
)
# The agent will use the tool with parameters like:
# url="https://web-scraping.dev/products"
# scrape_format="markdown"
# ignore_scrape_failures=True
# scrape_config={
# "asp": True, # Bypass scraping blocking solutions, like Cloudflare
# "render_js": True, # Enable JavaScript rendering with a cloud headless browser
# "proxy_pool": "public_residential_pool", # Select a proxy pool
# "country": "us", # Select a proxy location
# "auto_scroll": True, # Auto scroll the page
# }
scrape_task = Task(
description="Extract the main content from the product page at https://web-scraping.dev/products using advanced scraping options including JavaScript rendering and proxy settings.",
expected_output="A detailed summary of the products with all available information.",
agent=web_scraper_agent,
)
```
## Parameters
The `ScrapflyScrapeWebsiteTool` accepts the following parameters:
### Initialization Parameters
* **api\_key**: Required. Your Scrapfly API key.
### Run Parameters
* **url**: Required. The URL of the website to scrape.
* **scrape\_format**: Optional. The format in which to extract the web page content. Options are "raw" (HTML), "markdown", or "text". Default is "markdown".
* **scrape\_config**: Optional. A dictionary containing additional Scrapfly scraping configuration options.
* **ignore\_scrape\_failures**: Optional. Whether to ignore failures during scraping. If set to `True`, the tool will return `None` instead of raising an exception when scraping fails.
## Scrapfly Configuration Options
The `scrape_config` parameter allows you to customize the scraping behavior with the following options:
* **asp**: Enable anti-scraping protection bypass.
* **render\_js**: Enable JavaScript rendering with a cloud headless browser.
* **proxy\_pool**: Select a proxy pool (e.g., "public\_residential\_pool", "datacenter").
* **country**: Select a proxy location (e.g., "us", "uk").
* **auto\_scroll**: Automatically scroll the page to load lazy-loaded content.
* **js**: Execute custom JavaScript code by the headless browser.
For a complete list of configuration options, refer to the [Scrapfly API documentation](https://scrapfly.io/docs/scrape-api/getting-started).
## Usage
When using the `ScrapflyScrapeWebsiteTool` with an agent, the agent will need to provide the URL of the website to scrape and can optionally specify the format and additional configuration options:
```python Code
# Example of using the tool with an agent
web_scraper_agent = Agent(
role="Web Scraper",
goal="Extract information from websites",
backstory="An expert in web scraping who can extract content from any website.",
tools=[scrape_tool],
verbose=True,
)
# Create a task for the agent
scrape_task = Task(
description="Extract the main content from example.com in markdown format.",
expected_output="The main content of example.com in markdown format.",
agent=web_scraper_agent,
)
# Run the task
crew = Crew(agents=[web_scraper_agent], tasks=[scrape_task])
result = crew.kickoff()
```
For more advanced usage with custom configuration:
```python Code
# Create a task with more specific instructions
advanced_scrape_task = Task(
description="""
Extract content from example.com with the following requirements:
- Convert the content to plain text format
- Enable JavaScript rendering
- Use a US-based proxy
- Handle any scraping failures gracefully
""",
expected_output="The extracted content from example.com",
agent=web_scraper_agent,
)
```
## Error Handling
By default, the `ScrapflyScrapeWebsiteTool` will raise an exception if scraping fails. Agents can be instructed to handle failures gracefully by specifying the `ignore_scrape_failures` parameter:
```python Code
# Create a task that instructs the agent to handle errors
error_handling_task = Task(
description="""
Extract content from a potentially problematic website and make sure to handle any
scraping failures gracefully by setting ignore_scrape_failures to True.
""",
expected_output="Either the extracted content or a graceful error message",
agent=web_scraper_agent,
)
```
## Implementation Details
The `ScrapflyScrapeWebsiteTool` uses the Scrapfly SDK to interact with the Scrapfly API:
```python Code
class ScrapflyScrapeWebsiteTool(BaseTool):
name: str = "Scrapfly web scraping API tool"
description: str = (
"Scrape a webpage url using Scrapfly and return its content as markdown or text"
)
# Implementation details...
def _run(
self,
url: str,
scrape_format: str = "markdown",
scrape_config: Optional[Dict[str, Any]] = None,
ignore_scrape_failures: Optional[bool] = None,
):
from scrapfly import ScrapeApiResponse, ScrapeConfig
scrape_config = scrape_config if scrape_config is not None else {}
try:
response: ScrapeApiResponse = self.scrapfly.scrape(
ScrapeConfig(url, format=scrape_format, **scrape_config)
)
return response.scrape_result["content"]
except Exception as e:
if ignore_scrape_failures:
logger.error(f"Error fetching data from {url}, exception: {e}")
return None
else:
raise e
```
## Conclusion
The `ScrapflyScrapeWebsiteTool` provides a powerful way to extract content from websites using Scrapfly's advanced web scraping capabilities. With features like headless browser support, proxies, and anti-bot bypass, it can handle complex websites and extract content in various formats. This tool is particularly useful for data extraction, content monitoring, and research tasks where reliable web scraping is required.
# Selenium Scraper
Source: https://docs.crewai.com/tools/seleniumscrapingtool
The `SeleniumScrapingTool` is designed to extract and read the content of a specified website using Selenium.
# `SeleniumScrapingTool`
This tool is currently in development. As we refine its capabilities, users may encounter unexpected behavior.
Your feedback is invaluable to us for making improvements.
## Description
The `SeleniumScrapingTool` is crafted for high-efficiency web scraping tasks.
It allows for precise extraction of content from web pages by using CSS selectors to target specific elements.
Its design caters to a wide range of scraping needs, offering flexibility to work with any provided website URL.
## Installation
To use this tool, you need to install the CrewAI tools package and Selenium:
```shell
pip install 'crewai[tools]'
uv add selenium webdriver-manager
```
You'll also need to have Chrome installed on your system, as the tool uses Chrome WebDriver for browser automation.
## Example
The following example demonstrates how to use the `SeleniumScrapingTool` with a CrewAI agent:
```python Code
from crewai import Agent, Task, Crew, Process
from crewai_tools import SeleniumScrapingTool
# Initialize the tool
selenium_tool = SeleniumScrapingTool()
# Define an agent that uses the tool
web_scraper_agent = Agent(
role="Web Scraper",
goal="Extract information from websites using Selenium",
backstory="An expert web scraper who can extract content from dynamic websites.",
tools=[selenium_tool],
verbose=True,
)
# Example task to scrape content from a website
scrape_task = Task(
description="Extract the main content from the homepage of example.com. Use the CSS selector 'main' to target the main content area.",
expected_output="The main content from example.com's homepage.",
agent=web_scraper_agent,
)
# Create and run the crew
crew = Crew(
agents=[web_scraper_agent],
tasks=[scrape_task],
verbose=True,
process=Process.sequential,
)
result = crew.kickoff()
```
You can also initialize the tool with predefined parameters:
```python Code
# Initialize the tool with predefined parameters
selenium_tool = SeleniumScrapingTool(
website_url='https://example.com',
css_element='.main-content',
wait_time=5
)
# Define an agent that uses the tool
web_scraper_agent = Agent(
role="Web Scraper",
goal="Extract information from websites using Selenium",
backstory="An expert web scraper who can extract content from dynamic websites.",
tools=[selenium_tool],
verbose=True,
)
```
## Parameters
The `SeleniumScrapingTool` accepts the following parameters during initialization:
* **website\_url**: Optional. The URL of the website to scrape. If provided during initialization, the agent won't need to specify it when using the tool.
* **css\_element**: Optional. The CSS selector for the elements to extract. If provided during initialization, the agent won't need to specify it when using the tool.
* **cookie**: Optional. A dictionary containing cookie information, useful for simulating a logged-in session to access restricted content.
* **wait\_time**: Optional. Specifies the delay (in seconds) before scraping, allowing the website and any dynamic content to fully load. Default is `3` seconds.
* **return\_html**: Optional. Whether to return the HTML content instead of just the text. Default is `False`.
When using the tool with an agent, the agent will need to provide the following parameters (unless they were specified during initialization):
* **website\_url**: Required. The URL of the website to scrape.
* **css\_element**: Required. The CSS selector for the elements to extract.
## Agent Integration Example
Here's a more detailed example of how to integrate the `SeleniumScrapingTool` with a CrewAI agent:
```python Code
from crewai import Agent, Task, Crew, Process
from crewai_tools import SeleniumScrapingTool
# Initialize the tool
selenium_tool = SeleniumScrapingTool()
# Define an agent that uses the tool
web_scraper_agent = Agent(
role="Web Scraper",
goal="Extract and analyze information from dynamic websites",
backstory="""You are an expert web scraper who specializes in extracting
content from dynamic websites that require browser automation. You have
extensive knowledge of CSS selectors and can identify the right selectors
to target specific content on any website.""",
tools=[selenium_tool],
verbose=True,
)
# Create a task for the agent
scrape_task = Task(
description="""
Extract the following information from the news website at {website_url}:
1. The headlines of all featured articles (CSS selector: '.headline')
2. The publication dates of these articles (CSS selector: '.pub-date')
3. The author names where available (CSS selector: '.author')
Compile this information into a structured format with each article's details grouped together.
""",
expected_output="A structured list of articles with their headlines, publication dates, and authors.",
agent=web_scraper_agent,
)
# Run the task
crew = Crew(
agents=[web_scraper_agent],
tasks=[scrape_task],
verbose=True,
process=Process.sequential,
)
result = crew.kickoff(inputs={"website_url": "https://news-example.com"})
```
## Implementation Details
The `SeleniumScrapingTool` uses Selenium WebDriver to automate browser interactions:
```python Code
class SeleniumScrapingTool(BaseTool):
name: str = "Read a website content"
description: str = "A tool that can be used to read a website content."
args_schema: Type[BaseModel] = SeleniumScrapingToolSchema
def _run(self, **kwargs: Any) -> Any:
website_url = kwargs.get("website_url", self.website_url)
css_element = kwargs.get("css_element", self.css_element)
return_html = kwargs.get("return_html", self.return_html)
driver = self._create_driver(website_url, self.cookie, self.wait_time)
content = self._get_content(driver, css_element, return_html)
driver.close()
return "\n".join(content)
```
The tool performs the following steps:
1. Creates a headless Chrome browser instance
2. Navigates to the specified URL
3. Waits for the specified time to allow the page to load
4. Adds any cookies if provided
5. Extracts content based on the CSS selector
6. Returns the extracted content as text or HTML
7. Closes the browser instance
## Handling Dynamic Content
The `SeleniumScrapingTool` is particularly useful for scraping websites with dynamic content that is loaded via JavaScript. By using a real browser instance, it can:
1. Execute JavaScript on the page
2. Wait for dynamic content to load
3. Interact with elements if needed
4. Extract content that would not be available with simple HTTP requests
You can adjust the `wait_time` parameter to ensure that all dynamic content has loaded before extraction.
## Conclusion
The `SeleniumScrapingTool` provides a powerful way to extract content from websites using browser automation. By enabling agents to interact with websites as a real user would, it facilitates scraping of dynamic content that would be difficult or impossible to extract using simpler methods. This tool is particularly useful for research, data collection, and monitoring tasks that involve modern web applications with JavaScript-rendered content.
# Google Serper Search
Source: https://docs.crewai.com/tools/serperdevtool
The `SerperDevTool` is designed to search the internet and return the most relevant results.
# `SerperDevTool`
We are still working on improving tools, so there might be unexpected behavior or changes in the future.
## Description
This tool is designed to perform a semantic search for a specified query from a text's content across the internet. It utilizes the [serper.dev](https://serper.dev) API
to fetch and display the most relevant search results based on the query provided by the user.
## Installation
To incorporate this tool into your project, follow the installation instructions below:
```shell
pip install 'crewai[tools]'
```
## Example
The following example demonstrates how to initialize the tool and execute a search with a given query:
```python Code
from crewai_tools import SerperDevTool
# Initialize the tool for internet searching capabilities
tool = SerperDevTool()
```
## Steps to Get Started
To effectively use the `SerperDevTool`, follow these steps:
1. **Package Installation**: Confirm that the `crewai[tools]` package is installed in your Python environment.
2. **API Key Acquisition**: Acquire a `serper.dev` API key by registering for a free account at `serper.dev`.
3. **Environment Configuration**: Store your obtained API key in an environment variable named `SERPER_API_KEY` to facilitate its use by the tool.
## Parameters
The `SerperDevTool` comes with several parameters that will be passed to the API :
* **search\_url**: The URL endpoint for the search API. (Default is `https://google.serper.dev/search`)
* **country**: Optional. Specify the country for the search results.
* **location**: Optional. Specify the location for the search results.
* **locale**: Optional. Specify the locale for the search results.
* **n\_results**: Number of search results to return. Default is `10`.
The values for `country`, `location`, `locale` and `search_url` can be found on the [Serper Playground](https://serper.dev/playground).
## Example with Parameters
Here is an example demonstrating how to use the tool with additional parameters:
```python Code
from crewai_tools import SerperDevTool
tool = SerperDevTool(
search_url="https://google.serper.dev/scholar",
n_results=2,
)
print(tool.run(search_query="ChatGPT"))
# Using Tool: Search the internet
# Search results: Title: Role of chat gpt in public health
# Link: https://link.springer.com/article/10.1007/s10439-023-03172-7
# Snippet: … ChatGPT in public health. In this overview, we will examine the potential uses of ChatGPT in
# ---
# Title: Potential use of chat gpt in global warming
# Link: https://link.springer.com/article/10.1007/s10439-023-03171-8
# Snippet: … as ChatGPT, have the potential to play a critical role in advancing our understanding of climate
# ---
```
```python Code
from crewai_tools import SerperDevTool
tool = SerperDevTool(
country="fr",
locale="fr",
location="Paris, Paris, Ile-de-France, France",
n_results=2,
)
print(tool.run(search_query="Jeux Olympiques"))
# Using Tool: Search the internet
# Search results: Title: Jeux Olympiques de Paris 2024 - Actualités, calendriers, résultats
# Link: https://olympics.com/fr/paris-2024
# Snippet: Quels sont les sports présents aux Jeux Olympiques de Paris 2024 ? · Athlétisme · Aviron · Badminton · Basketball · Basketball 3x3 · Boxe · Breaking · Canoë ...
# ---
# Title: Billetterie Officielle de Paris 2024 - Jeux Olympiques et Paralympiques
# Link: https://tickets.paris2024.org/
# Snippet: Achetez vos billets exclusivement sur le site officiel de la billetterie de Paris 2024 pour participer au plus grand événement sportif au monde.
# ---
```
## Conclusion
By integrating the `SerperDevTool` into Python projects, users gain the ability to conduct real-time, relevant searches across the internet directly from their applications.
The updated parameters allow for more customized and localized search results. By adhering to the setup and usage guidelines provided, incorporating this tool into projects is streamlined and straightforward.
# Snowflake Search Tool
Source: https://docs.crewai.com/tools/snowflakesearchtool
The `SnowflakeSearchTool` enables CrewAI agents to execute SQL queries and perform semantic search on Snowflake data warehouses.
# `SnowflakeSearchTool`
## Description
The `SnowflakeSearchTool` is designed to connect to Snowflake data warehouses and execute SQL queries with advanced features like connection pooling, retry logic, and asynchronous execution. This tool allows CrewAI agents to interact with Snowflake databases, making it ideal for data analysis, reporting, and business intelligence tasks that require access to enterprise data stored in Snowflake.
## Installation
To use this tool, you need to install the required dependencies:
```shell
uv add cryptography snowflake-connector-python snowflake-sqlalchemy
```
Or alternatively:
```shell
uv sync --extra snowflake
```
## Steps to Get Started
To effectively use the `SnowflakeSearchTool`, follow these steps:
1. **Install Dependencies**: Install the required packages using one of the commands above.
2. **Configure Snowflake Connection**: Create a `SnowflakeConfig` object with your Snowflake credentials.
3. **Initialize the Tool**: Create an instance of the tool with the necessary configuration.
4. **Execute Queries**: Use the tool to run SQL queries against your Snowflake database.
## Example
The following example demonstrates how to use the `SnowflakeSearchTool` to query data from a Snowflake database:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools import SnowflakeSearchTool, SnowflakeConfig
# Create Snowflake configuration
config = SnowflakeConfig(
account="your_account",
user="your_username",
password="your_password",
warehouse="COMPUTE_WH",
database="your_database",
snowflake_schema="your_schema"
)
# Initialize the tool
snowflake_tool = SnowflakeSearchTool(config=config)
# Define an agent that uses the tool
data_analyst_agent = Agent(
role="Data Analyst",
goal="Analyze data from Snowflake database",
backstory="An expert data analyst who can extract insights from enterprise data.",
tools=[snowflake_tool],
verbose=True,
)
# Example task to query sales data
query_task = Task(
description="Query the sales data for the last quarter and summarize the top 5 products by revenue.",
expected_output="A summary of the top 5 products by revenue for the last quarter.",
agent=data_analyst_agent,
)
# Create and run the crew
crew = Crew(agents=[data_analyst_agent],
tasks=[query_task])
result = crew.kickoff()
```
You can also customize the tool with additional parameters:
```python Code
# Initialize the tool with custom parameters
snowflake_tool = SnowflakeSearchTool(
config=config,
pool_size=10,
max_retries=5,
retry_delay=2.0,
enable_caching=True
)
```
## Parameters
### SnowflakeConfig Parameters
The `SnowflakeConfig` class accepts the following parameters:
* **account**: Required. Snowflake account identifier.
* **user**: Required. Snowflake username.
* **password**: Optional\*. Snowflake password.
* **private\_key\_path**: Optional\*. Path to private key file (alternative to password).
* **warehouse**: Required. Snowflake warehouse name.
* **database**: Required. Default database.
* **snowflake\_schema**: Required. Default schema.
* **role**: Optional. Snowflake role.
* **session\_parameters**: Optional. Custom session parameters as a dictionary.
\*Either `password` or `private_key_path` must be provided.
### SnowflakeSearchTool Parameters
The `SnowflakeSearchTool` accepts the following parameters during initialization:
* **config**: Required. A `SnowflakeConfig` object containing connection details.
* **pool\_size**: Optional. Number of connections in the pool. Default is 5.
* **max\_retries**: Optional. Maximum retry attempts for failed queries. Default is 3.
* **retry\_delay**: Optional. Delay between retries in seconds. Default is 1.0.
* **enable\_caching**: Optional. Whether to enable query result caching. Default is True.
## Usage
When using the `SnowflakeSearchTool`, you need to provide the following parameters:
* **query**: Required. The SQL query to execute.
* **database**: Optional. Override the default database specified in the config.
* **snowflake\_schema**: Optional. Override the default schema specified in the config.
* **timeout**: Optional. Query timeout in seconds. Default is 300.
The tool will return the query results as a list of dictionaries, where each dictionary represents a row with column names as keys.
```python Code
# Example of using the tool with an agent
data_analyst = Agent(
role="Data Analyst",
goal="Analyze sales data from Snowflake",
backstory="An expert data analyst with experience in SQL and data visualization.",
tools=[snowflake_tool],
verbose=True
)
# The agent will use the tool with parameters like:
# query="SELECT product_name, SUM(revenue) as total_revenue FROM sales GROUP BY product_name ORDER BY total_revenue DESC LIMIT 5"
# timeout=600
# Create a task for the agent
analysis_task = Task(
description="Query the sales database and identify the top 5 products by revenue for the last quarter.",
expected_output="A detailed analysis of the top 5 products by revenue.",
agent=data_analyst
)
# Run the task
crew = Crew(
agents=[data_analyst],
tasks=[analysis_task]
)
result = crew.kickoff()
```
## Advanced Features
### Connection Pooling
The `SnowflakeSearchTool` implements connection pooling to improve performance by reusing database connections. You can control the pool size with the `pool_size` parameter.
### Automatic Retries
The tool automatically retries failed queries with exponential backoff. You can configure the retry behavior with the `max_retries` and `retry_delay` parameters.
### Query Result Caching
To improve performance for repeated queries, the tool can cache query results. This feature is enabled by default but can be disabled by setting `enable_caching=False`.
### Key-Pair Authentication
In addition to password authentication, the tool supports key-pair authentication for enhanced security:
```python Code
config = SnowflakeConfig(
account="your_account",
user="your_username",
private_key_path="/path/to/your/private/key.p8",
warehouse="COMPUTE_WH",
database="your_database",
snowflake_schema="your_schema"
)
```
## Error Handling
The `SnowflakeSearchTool` includes comprehensive error handling for common Snowflake issues:
* Connection failures
* Query timeouts
* Authentication errors
* Database and schema errors
When an error occurs, the tool will attempt to retry the operation (if configured) and provide detailed error information.
## Conclusion
The `SnowflakeSearchTool` provides a powerful way to integrate Snowflake data warehouses with CrewAI agents. With features like connection pooling, automatic retries, and query caching, it enables efficient and reliable access to enterprise data. This tool is particularly useful for data analysis, reporting, and business intelligence tasks that require access to structured data stored in Snowflake.
# Spider Scraper
Source: https://docs.crewai.com/tools/spidertool
The `SpiderTool` is designed to extract and read the content of a specified website using Spider.
# `SpiderTool`
## Description
[Spider](https://spider.cloud/?ref=crewai) is the [fastest](https://github.com/spider-rs/spider/blob/main/benches/BENCHMARKS.md#benchmark-results)
open source scraper and crawler that returns LLM-ready data.
It converts any website into pure HTML, markdown, metadata or text while enabling you to crawl with custom actions using AI.
## Installation
To use the `SpiderTool` you need to download the [Spider SDK](https://pypi.org/project/spider-client/)
and the `crewai[tools]` SDK too:
```shell
pip install spider-client 'crewai[tools]'
```
## Example
This example shows you how you can use the `SpiderTool` to enable your agent to scrape and crawl websites.
The data returned from the Spider API is already LLM-ready, so no need to do any cleaning there.
```python Code
from crewai_tools import SpiderTool
def main():
spider_tool = SpiderTool()
searcher = Agent(
role="Web Research Expert",
goal="Find related information from specific URL's",
backstory="An expert web researcher that uses the web extremely well",
tools=[spider_tool],
verbose=True,
)
return_metadata = Task(
description="Scrape https://spider.cloud with a limit of 1 and enable metadata",
expected_output="Metadata and 10 word summary of spider.cloud",
agent=searcher
)
crew = Crew(
agents=[searcher],
tasks=[
return_metadata,
],
verbose=2
)
crew.kickoff()
if __name__ == "__main__":
main()
```
## Arguments
| Argument | Type | Description |
| :---------------------- | :------- | :-------------------------------------------------------------------------------------------------------------------------------- |
| **api\_key** | `string` | Specifies Spider API key. If not specified, it looks for `SPIDER_API_KEY` in environment variables. |
| **params** | `object` | Optional parameters for the request. Defaults to `{"return_format": "markdown"}` to optimize content for LLMs. |
| **request** | `string` | Type of request to perform (`http`, `chrome`, `smart`). `smart` defaults to HTTP, switching to JavaScript rendering if needed. |
| **limit** | `int` | Max pages to crawl per website. Set to `0` or omit for unlimited. |
| **depth** | `int` | Max crawl depth. Set to `0` for no limit. |
| **cache** | `bool` | Enables HTTP caching to speed up repeated runs. Default is `true`. |
| **budget** | `object` | Sets path-based limits for crawled pages, e.g., `{"*":1}` for root page only. |
| **locale** | `string` | Locale for the request, e.g., `en-US`. |
| **cookies** | `string` | HTTP cookies for the request. |
| **stealth** | `bool` | Enables stealth mode for Chrome requests to avoid detection. Default is `true`. |
| **headers** | `object` | HTTP headers as a map of key-value pairs for all requests. |
| **metadata** | `bool` | Stores metadata about pages and content, aiding AI interoperability. Defaults to `false`. |
| **viewport** | `object` | Sets Chrome viewport dimensions. Default is `800x600`. |
| **encoding** | `string` | Specifies encoding type, e.g., `UTF-8`, `SHIFT_JIS`. |
| **subdomains** | `bool` | Includes subdomains in the crawl. Default is `false`. |
| **user\_agent** | `string` | Custom HTTP user agent. Defaults to a random agent. |
| **store\_data** | `bool` | Enables data storage for the request. Overrides `storageless` when set. Default is `false`. |
| **gpt\_config** | `object` | Allows AI to generate crawl actions, with optional chaining steps via an array for `"prompt"`. |
| **fingerprint** | `bool` | Enables advanced fingerprinting for Chrome. |
| **storageless** | `bool` | Prevents all data storage, including AI embeddings. Default is `false`. |
| **readability** | `bool` | Pre-processes content for reading via [Mozilla’s readability](https://github.com/mozilla/readability). Improves content for LLMs. |
| **return\_format** | `string` | Format to return data: `markdown`, `raw`, `text`, `html2text`. Use `raw` for default page format. |
| **proxy\_enabled** | `bool` | Enables high-performance proxies to avoid network-level blocking. |
| **query\_selector** | `string` | CSS query selector for content extraction from markup. |
| **full\_resources** | `bool` | Downloads all resources linked to the website. |
| **request\_timeout** | `int` | Timeout in seconds for requests (5-60). Default is `30`. |
| **run\_in\_background** | `bool` | Runs the request in the background, useful for data storage and triggering dashboard crawls. No effect if `storageless` is set. |
# TXT RAG Search
Source: https://docs.crewai.com/tools/txtsearchtool
The `TXTSearchTool` is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a text file.
# `TXTSearchTool`
We are still working on improving tools, so there might be unexpected behavior or changes in the future.
## Description
This tool is used to perform a RAG (Retrieval-Augmented Generation) search within the content of a text file.
It allows for semantic searching of a query within a specified text file's content,
making it an invaluable resource for quickly extracting information or finding specific sections of text based on the query provided.
## Installation
To use the `TXTSearchTool`, you first need to install the `crewai_tools` package.
This can be done using pip, a package manager for Python.
Open your terminal or command prompt and enter the following command:
```shell
pip install 'crewai[tools]'
```
This command will download and install the TXTSearchTool along with any necessary dependencies.
## Example
The following example demonstrates how to use the TXTSearchTool to search within a text file.
This example shows both the initialization of the tool with a specific text file and the subsequent search within that file's content.
```python Code
from crewai_tools import TXTSearchTool
# Initialize the tool to search within any text file's content
# the agent learns about during its execution
tool = TXTSearchTool()
# OR
# Initialize the tool with a specific text file,
# so the agent can search within the given text file's content
tool = TXTSearchTool(txt='path/to/text/file.txt')
```
## Arguments
* `txt` (str): **Optional**. The path to the text file you want to search.
This argument is only required if the tool was not initialized with a specific text file;
otherwise, the search will be conducted within the initially provided text file.
## Custom model and embeddings
By default, the tool uses OpenAI for both embeddings and summarization.
To customize the model, you can use a config dictionary as follows:
```python Code
tool = TXTSearchTool(
config=dict(
llm=dict(
provider="ollama", # or google, openai, anthropic, llama2, ...
config=dict(
model="llama2",
# temperature=0.5,
# top_p=1,
# stream=true,
),
),
embedder=dict(
provider="google", # or openai, ollama, ...
config=dict(
model="models/embedding-001",
task_type="retrieval_document",
# title="Embeddings",
),
),
)
)
```
# Vision Tool
Source: https://docs.crewai.com/tools/visiontool
The `VisionTool` is designed to extract text from images.
# `VisionTool`
## Description
This tool is used to extract text from images. When passed to the agent it will extract the text from the image and then use it to generate a response, report or any other output.
The URL or the PATH of the image should be passed to the Agent.
## Installation
Install the crewai\_tools package
```shell
pip install 'crewai[tools]'
```
## Usage
In order to use the VisionTool, the OpenAI API key should be set in the environment variable `OPENAI_API_KEY`.
```python Code
from crewai_tools import VisionTool
vision_tool = VisionTool()
@agent
def researcher(self) -> Agent:
'''
This agent uses the VisionTool to extract text from images.
'''
return Agent(
config=self.agents_config["researcher"],
allow_delegation=False,
tools=[vision_tool]
)
```
## Arguments
The VisionTool requires the following arguments:
| Argument | Type | Description |
| :------------------- | :------- | :------------------------------------------------------------------------------- |
| **image\_path\_url** | `string` | **Mandatory**. The path to the image file from which text needs to be extracted. |
# Weaviate Vector Search
Source: https://docs.crewai.com/tools/weaviatevectorsearchtool
The `WeaviateVectorSearchTool` is designed to search a Weaviate vector database for semantically similar documents.
# `WeaviateVectorSearchTool`
## Description
The `WeaviateVectorSearchTool` is specifically crafted for conducting semantic searches within documents stored in a Weaviate vector database. This tool allows you to find semantically similar documents to a given query, leveraging the power of vector embeddings for more accurate and contextually relevant search results.
[Weaviate](https://weaviate.io/) is a vector database that stores and queries vector embeddings, enabling semantic search capabilities.
## Installation
To incorporate this tool into your project, you need to install the Weaviate client:
```shell
uv add weaviate-client
```
## Steps to Get Started
To effectively use the `WeaviateVectorSearchTool`, follow these steps:
1. **Package Installation**: Confirm that the `crewai[tools]` and `weaviate-client` packages are installed in your Python environment.
2. **Weaviate Setup**: Set up a Weaviate cluster. You can follow the [Weaviate documentation](https://weaviate.io/developers/wcs/manage-clusters/connect) for instructions.
3. **API Keys**: Obtain your Weaviate cluster URL and API key.
4. **OpenAI API Key**: Ensure you have an OpenAI API key set in your environment variables as `OPENAI_API_KEY`.
## Example
The following example demonstrates how to initialize the tool and execute a search:
```python Code
from crewai_tools import WeaviateVectorSearchTool
# Initialize the tool
tool = WeaviateVectorSearchTool(
collection_name='example_collections',
limit=3,
weaviate_cluster_url="https://your-weaviate-cluster-url.com",
weaviate_api_key="your-weaviate-api-key",
)
@agent
def search_agent(self) -> Agent:
'''
This agent uses the WeaviateVectorSearchTool to search for
semantically similar documents in a Weaviate vector database.
'''
return Agent(
config=self.agents_config["search_agent"],
tools=[tool]
)
```
## Parameters
The `WeaviateVectorSearchTool` accepts the following parameters:
* **collection\_name**: Required. The name of the collection to search within.
* **weaviate\_cluster\_url**: Required. The URL of the Weaviate cluster.
* **weaviate\_api\_key**: Required. The API key for the Weaviate cluster.
* **limit**: Optional. The number of results to return. Default is `3`.
* **vectorizer**: Optional. The vectorizer to use. If not provided, it will use `text2vec_openai` with the `nomic-embed-text` model.
* **generative\_model**: Optional. The generative model to use. If not provided, it will use OpenAI's `gpt-4o`.
## Advanced Configuration
You can customize the vectorizer and generative model used by the tool:
```python Code
from crewai_tools import WeaviateVectorSearchTool
from weaviate.classes.config import Configure
# Setup custom model for vectorizer and generative model
tool = WeaviateVectorSearchTool(
collection_name='example_collections',
limit=3,
vectorizer=Configure.Vectorizer.text2vec_openai(model="nomic-embed-text"),
generative_model=Configure.Generative.openai(model="gpt-4o-mini"),
weaviate_cluster_url="https://your-weaviate-cluster-url.com",
weaviate_api_key="your-weaviate-api-key",
)
```
## Preloading Documents
You can preload your Weaviate database with documents before using the tool:
```python Code
import os
from crewai_tools import WeaviateVectorSearchTool
import weaviate
from weaviate.classes.init import Auth
# Connect to Weaviate
client = weaviate.connect_to_weaviate_cloud(
cluster_url="https://your-weaviate-cluster-url.com",
auth_credentials=Auth.api_key("your-weaviate-api-key"),
headers={"X-OpenAI-Api-Key": "your-openai-api-key"}
)
# Get or create collection
test_docs = client.collections.get("example_collections")
if not test_docs:
test_docs = client.collections.create(
name="example_collections",
vectorizer_config=Configure.Vectorizer.text2vec_openai(model="nomic-embed-text"),
generative_config=Configure.Generative.openai(model="gpt-4o"),
)
# Load documents
docs_to_load = os.listdir("knowledge")
with test_docs.batch.dynamic() as batch:
for d in docs_to_load:
with open(os.path.join("knowledge", d), "r") as f:
content = f.read()
batch.add_object(
{
"content": content,
"year": d.split("_")[0],
}
)
# Initialize the tool
tool = WeaviateVectorSearchTool(
collection_name='example_collections',
limit=3,
weaviate_cluster_url="https://your-weaviate-cluster-url.com",
weaviate_api_key="your-weaviate-api-key",
)
```
## Agent Integration Example
Here's how to integrate the `WeaviateVectorSearchTool` with a CrewAI agent:
```python Code
from crewai import Agent
from crewai_tools import WeaviateVectorSearchTool
# Initialize the tool
weaviate_tool = WeaviateVectorSearchTool(
collection_name='example_collections',
limit=3,
weaviate_cluster_url="https://your-weaviate-cluster-url.com",
weaviate_api_key="your-weaviate-api-key",
)
# Create an agent with the tool
rag_agent = Agent(
name="rag_agent",
role="You are a helpful assistant that can answer questions with the help of the WeaviateVectorSearchTool.",
llm="gpt-4o-mini",
tools=[weaviate_tool],
)
```
## Conclusion
The `WeaviateVectorSearchTool` provides a powerful way to search for semantically similar documents in a Weaviate vector database. By leveraging vector embeddings, it enables more accurate and contextually relevant search results compared to traditional keyword-based searches. This tool is particularly useful for applications that require finding information based on meaning rather than exact matches.
# Website RAG Search
Source: https://docs.crewai.com/tools/websitesearchtool
The `WebsiteSearchTool` is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a website.
# `WebsiteSearchTool`
The WebsiteSearchTool is currently in an experimental phase. We are actively working on incorporating this tool into our suite of offerings and will update the documentation accordingly.
## Description
The WebsiteSearchTool is designed as a concept for conducting semantic searches within the content of websites.
It aims to leverage advanced machine learning models like Retrieval-Augmented Generation (RAG) to navigate and extract information from specified URLs efficiently.
This tool intends to offer flexibility, allowing users to perform searches across any website or focus on specific websites of interest.
Please note, the current implementation details of the WebsiteSearchTool are under development, and its functionalities as described may not yet be accessible.
## Installation
To prepare your environment for when the WebsiteSearchTool becomes available, you can install the foundational package with:
```shell
pip install 'crewai[tools]'
```
This command installs the necessary dependencies to ensure that once the tool is fully integrated, users can start using it immediately.
## Example Usage
Below are examples of how the WebsiteSearchTool could be utilized in different scenarios. Please note, these examples are illustrative and represent planned functionality:
```python Code
from crewai_tools import WebsiteSearchTool
# Example of initiating tool that agents can use
# to search across any discovered websites
tool = WebsiteSearchTool()
# Example of limiting the search to the content of a specific website,
# so now agents can only search within that website
tool = WebsiteSearchTool(website='https://example.com')
```
## Arguments
* `website`: An optional argument intended to specify the website URL for focused searches. This argument is designed to enhance the tool's flexibility by allowing targeted searches when necessary.
## Customization Options
By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
```python Code
tool = WebsiteSearchTool(
config=dict(
llm=dict(
provider="ollama", # or google, openai, anthropic, llama2, ...
config=dict(
model="llama2",
# temperature=0.5,
# top_p=1,
# stream=true,
),
),
embedder=dict(
provider="google", # or openai, ollama, ...
config=dict(
model="models/embedding-001",
task_type="retrieval_document",
# title="Embeddings",
),
),
)
)
```
# XML RAG Search
Source: https://docs.crewai.com/tools/xmlsearchtool
The `XMLSearchTool` is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a XML file.
# `XMLSearchTool`
We are still working on improving tools, so there might be unexpected behavior or changes in the future.
## Description
The XMLSearchTool is a cutting-edge RAG tool engineered for conducting semantic searches within XML files.
Ideal for users needing to parse and extract information from XML content efficiently, this tool supports inputting a search query and an optional XML file path.
By specifying an XML path, users can target their search more precisely to the content of that file, thereby obtaining more relevant search outcomes.
## Installation
To start using the XMLSearchTool, you must first install the crewai\_tools package. This can be easily done with the following command:
```shell
pip install 'crewai[tools]'
```
## Example
Here are two examples demonstrating how to use the XMLSearchTool.
The first example shows searching within a specific XML file, while the second example illustrates initiating a search without predefining an XML path, providing flexibility in search scope.
```python Code
from crewai_tools import XMLSearchTool
# Allow agents to search within any XML file's content
#as it learns about their paths during execution
tool = XMLSearchTool()
# OR
# Initialize the tool with a specific XML file path
#for exclusive search within that document
tool = XMLSearchTool(xml='path/to/your/xmlfile.xml')
```
## Arguments
* `xml`: This is the path to the XML file you wish to search.
It is an optional parameter during the tool's initialization but must be provided either at initialization or as part of the `run` method's arguments to execute a search.
## Custom model and embeddings
By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
```python Code
tool = XMLSearchTool(
config=dict(
llm=dict(
provider="ollama", # or google, openai, anthropic, llama2, ...
config=dict(
model="llama2",
# temperature=0.5,
# top_p=1,
# stream=true,
),
),
embedder=dict(
provider="google", # or openai, ollama, ...
config=dict(
model="models/embedding-001",
task_type="retrieval_document",
# title="Embeddings",
),
),
)
)
```
# YouTube Channel RAG Search
Source: https://docs.crewai.com/tools/youtubechannelsearchtool
The `YoutubeChannelSearchTool` is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a Youtube channel.
# `YoutubeChannelSearchTool`
We are still working on improving tools, so there might be unexpected behavior or changes in the future.
## Description
This tool is designed to perform semantic searches within a specific Youtube channel's content.
Leveraging the RAG (Retrieval-Augmented Generation) methodology, it provides relevant search results,
making it invaluable for extracting information or finding specific content without the need to manually sift through videos.
It streamlines the search process within Youtube channels, catering to researchers, content creators, and viewers seeking specific information or topics.
## Installation
To utilize the YoutubeChannelSearchTool, the `crewai_tools` package must be installed. Execute the following command in your shell to install:
```shell
pip install 'crewai[tools]'
```
## Example
The following example demonstrates how to use the `YoutubeChannelSearchTool` with a CrewAI agent:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools import YoutubeChannelSearchTool
# Initialize the tool for general YouTube channel searches
youtube_channel_tool = YoutubeChannelSearchTool()
# Define an agent that uses the tool
channel_researcher = Agent(
role="Channel Researcher",
goal="Extract relevant information from YouTube channels",
backstory="An expert researcher who specializes in analyzing YouTube channel content.",
tools=[youtube_channel_tool],
verbose=True,
)
# Example task to search for information in a specific channel
research_task = Task(
description="Search for information about machine learning tutorials in the YouTube channel {youtube_channel_handle}",
expected_output="A summary of the key machine learning tutorials available on the channel.",
agent=channel_researcher,
)
# Create and run the crew
crew = Crew(agents=[channel_researcher], tasks=[research_task])
result = crew.kickoff(inputs={"youtube_channel_handle": "@exampleChannel"})
```
You can also initialize the tool with a specific YouTube channel handle:
```python Code
# Initialize the tool with a specific YouTube channel handle
youtube_channel_tool = YoutubeChannelSearchTool(
youtube_channel_handle='@exampleChannel'
)
# Define an agent that uses the tool
channel_researcher = Agent(
role="Channel Researcher",
goal="Extract relevant information from a specific YouTube channel",
backstory="An expert researcher who specializes in analyzing YouTube channel content.",
tools=[youtube_channel_tool],
verbose=True,
)
```
## Parameters
The `YoutubeChannelSearchTool` accepts the following parameters:
* **youtube\_channel\_handle**: Optional. The handle of the YouTube channel to search within. If provided during initialization, the agent won't need to specify it when using the tool. If the handle doesn't start with '@', it will be automatically added.
* **config**: Optional. Configuration for the underlying RAG system, including LLM and embedder settings.
* **summarize**: Optional. Whether to summarize the retrieved content. Default is `False`.
When using the tool with an agent, the agent will need to provide:
* **search\_query**: Required. The search query to find relevant information in the channel content.
* **youtube\_channel\_handle**: Required only if not provided during initialization. The handle of the YouTube channel to search within.
## Custom Model and Embeddings
By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
```python Code
youtube_channel_tool = YoutubeChannelSearchTool(
config=dict(
llm=dict(
provider="ollama", # or google, openai, anthropic, llama2, ...
config=dict(
model="llama2",
# temperature=0.5,
# top_p=1,
# stream=true,
),
),
embedder=dict(
provider="google", # or openai, ollama, ...
config=dict(
model="models/embedding-001",
task_type="retrieval_document",
# title="Embeddings",
),
),
)
)
```
## Agent Integration Example
Here's a more detailed example of how to integrate the `YoutubeChannelSearchTool` with a CrewAI agent:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools import YoutubeChannelSearchTool
# Initialize the tool
youtube_channel_tool = YoutubeChannelSearchTool()
# Define an agent that uses the tool
channel_researcher = Agent(
role="Channel Researcher",
goal="Extract and analyze information from YouTube channels",
backstory="""You are an expert channel researcher who specializes in extracting
and analyzing information from YouTube channels. You have a keen eye for detail
and can quickly identify key points and insights from video content across an entire channel.""",
tools=[youtube_channel_tool],
verbose=True,
)
# Create a task for the agent
research_task = Task(
description="""
Search for information about data science projects and tutorials
in the YouTube channel {youtube_channel_handle}.
Focus on:
1. Key data science techniques covered
2. Popular tutorial series
3. Most viewed or recommended videos
Provide a comprehensive summary of these points.
""",
expected_output="A detailed summary of data science content available on the channel.",
agent=channel_researcher,
)
# Run the task
crew = Crew(agents=[channel_researcher], tasks=[research_task])
result = crew.kickoff(inputs={"youtube_channel_handle": "@exampleDataScienceChannel"})
```
## Implementation Details
The `YoutubeChannelSearchTool` is implemented as a subclass of `RagTool`, which provides the base functionality for Retrieval-Augmented Generation:
```python Code
class YoutubeChannelSearchTool(RagTool):
name: str = "Search a Youtube Channels content"
description: str = "A tool that can be used to semantic search a query from a Youtube Channels content."
args_schema: Type[BaseModel] = YoutubeChannelSearchToolSchema
def __init__(self, youtube_channel_handle: Optional[str] = None, **kwargs):
super().__init__(**kwargs)
if youtube_channel_handle is not None:
kwargs["data_type"] = DataType.YOUTUBE_CHANNEL
self.add(youtube_channel_handle)
self.description = f"A tool that can be used to semantic search a query the {youtube_channel_handle} Youtube Channels content."
self.args_schema = FixedYoutubeChannelSearchToolSchema
self._generate_description()
def add(
self,
youtube_channel_handle: str,
**kwargs: Any,
) -> None:
if not youtube_channel_handle.startswith("@"):
youtube_channel_handle = f"@{youtube_channel_handle}"
super().add(youtube_channel_handle, **kwargs)
```
## Conclusion
The `YoutubeChannelSearchTool` provides a powerful way to search and extract information from YouTube channel content using RAG techniques. By enabling agents to search across an entire channel's videos, it facilitates information extraction and analysis tasks that would otherwise be difficult to perform. This tool is particularly useful for research, content analysis, and knowledge extraction from YouTube channels.
# YouTube Video RAG Search
Source: https://docs.crewai.com/tools/youtubevideosearchtool
The `YoutubeVideoSearchTool` is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a Youtube video.
# `YoutubeVideoSearchTool`
We are still working on improving tools, so there might be unexpected behavior or changes in the future.
## Description
This tool is part of the `crewai_tools` package and is designed to perform semantic searches within Youtube video content, utilizing Retrieval-Augmented Generation (RAG) techniques.
It is one of several "Search" tools in the package that leverage RAG for different sources.
The YoutubeVideoSearchTool allows for flexibility in searches; users can search across any Youtube video content without specifying a video URL,
or they can target their search to a specific Youtube video by providing its URL.
## Installation
To utilize the `YoutubeVideoSearchTool`, you must first install the `crewai_tools` package.
This package contains the `YoutubeVideoSearchTool` among other utilities designed to enhance your data analysis and processing tasks.
Install the package by executing the following command in your terminal:
```shell
pip install 'crewai[tools]'
```
## Example
The following example demonstrates how to use the `YoutubeVideoSearchTool` with a CrewAI agent:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools import YoutubeVideoSearchTool
# Initialize the tool for general YouTube video searches
youtube_search_tool = YoutubeVideoSearchTool()
# Define an agent that uses the tool
video_researcher = Agent(
role="Video Researcher",
goal="Extract relevant information from YouTube videos",
backstory="An expert researcher who specializes in analyzing video content.",
tools=[youtube_search_tool],
verbose=True,
)
# Example task to search for information in a specific video
research_task = Task(
description="Search for information about machine learning frameworks in the YouTube video at {youtube_video_url}",
expected_output="A summary of the key machine learning frameworks mentioned in the video.",
agent=video_researcher,
)
# Create and run the crew
crew = Crew(agents=[video_researcher], tasks=[research_task])
result = crew.kickoff(inputs={"youtube_video_url": "https://youtube.com/watch?v=example"})
```
You can also initialize the tool with a specific YouTube video URL:
```python Code
# Initialize the tool with a specific YouTube video URL
youtube_search_tool = YoutubeVideoSearchTool(
youtube_video_url='https://youtube.com/watch?v=example'
)
# Define an agent that uses the tool
video_researcher = Agent(
role="Video Researcher",
goal="Extract relevant information from a specific YouTube video",
backstory="An expert researcher who specializes in analyzing video content.",
tools=[youtube_search_tool],
verbose=True,
)
```
## Parameters
The `YoutubeVideoSearchTool` accepts the following parameters:
* **youtube\_video\_url**: Optional. The URL of the YouTube video to search within. If provided during initialization, the agent won't need to specify it when using the tool.
* **config**: Optional. Configuration for the underlying RAG system, including LLM and embedder settings.
* **summarize**: Optional. Whether to summarize the retrieved content. Default is `False`.
When using the tool with an agent, the agent will need to provide:
* **search\_query**: Required. The search query to find relevant information in the video content.
* **youtube\_video\_url**: Required only if not provided during initialization. The URL of the YouTube video to search within.
## Custom Model and Embeddings
By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
```python Code
youtube_search_tool = YoutubeVideoSearchTool(
config=dict(
llm=dict(
provider="ollama", # or google, openai, anthropic, llama2, ...
config=dict(
model="llama2",
# temperature=0.5,
# top_p=1,
# stream=true,
),
),
embedder=dict(
provider="google", # or openai, ollama, ...
config=dict(
model="models/embedding-001",
task_type="retrieval_document",
# title="Embeddings",
),
),
)
)
```
## Agent Integration Example
Here's a more detailed example of how to integrate the `YoutubeVideoSearchTool` with a CrewAI agent:
```python Code
from crewai import Agent, Task, Crew
from crewai_tools import YoutubeVideoSearchTool
# Initialize the tool
youtube_search_tool = YoutubeVideoSearchTool()
# Define an agent that uses the tool
video_researcher = Agent(
role="Video Researcher",
goal="Extract and analyze information from YouTube videos",
backstory="""You are an expert video researcher who specializes in extracting
and analyzing information from YouTube videos. You have a keen eye for detail
and can quickly identify key points and insights from video content.""",
tools=[youtube_search_tool],
verbose=True,
)
# Create a task for the agent
research_task = Task(
description="""
Search for information about recent advancements in artificial intelligence
in the YouTube video at {youtube_video_url}.
Focus on:
1. Key AI technologies mentioned
2. Real-world applications discussed
3. Future predictions made by the speaker
Provide a comprehensive summary of these points.
""",
expected_output="A detailed summary of AI advancements, applications, and future predictions from the video.",
agent=video_researcher,
)
# Run the task
crew = Crew(agents=[video_researcher], tasks=[research_task])
result = crew.kickoff(inputs={"youtube_video_url": "https://youtube.com/watch?v=example"})
```
## Implementation Details
The `YoutubeVideoSearchTool` is implemented as a subclass of `RagTool`, which provides the base functionality for Retrieval-Augmented Generation:
```python Code
class YoutubeVideoSearchTool(RagTool):
name: str = "Search a Youtube Video content"
description: str = "A tool that can be used to semantic search a query from a Youtube Video content."
args_schema: Type[BaseModel] = YoutubeVideoSearchToolSchema
def __init__(self, youtube_video_url: Optional[str] = None, **kwargs):
super().__init__(**kwargs)
if youtube_video_url is not None:
kwargs["data_type"] = DataType.YOUTUBE_VIDEO
self.add(youtube_video_url)
self.description = f"A tool that can be used to semantic search a query the {youtube_video_url} Youtube Video content."
self.args_schema = FixedYoutubeVideoSearchToolSchema
self._generate_description()
```
## Conclusion
The `YoutubeVideoSearchTool` provides a powerful way to search and extract information from YouTube video content using RAG techniques. By enabling agents to search within video content, it facilitates information extraction and analysis tasks that would otherwise be difficult to perform. This tool is particularly useful for research, content analysis, and knowledge extraction from video sources.
This matrix helps visualize how different approaches align with varying requirements for complexity and precision. Let's explore what each quadrant means and how it guides your architectural choices.
## The Complexity-Precision Matrix Explained
### What is Complexity?
In the context of CrewAI applications, **complexity** refers to:
* The number of distinct steps or operations required
* The diversity of tasks that need to be performed
* The interdependencies between different components
* The need for conditional logic and branching
* The sophistication of the overall workflow
### What is Precision?
**Precision** in this context refers to:
* The accuracy required in the final output
* The need for structured, predictable results
* The importance of reproducibility
* The level of control needed over each step
* The tolerance for variation in outputs
### The Four Quadrants
#### 1. Low Complexity, Low Precision
**Characteristics:**
* Simple, straightforward tasks
* Tolerance for some variation in outputs
* Limited number of steps
* Creative or exploratory applications
**Recommended Approach:** Simple Crews with minimal agents
**Example Use Cases:**
* Basic content generation
* Idea brainstorming
* Simple summarization tasks
* Creative writing assistance
#### 2. Low Complexity, High Precision
**Characteristics:**
* Simple workflows that require exact, structured outputs
* Need for reproducible results
* Limited steps but high accuracy requirements
* Often involves data processing or transformation
**Recommended Approach:** Flows with direct LLM calls or simple Crews with structured outputs
**Example Use Cases:**
* Data extraction and transformation
* Form filling and validation
* Structured content generation (JSON, XML)
* Simple classification tasks
#### 3. High Complexity, Low Precision
**Characteristics:**
* Multi-stage processes with many steps
* Creative or exploratory outputs
* Complex interactions between components
* Tolerance for variation in final results
**Recommended Approach:** Complex Crews with multiple specialized agents
**Example Use Cases:**
* Research and analysis
* Content creation pipelines
* Exploratory data analysis
* Creative problem-solving
#### 4. High Complexity, High Precision
**Characteristics:**
* Complex workflows requiring structured outputs
* Multiple interdependent steps with strict accuracy requirements
* Need for both sophisticated processing and precise results
* Often mission-critical applications
**Recommended Approach:** Flows orchestrating multiple Crews with validation steps
**Example Use Cases:**
* Enterprise decision support systems
* Complex data processing pipelines
* Multi-stage document processing
* Regulated industry applications
## Choosing Between Crews and Flows
### When to Choose Crews
Crews are ideal when:
1. **You need collaborative intelligence** - Multiple agents with different specializations need to work together
2. **The problem requires emergent thinking** - The solution benefits from different perspectives and approaches
3. **The task is primarily creative or analytical** - The work involves research, content creation, or analysis
4. **You value adaptability over strict structure** - The workflow can benefit from agent autonomy
5. **The output format can be somewhat flexible** - Some variation in output structure is acceptable
```python
# Example: Research Crew for market analysis
from crewai import Agent, Crew, Process, Task
# Create specialized agents
researcher = Agent(
role="Market Research Specialist",
goal="Find comprehensive market data on emerging technologies",
backstory="You are an expert at discovering market trends and gathering data."
)
analyst = Agent(
role="Market Analyst",
goal="Analyze market data and identify key opportunities",
backstory="You excel at interpreting market data and spotting valuable insights."
)
# Define their tasks
research_task = Task(
description="Research the current market landscape for AI-powered healthcare solutions",
expected_output="Comprehensive market data including key players, market size, and growth trends",
agent=researcher
)
analysis_task = Task(
description="Analyze the market data and identify the top 3 investment opportunities",
expected_output="Analysis report with 3 recommended investment opportunities and rationale",
agent=analyst,
context=[research_task]
)
# Create the crew
market_analysis_crew = Crew(
agents=[researcher, analyst],
tasks=[research_task, analysis_task],
process=Process.sequential,
verbose=True
)
# Run the crew
result = market_analysis_crew.kickoff()
```
### When to Choose Flows
Flows are ideal when:
1. **You need precise control over execution** - The workflow requires exact sequencing and state management
2. **The application has complex state requirements** - You need to maintain and transform state across multiple steps
3. **You need structured, predictable outputs** - The application requires consistent, formatted results
4. **The workflow involves conditional logic** - Different paths need to be taken based on intermediate results
5. **You need to combine AI with procedural code** - The solution requires both AI capabilities and traditional programming
```python
# Example: Customer Support Flow with structured processing
from crewai.flow.flow import Flow, listen, router, start
from pydantic import BaseModel
from typing import List, Dict
# Define structured state
class SupportTicketState(BaseModel):
ticket_id: str = ""
customer_name: str = ""
issue_description: str = ""
category: str = ""
priority: str = "medium"
resolution: str = ""
satisfaction_score: int = 0
class CustomerSupportFlow(Flow[SupportTicketState]):
@start()
def receive_ticket(self):
# In a real app, this might come from an API
self.state.ticket_id = "TKT-12345"
self.state.customer_name = "Alex Johnson"
self.state.issue_description = "Unable to access premium features after payment"
return "Ticket received"
@listen(receive_ticket)
def categorize_ticket(self, _):
# Use a direct LLM call for categorization
from crewai import LLM
llm = LLM(model="openai/gpt-4o-mini")
prompt = f"""
Categorize the following customer support issue into one of these categories:
- Billing
- Account Access
- Technical Issue
- Feature Request
- Other
Issue: {self.state.issue_description}
Return only the category name.
"""
self.state.category = llm.call(prompt).strip()
return self.state.category
@router(categorize_ticket)
def route_by_category(self, category):
# Route to different handlers based on category
return category.lower().replace(" ", "_")
@listen("billing")
def handle_billing_issue(self):
# Handle billing-specific logic
self.state.priority = "high"
# More billing-specific processing...
return "Billing issue handled"
@listen("account_access")
def handle_access_issue(self):
# Handle access-specific logic
self.state.priority = "high"
# More access-specific processing...
return "Access issue handled"
# Additional category handlers...
@listen("billing", "account_access", "technical_issue", "feature_request", "other")
def resolve_ticket(self, resolution_info):
# Final resolution step
self.state.resolution = f"Issue resolved: {resolution_info}"
return self.state.resolution
# Run the flow
support_flow = CustomerSupportFlow()
result = support_flow.kickoff()
```
### When to Combine Crews and Flows
The most sophisticated applications often benefit from combining Crews and Flows:
1. **Complex multi-stage processes** - Use Flows to orchestrate the overall process and Crews for complex subtasks
2. **Applications requiring both creativity and structure** - Use Crews for creative tasks and Flows for structured processing
3. **Enterprise-grade AI applications** - Use Flows to manage state and process flow while leveraging Crews for specialized work
```python
# Example: Content Production Pipeline combining Crews and Flows
from crewai.flow.flow import Flow, listen, start
from crewai import Agent, Crew, Process, Task
from pydantic import BaseModel
from typing import List, Dict
class ContentState(BaseModel):
topic: str = ""
target_audience: str = ""
content_type: str = ""
outline: Dict = {}
draft_content: str = ""
final_content: str = ""
seo_score: int = 0
class ContentProductionFlow(Flow[ContentState]):
@start()
def initialize_project(self):
# Set initial parameters
self.state.topic = "Sustainable Investing"
self.state.target_audience = "Millennial Investors"
self.state.content_type = "Blog Post"
return "Project initialized"
@listen(initialize_project)
def create_outline(self, _):
# Use a research crew to create an outline
researcher = Agent(
role="Content Researcher",
goal=f"Research {self.state.topic} for {self.state.target_audience}",
backstory="You are an expert researcher with deep knowledge of content creation."
)
outliner = Agent(
role="Content Strategist",
goal=f"Create an engaging outline for a {self.state.content_type}",
backstory="You excel at structuring content for maximum engagement."
)
research_task = Task(
description=f"Research {self.state.topic} focusing on what would interest {self.state.target_audience}",
expected_output="Comprehensive research notes with key points and statistics",
agent=researcher
)
outline_task = Task(
description=f"Create an outline for a {self.state.content_type} about {self.state.topic}",
expected_output="Detailed content outline with sections and key points",
agent=outliner,
context=[research_task]
)
outline_crew = Crew(
agents=[researcher, outliner],
tasks=[research_task, outline_task],
process=Process.sequential,
verbose=True
)
# Run the crew and store the result
result = outline_crew.kickoff()
# Parse the outline (in a real app, you might use a more robust parsing approach)
import json
try:
self.state.outline = json.loads(result.raw)
except:
# Fallback if not valid JSON
self.state.outline = {"sections": result.raw}
return "Outline created"
@listen(create_outline)
def write_content(self, _):
# Use a writing crew to create the content
writer = Agent(
role="Content Writer",
goal=f"Write engaging content for {self.state.target_audience}",
backstory="You are a skilled writer who creates compelling content."
)
editor = Agent(
role="Content Editor",
goal="Ensure content is polished, accurate, and engaging",
backstory="You have a keen eye for detail and a talent for improving content."
)
writing_task = Task(
description=f"Write a {self.state.content_type} about {self.state.topic} following this outline: {self.state.outline}",
expected_output="Complete draft content in markdown format",
agent=writer
)
editing_task = Task(
description="Edit and improve the draft content for clarity, engagement, and accuracy",
expected_output="Polished final content in markdown format",
agent=editor,
context=[writing_task]
)
writing_crew = Crew(
agents=[writer, editor],
tasks=[writing_task, editing_task],
process=Process.sequential,
verbose=True
)
# Run the crew and store the result
result = writing_crew.kickoff()
self.state.final_content = result.raw
return "Content created"
@listen(write_content)
def optimize_for_seo(self, _):
# Use a direct LLM call for SEO optimization
from crewai import LLM
llm = LLM(model="openai/gpt-4o-mini")
prompt = f"""
Analyze this content for SEO effectiveness for the keyword "{self.state.topic}".
Rate it on a scale of 1-100 and provide 3 specific recommendations for improvement.
Content: {self.state.final_content[:1000]}... (truncated for brevity)
Format your response as JSON with the following structure:
{{
"score": 85,
"recommendations": [
"Recommendation 1",
"Recommendation 2",
"Recommendation 3"
]
}}
"""
seo_analysis = llm.call(prompt)
# Parse the SEO analysis
import json
try:
analysis = json.loads(seo_analysis)
self.state.seo_score = analysis.get("score", 0)
return analysis
except:
self.state.seo_score = 50
return {"score": 50, "recommendations": ["Unable to parse SEO analysis"]}
# Run the flow
content_flow = ContentProductionFlow()
result = content_flow.kickoff()
```
## Practical Evaluation Framework
To determine the right approach for your specific use case, follow this step-by-step evaluation framework:
### Step 1: Assess Complexity
Rate your application's complexity on a scale of 1-10 by considering:
1. **Number of steps**: How many distinct operations are required?
* 1-3 steps: Low complexity (1-3)
* 4-7 steps: Medium complexity (4-7)
* 8+ steps: High complexity (8-10)
2. **Interdependencies**: How interconnected are the different parts?
* Few dependencies: Low complexity (1-3)
* Some dependencies: Medium complexity (4-7)
* Many complex dependencies: High complexity (8-10)
3. **Conditional logic**: How much branching and decision-making is needed?
* Linear process: Low complexity (1-3)
* Some branching: Medium complexity (4-7)
* Complex decision trees: High complexity (8-10)
4. **Domain knowledge**: How specialized is the knowledge required?
* General knowledge: Low complexity (1-3)
* Some specialized knowledge: Medium complexity (4-7)
* Deep expertise in multiple domains: High complexity (8-10)
Calculate your average score to determine overall complexity.
### Step 2: Assess Precision Requirements
Rate your precision requirements on a scale of 1-10 by considering:
1. **Output structure**: How structured must the output be?
* Free-form text: Low precision (1-3)
* Semi-structured: Medium precision (4-7)
* Strictly formatted (JSON, XML): High precision (8-10)
2. **Accuracy needs**: How important is factual accuracy?
* Creative content: Low precision (1-3)
* Informational content: Medium precision (4-7)
* Critical information: High precision (8-10)
3. **Reproducibility**: How consistent must results be across runs?
* Variation acceptable: Low precision (1-3)
* Some consistency needed: Medium precision (4-7)
* Exact reproducibility required: High precision (8-10)
4. **Error tolerance**: What is the impact of errors?
* Low impact: Low precision (1-3)
* Moderate impact: Medium precision (4-7)
* High impact: High precision (8-10)
Calculate your average score to determine overall precision requirements.
### Step 3: Map to the Matrix
Plot your complexity and precision scores on the matrix:
* **Low Complexity (1-4), Low Precision (1-4)**: Simple Crews
* **Low Complexity (1-4), High Precision (5-10)**: Flows with direct LLM calls
* **High Complexity (5-10), Low Precision (1-4)**: Complex Crews
* **High Complexity (5-10), High Precision (5-10)**: Flows orchestrating Crews
### Step 4: Consider Additional Factors
Beyond complexity and precision, consider:
1. **Development time**: Crews are often faster to prototype
2. **Maintenance needs**: Flows provide better long-term maintainability
3. **Team expertise**: Consider your team's familiarity with different approaches
4. **Scalability requirements**: Flows typically scale better for complex applications
5. **Integration needs**: Consider how the solution will integrate with existing systems
## Conclusion
Choosing between Crews and Flows—or combining them—is a critical architectural decision that impacts the effectiveness, maintainability, and scalability of your CrewAI application. By evaluating your use case along the dimensions of complexity and precision, you can make informed decisions that align with your specific requirements.
Remember that the best approach often evolves as your application matures. Start with the simplest solution that meets your needs, and be prepared to refine your architecture as you gain experience and your requirements become clearer.
## Step 2: Explore the Project Structure
Let's take a moment to understand the project structure created by the CLI. CrewAI follows best practices for Python projects, making it easy to maintain and extend your code as your crews become more complex.
```
research_crew/
├── .gitignore
├── pyproject.toml
├── README.md
├── .env
└── src/
└── research_crew/
├── __init__.py
├── main.py
├── crew.py
├── tools/
│ ├── custom_tool.py
│ └── __init__.py
└── config/
├── agents.yaml
└── tasks.yaml
```
This structure follows best practices for Python projects and makes it easy to organize your code. The separation of configuration files (in YAML) from implementation code (in Python) makes it easy to modify your crew's behavior without changing the underlying code.
## Step 3: Configure Your Agents
Now comes the fun part - defining your AI agents! In CrewAI, agents are specialized entities with specific roles, goals, and backstories that shape their behavior. Think of them as characters in a play, each with their own personality and purpose.
For our research crew, we'll create two agents:
1. A **researcher** who excels at finding and organizing information
2. An **analyst** who can interpret research findings and create insightful reports
Let's modify the `agents.yaml` file to define these specialized agents:
```yaml
# src/research_crew/config/agents.yaml
researcher:
role: >
Senior Research Specialist for {topic}
goal: >
Find comprehensive and accurate information about {topic}
with a focus on recent developments and key insights
backstory: >
You are an experienced research specialist with a talent for
finding relevant information from various sources. You excel at
organizing information in a clear and structured manner, making
complex topics accessible to others.
llm: openai/gpt-4o-mini
analyst:
role: >
Data Analyst and Report Writer for {topic}
goal: >
Analyze research findings and create a comprehensive, well-structured
report that presents insights in a clear and engaging way
backstory: >
You are a skilled analyst with a background in data interpretation
and technical writing. You have a talent for identifying patterns
and extracting meaningful insights from research data, then
communicating those insights effectively through well-crafted reports.
llm: openai/gpt-4o-mini
```
Notice how each agent has a distinct role, goal, and backstory. These elements aren't just descriptive - they actively shape how the agent approaches its tasks. By crafting these carefully, you can create agents with specialized skills and perspectives that complement each other.
## Step 4: Define Your Tasks
With our agents defined, we now need to give them specific tasks to perform. Tasks in CrewAI represent the concrete work that agents will perform, with detailed instructions and expected outputs.
For our research crew, we'll define two main tasks:
1. A **research task** for gathering comprehensive information
2. An **analysis task** for creating an insightful report
Let's modify the `tasks.yaml` file:
```yaml
# src/research_crew/config/tasks.yaml
research_task:
description: >
Conduct thorough research on {topic}. Focus on:
1. Key concepts and definitions
2. Historical development and recent trends
3. Major challenges and opportunities
4. Notable applications or case studies
5. Future outlook and potential developments
Make sure to organize your findings in a structured format with clear sections.
expected_output: >
A comprehensive research document with well-organized sections covering
all the requested aspects of {topic}. Include specific facts, figures,
and examples where relevant.
agent: researcher
analysis_task:
description: >
Analyze the research findings and create a comprehensive report on {topic}.
Your report should:
1. Begin with an executive summary
2. Include all key information from the research
3. Provide insightful analysis of trends and patterns
4. Offer recommendations or future considerations
5. Be formatted in a professional, easy-to-read style with clear headings
expected_output: >
A polished, professional report on {topic} that presents the research
findings with added analysis and insights. The report should be well-structured
with an executive summary, main sections, and conclusion.
agent: analyst
context:
- research_task
output_file: output/report.md
```
Note the `context` field in the analysis task - this is a powerful feature that allows the analyst to access the output of the research task. This creates a workflow where information flows naturally between agents, just as it would in a human team.
## Step 5: Configure Your Crew
Now it's time to bring everything together by configuring our crew. The crew is the container that orchestrates how agents work together to complete tasks.
Let's modify the `crew.py` file:
```python
# src/research_crew/crew.py
from crewai import Agent, Crew, Process, Task
from crewai.project import CrewBase, agent, crew, task
from crewai_tools import SerperDevTool
from crewai.agents.agent_builder.base_agent import BaseAgent
from typing import List
@CrewBase
class ResearchCrew():
"""Research crew for comprehensive topic analysis and reporting"""
agents: List[BaseAgent]
tasks: List[Task]
@agent
def researcher(self) -> Agent:
return Agent(
config=self.agents_config['researcher'], # type: ignore[index]
verbose=True,
tools=[SerperDevTool()]
)
@agent
def analyst(self) -> Agent:
return Agent(
config=self.agents_config['analyst'], # type: ignore[index]
verbose=True
)
@task
def research_task(self) -> Task:
return Task(
config=self.tasks_config['research_task'] # type: ignore[index]
)
@task
def analysis_task(self) -> Task:
return Task(
config=self.tasks_config['analysis_task'], # type: ignore[index]
output_file='output/report.md'
)
@crew
def crew(self) -> Crew:
"""Creates the research crew"""
return Crew(
agents=self.agents,
tasks=self.tasks,
process=Process.sequential,
verbose=True,
)
```
In this code, we're:
1. Creating the researcher agent and equipping it with the SerperDevTool to search the web
2. Creating the analyst agent
3. Setting up the research and analysis tasks
4. Configuring the crew to run tasks sequentially (the analyst will wait for the researcher to finish)
This is where the magic happens - with just a few lines of code, we've defined a collaborative AI system where specialized agents work together in a coordinated process.
## Step 6: Set Up Your Main Script
Now, let's set up the main script that will run our crew. This is where we provide the specific topic we want our crew to research.
```python
#!/usr/bin/env python
# src/research_crew/main.py
import os
from research_crew.crew import ResearchCrew
# Create output directory if it doesn't exist
os.makedirs('output', exist_ok=True)
def run():
"""
Run the research crew.
"""
inputs = {
'topic': 'Artificial Intelligence in Healthcare'
}
# Create and run the crew
result = ResearchCrew().crew().kickoff(inputs=inputs)
# Print the result
print("\n\n=== FINAL REPORT ===\n\n")
print(result.raw)
print("\n\nReport has been saved to output/report.md")
if __name__ == "__main__":
run()
```
This script prepares the environment, specifies our research topic, and kicks off the crew's work. The power of CrewAI is evident in how simple this code is - all the complexity of managing multiple AI agents is handled by the framework.
## Step 7: Set Up Your Environment Variables
Create a `.env` file in your project root with your API keys:
```
OPENAI_API_KEY=your_openai_api_key
SERPER_API_KEY=your_serper_api_key
```
You can get a Serper API key from [Serper.dev](https://serper.dev/).
## Step 8: Install Dependencies
Install the required dependencies using the CrewAI CLI:
```bash
crewai install
```
This command will:
1. Read the dependencies from your project configuration
2. Create a virtual environment if needed
3. Install all required packages
## Step 9: Run Your Crew
Now for the exciting moment - it's time to run your crew and see AI collaboration in action!
```bash
crewai run
```
When you run this command, you'll see your crew spring to life. The researcher will gather information about the specified topic, and the analyst will then create a comprehensive report based on that research. You'll see the agents' thought processes, actions, and outputs in real-time as they work together to complete their tasks.
## Step 10: Review the Output
Once the crew completes its work, you'll find the final report in the `output/report.md` file. The report will include:
1. An executive summary
2. Detailed information about the topic
3. Analysis and insights
4. Recommendations or future considerations
Take a moment to appreciate what you've accomplished - you've created a system where multiple AI agents collaborated on a complex task, each contributing their specialized skills to produce a result that's greater than what any single agent could achieve alone.
## Exploring Other CLI Commands
CrewAI offers several other useful CLI commands for working with crews:
```bash
# View all available commands
crewai --help
# Run the crew
crewai run
# Test the crew
crewai test
# Reset crew memories
crewai reset-memories
# Replay from a specific task
crewai replay -t 
## Step 2: Understanding the Project Structure
The generated project has the following structure. Take a moment to familiarize yourself with it, as understanding this structure will help you create more complex flows in the future.
```
guide_creator_flow/
├── .gitignore
├── pyproject.toml
├── README.md
├── .env
├── main.py
├── crews/
│ └── poem_crew/
│ ├── config/
│ │ ├── agents.yaml
│ │ └── tasks.yaml
│ └── poem_crew.py
└── tools/
└── custom_tool.py
```
This structure provides a clear separation between different components of your flow:
* The main flow logic in the `main.py` file
* Specialized crews in the `crews` directory
* Custom tools in the `tools` directory
We'll modify this structure to create our guide creator flow, which will orchestrate the process of generating comprehensive learning guides.
## Step 3: Add a Content Writer Crew
Our flow will need a specialized crew to handle the content creation process. Let's use the CrewAI CLI to add a content writer crew:
```bash
crewai flow add-crew content-crew
```
This command automatically creates the necessary directories and template files for your crew. The content writer crew will be responsible for writing and reviewing sections of our guide, working within the overall flow orchestrated by our main application.
## Step 4: Configure the Content Writer Crew
Now, let's modify the generated files for the content writer crew. We'll set up two specialized agents - a writer and a reviewer - that will collaborate to create high-quality content for our guide.
1. First, update the agents configuration file to define our content creation team:
```yaml
# src/guide_creator_flow/crews/content_crew/config/agents.yaml
content_writer:
role: >
Educational Content Writer
goal: >
Create engaging, informative content that thoroughly explains the assigned topic
and provides valuable insights to the reader
backstory: >
You are a talented educational writer with expertise in creating clear, engaging
content. You have a gift for explaining complex concepts in accessible language
and organizing information in a way that helps readers build their understanding.
llm: openai/gpt-4o-mini
content_reviewer:
role: >
Educational Content Reviewer and Editor
goal: >
Ensure content is accurate, comprehensive, well-structured, and maintains
consistency with previously written sections
backstory: >
You are a meticulous editor with years of experience reviewing educational
content. You have an eye for detail, clarity, and coherence. You excel at
improving content while maintaining the original author's voice and ensuring
consistent quality across multiple sections.
llm: openai/gpt-4o-mini
```
These agent definitions establish the specialized roles and perspectives that will shape how our AI agents approach content creation. Notice how each agent has a distinct purpose and expertise.
2. Next, update the tasks configuration file to define the specific writing and reviewing tasks:
```yaml
# src/guide_creator_flow/crews/content_crew/config/tasks.yaml
write_section_task:
description: >
Write a comprehensive section on the topic: "{section_title}"
Section description: {section_description}
Target audience: {audience_level} level learners
Your content should:
1. Begin with a brief introduction to the section topic
2. Explain all key concepts clearly with examples
3. Include practical applications or exercises where appropriate
4. End with a summary of key points
5. Be approximately 500-800 words in length
Format your content in Markdown with appropriate headings, lists, and emphasis.
Previously written sections:
{previous_sections}
Make sure your content maintains consistency with previously written sections
and builds upon concepts that have already been explained.
expected_output: >
A well-structured, comprehensive section in Markdown format that thoroughly
explains the topic and is appropriate for the target audience.
agent: content_writer
review_section_task:
description: >
Review and improve the following section on "{section_title}":
{draft_content}
Target audience: {audience_level} level learners
Previously written sections:
{previous_sections}
Your review should:
1. Fix any grammatical or spelling errors
2. Improve clarity and readability
3. Ensure content is comprehensive and accurate
4. Verify consistency with previously written sections
5. Enhance the structure and flow
6. Add any missing key information
Provide the improved version of the section in Markdown format.
expected_output: >
An improved, polished version of the section that maintains the original
structure but enhances clarity, accuracy, and consistency.
agent: content_reviewer
context:
- write_section_task
```
These task definitions provide detailed instructions to our agents, ensuring they produce content that meets our quality standards. Note how the `context` parameter in the review task creates a workflow where the reviewer has access to the writer's output.
3. Now, update the crew implementation file to define how our agents and tasks work together:
```python
# src/guide_creator_flow/crews/content_crew/content_crew.py
from crewai import Agent, Crew, Process, Task
from crewai.project import CrewBase, agent, crew, task
from crewai.agents.agent_builder.base_agent import BaseAgent
from typing import List
@CrewBase
class ContentCrew():
"""Content writing crew"""
agents: List[BaseAgent]
tasks: List[Task]
@agent
def content_writer(self) -> Agent:
return Agent(
config=self.agents_config['content_writer'], # type: ignore[index]
verbose=True
)
@agent
def content_reviewer(self) -> Agent:
return Agent(
config=self.agents_config['content_reviewer'], # type: ignore[index]
verbose=True
)
@task
def write_section_task(self) -> Task:
return Task(
config=self.tasks_config['write_section_task'] # type: ignore[index]
)
@task
def review_section_task(self) -> Task:
return Task(
config=self.tasks_config['review_section_task'], # type: ignore[index]
context=[self.write_section_task()]
)
@crew
def crew(self) -> Crew:
"""Creates the content writing crew"""
return Crew(
agents=self.agents,
tasks=self.tasks,
process=Process.sequential,
verbose=True,
)
```
This crew definition establishes the relationship between our agents and tasks, setting up a sequential process where the content writer creates a draft and then the reviewer improves it. While this crew can function independently, in our flow it will be orchestrated as part of a larger system.
## Step 5: Create the Flow
Now comes the exciting part - creating the flow that will orchestrate the entire guide creation process. This is where we'll combine regular Python code, direct LLM calls, and our content creation crew into a cohesive system.
Our flow will:
1. Get user input for a topic and audience level
2. Make a direct LLM call to create a structured guide outline
3. Process each section sequentially using the content writer crew
4. Combine everything into a final comprehensive document
Let's create our flow in the `main.py` file:
```python
#!/usr/bin/env python
import json
import os
from typing import List, Dict
from pydantic import BaseModel, Field
from crewai import LLM
from crewai.flow.flow import Flow, listen, start
from guide_creator_flow.crews.content_crew.content_crew import ContentCrew
# Define our models for structured data
class Section(BaseModel):
title: str = Field(description="Title of the section")
description: str = Field(description="Brief description of what the section should cover")
class GuideOutline(BaseModel):
title: str = Field(description="Title of the guide")
introduction: str = Field(description="Introduction to the topic")
target_audience: str = Field(description="Description of the target audience")
sections: List[Section] = Field(description="List of sections in the guide")
conclusion: str = Field(description="Conclusion or summary of the guide")
# Define our flow state
class GuideCreatorState(BaseModel):
topic: str = ""
audience_level: str = ""
guide_outline: GuideOutline = None
sections_content: Dict[str, str] = {}
class GuideCreatorFlow(Flow[GuideCreatorState]):
"""Flow for creating a comprehensive guide on any topic"""
@start()
def get_user_input(self):
"""Get input from the user about the guide topic and audience"""
print("\n=== Create Your Comprehensive Guide ===\n")
# Get user input
self.state.topic = input("What topic would you like to create a guide for? ")
# Get audience level with validation
while True:
audience = input("Who is your target audience? (beginner/intermediate/advanced) ").lower()
if audience in ["beginner", "intermediate", "advanced"]:
self.state.audience_level = audience
break
print("Please enter 'beginner', 'intermediate', or 'advanced'")
print(f"\nCreating a guide on {self.state.topic} for {self.state.audience_level} audience...\n")
return self.state
@listen(get_user_input)
def create_guide_outline(self, state):
"""Create a structured outline for the guide using a direct LLM call"""
print("Creating guide outline...")
# Initialize the LLM
llm = LLM(model="openai/gpt-4o-mini", response_format=GuideOutline)
# Create the messages for the outline
messages = [
{"role": "system", "content": "You are a helpful assistant designed to output JSON."},
{"role": "user", "content": f"""
Create a detailed outline for a comprehensive guide on "{state.topic}" for {state.audience_level} level learners.
The outline should include:
1. A compelling title for the guide
2. An introduction to the topic
3. 4-6 main sections that cover the most important aspects of the topic
4. A conclusion or summary
For each section, provide a clear title and a brief description of what it should cover.
"""}
]
# Make the LLM call with JSON response format
response = llm.call(messages=messages)
# Parse the JSON response
outline_dict = json.loads(response)
self.state.guide_outline = GuideOutline(**outline_dict)
# Ensure output directory exists before saving
os.makedirs("output", exist_ok=True)
# Save the outline to a file
with open("output/guide_outline.json", "w") as f:
json.dump(outline_dict, f, indent=2)
print(f"Guide outline created with {len(self.state.guide_outline.sections)} sections")
return self.state.guide_outline
@listen(create_guide_outline)
def write_and_compile_guide(self, outline):
"""Write all sections and compile the guide"""
print("Writing guide sections and compiling...")
completed_sections = []
# Process sections one by one to maintain context flow
for section in outline.sections:
print(f"Processing section: {section.title}")
# Build context from previous sections
previous_sections_text = ""
if completed_sections:
previous_sections_text = "# Previously Written Sections\n\n"
for title in completed_sections:
previous_sections_text += f"## {title}\n\n"
previous_sections_text += self.state.sections_content.get(title, "") + "\n\n"
else:
previous_sections_text = "No previous sections written yet."
# Run the content crew for this section
result = ContentCrew().crew().kickoff(inputs={
"section_title": section.title,
"section_description": section.description,
"audience_level": self.state.audience_level,
"previous_sections": previous_sections_text,
"draft_content": ""
})
# Store the content
self.state.sections_content[section.title] = result.raw
completed_sections.append(section.title)
print(f"Section completed: {section.title}")
# Compile the final guide
guide_content = f"# {outline.title}\n\n"
guide_content += f"## Introduction\n\n{outline.introduction}\n\n"
# Add each section in order
for section in outline.sections:
section_content = self.state.sections_content.get(section.title, "")
guide_content += f"\n\n{section_content}\n\n"
# Add conclusion
guide_content += f"## Conclusion\n\n{outline.conclusion}\n\n"
# Save the guide
with open("output/complete_guide.md", "w") as f:
f.write(guide_content)
print("\nComplete guide compiled and saved to output/complete_guide.md")
return "Guide creation completed successfully"
def kickoff():
"""Run the guide creator flow"""
GuideCreatorFlow().kickoff()
print("\n=== Flow Complete ===")
print("Your comprehensive guide is ready in the output directory.")
print("Open output/complete_guide.md to view it.")
def plot():
"""Generate a visualization of the flow"""
flow = GuideCreatorFlow()
flow.plot("guide_creator_flow")
print("Flow visualization saved to guide_creator_flow.html")
if __name__ == "__main__":
kickoff()
```
Let's analyze what's happening in this flow:
1. We define Pydantic models for structured data, ensuring type safety and clear data representation
2. We create a state class to maintain data across different steps of the flow
3. We implement three main flow steps:
* Getting user input with the `@start()` decorator
* Creating a guide outline with a direct LLM call
* Processing sections with our content crew
4. We use the `@listen()` decorator to establish event-driven relationships between steps
This is the power of flows - combining different types of processing (user interaction, direct LLM calls, crew-based tasks) into a coherent, event-driven system.
## Step 6: Set Up Your Environment Variables
Create a `.env` file in your project root with your API keys:
```
OPENAI_API_KEY=your_openai_api_key
```
## Step 7: Install Dependencies
Install the required dependencies:
```bash
crewai install
```
## Step 8: Run Your Flow
Now it's time to see your flow in action! Run it using the CrewAI CLI:
```bash
crewai flow kickoff
```
When you run this command, you'll see your flow spring to life:
1. It will prompt you for a topic and audience level
2. It will create a structured outline for your guide
3. It will process each section, with the content writer and reviewer collaborating on each
4. Finally, it will compile everything into a comprehensive guide
This demonstrates the power of flows to orchestrate complex processes involving multiple components, both AI and non-AI.
## Step 9: Visualize Your Flow
One of the powerful features of flows is the ability to visualize their structure:
```bash
crewai flow plot
```
This will create an HTML file that shows the structure of your flow, including the relationships between different steps and the data that flows between them. This visualization can be invaluable for understanding and debugging complex flows.
## Step 10: Review the Output
Once the flow completes, you'll find two files in the `output` directory:
1. `guide_outline.json`: Contains the structured outline of the guide
2. `complete_guide.md`: The comprehensive guide with all sections
Take a moment to review these files and appreciate what you've built - a system that combines user input, direct AI interactions, and collaborative agent work to produce a complex, high-quality output.
## The Art of the Possible: Beyond Your First Flow
What you've learned in this guide provides a foundation for creating much more sophisticated AI systems. Here are some ways you could extend this basic flow:
### Enhancing User Interaction
You could create more interactive flows with:
* Web interfaces for input and output
* Real-time progress updates
* Interactive feedback and refinement loops
* Multi-stage user interactions
### Adding More Processing Steps
You could expand your flow with additional steps for:
* Research before outline creation
* Image generation for illustrations
* Code snippet generation for technical guides
* Final quality assurance and fact-checking
### Creating More Complex Flows
You could implement more sophisticated flow patterns:
* Conditional branching based on user preferences or content type
* Parallel processing of independent sections
* Iterative refinement loops with feedback
* Integration with external APIs and services
### Applying to Different Domains
The same patterns can be applied to create flows for:
* **Interactive storytelling**: Create personalized stories based on user input
* **Business intelligence**: Process data, generate insights, and create reports
* **Product development**: Facilitate ideation, design, and planning
* **Educational systems**: Create personalized learning experiences
## Key Features Demonstrated
This guide creator flow demonstrates several powerful features of CrewAI:
1. **User interaction**: The flow collects input directly from the user
2. **Direct LLM calls**: Uses the LLM class for efficient, single-purpose AI interactions
3. **Structured data with Pydantic**: Uses Pydantic models to ensure type safety
4. **Sequential processing with context**: Writes sections in order, providing previous sections for context
5. **Multi-agent crews**: Leverages specialized agents (writer and reviewer) for content creation
6. **State management**: Maintains state across different steps of the process
7. **Event-driven architecture**: Uses the `@listen` decorator to respond to events
## Understanding the Flow Structure
Let's break down the key components of flows to help you understand how to build your own:
### 1. Direct LLM Calls
Flows allow you to make direct calls to language models when you need simple, structured responses:
```python
llm = LLM(model="openai/gpt-4o-mini", response_format=GuideOutline)
response = llm.call(messages=messages)
```
This is more efficient than using a crew when you need a specific, structured output.
### 2. Event-Driven Architecture
Flows use decorators to establish relationships between components:
```python
@start()
def get_user_input(self):
# First step in the flow
# ...
@listen(get_user_input)
def create_guide_outline(self, state):
# This runs when get_user_input completes
# ...
```
This creates a clear, declarative structure for your application.
### 3. State Management
Flows maintain state across steps, making it easy to share data:
```python
class GuideCreatorState(BaseModel):
topic: str = ""
audience_level: str = ""
guide_outline: GuideOutline = None
sections_content: Dict[str, str] = {}
```
This provides a type-safe way to track and transform data throughout your flow.
### 4. Crew Integration
Flows can seamlessly integrate with crews for complex collaborative tasks:
```python
result = ContentCrew().crew().kickoff(inputs={
"section_title": section.title,
# ...
})
```
This allows you to use the right tool for each part of your application - direct LLM calls for simple tasks and crews for complex collaboration.
## Next Steps
Now that you've built your first flow, you can:
1. Experiment with more complex flow structures and patterns
2. Try using `@router()` to create conditional branches in your flows
3. Explore the `and_` and `or_` functions for more complex parallel execution
4. Connect your flow to external APIs, databases, or user interfaces
5. Combine multiple specialized crews in a single flow
### Features
* **Analytics Dashboard**: Monitor your Agents health and performance with detailed dashboards that track metrics, costs, and user interactions.
* **OpenTelemetry-native Observability SDK**: Vendor-neutral SDKs to send traces and metrics to your existing observability tools like Grafana, DataDog and more.
* **Cost Tracking for Custom and Fine-Tuned Models**: Tailor cost estimations for specific models using custom pricing files for precise budgeting.
* **Exceptions Monitoring Dashboard**: Quickly spot and resolve issues by tracking common exceptions and errors with a monitoring dashboard.
* **Compliance and Security**: Detect potential threats such as profanity and PII leaks.
* **Prompt Injection Detection**: Identify potential code injection and secret leaks.
* **API Keys and Secrets Management**: Securely handle your LLM API keys and secrets centrally, avoiding insecure practices.
* **Prompt Management**: Manage and version Agent prompts using PromptHub for consistent and easy access across Agents.
* **Model Playground** Test and compare different models for your CrewAI agents before deployment.
## Setup Instructions
Opik provides comprehensive support for every stage of your CrewAI application development:
* **Log Traces and Spans**: Automatically track LLM calls and application logic to debug and analyze development and production systems. Manually or programmatically annotate, view, and compare responses across projects.
* **Evaluate Your LLM Application's Performance**: Evaluate against a custom test set and run built-in evaluation metrics or define your own metrics in the SDK or UI.
* **Test Within Your CI/CD Pipeline**: Establish reliable performance baselines with Opik's LLM unit tests, built on PyTest. Run online evaluations for continuous monitoring in production.
* **Monitor & Analyze Production Data**: Understand your models' performance on unseen data in production and generate datasets for new dev iterations.
## Setup
Comet provides a hosted version of the Opik platform, or you can run the platform locally.
To use the hosted version, simply [create a free Comet account](https://www.comet.com/signup?utm_medium=github\&utm_source=crewai_docs) and grab you API Key.
To run the Opik platform locally, see our [installation guide](https://www.comet.com/docs/opik/self-host/overview/) for more information.
For this guide we will use CrewAI’s quickstart example.
[Portkey](https://portkey.ai/?utm_source=crewai\&utm_medium=crewai\&utm_campaign=crewai) is a 2-line upgrade to make your CrewAI agents reliable, cost-efficient, and fast.
Portkey adds 4 core production capabilities to any CrewAI agent:
1. Routing to **200+ LLMs**
2. Making each LLM call more robust
3. Full-stack tracing & cost, performance analytics
4. Real-time guardrails to enforce behavior
## Getting Started
### 1. Use 250+ LLMs
Access various LLMs like Anthropic, Gemini, Mistral, Azure OpenAI, and more with minimal code changes. Switch between providers or use them together seamlessly. [Learn more about Universal API](https://portkey.ai/docs/product/ai-gateway/universal-api)
Easily switch between different LLM providers:
```python
# Anthropic Configuration
anthropic_llm = LLM(
model="claude-3-5-sonnet-latest",
base_url=PORTKEY_GATEWAY_URL,
api_key="dummy",
extra_headers=createHeaders(
api_key="YOUR_PORTKEY_API_KEY",
virtual_key="YOUR_ANTHROPIC_VIRTUAL_KEY", #You don't need provider when using Virtual keys
trace_id="anthropic_agent"
)
)
# Azure OpenAI Configuration
azure_llm = LLM(
model="gpt-4",
base_url=PORTKEY_GATEWAY_URL,
api_key="dummy",
extra_headers=createHeaders(
api_key="YOUR_PORTKEY_API_KEY",
virtual_key="YOUR_AZURE_VIRTUAL_KEY", #You don't need provider when using Virtual keys
trace_id="azure_agent"
)
)
```
### 2. Caching
Improve response times and reduce costs with two powerful caching modes:
* **Simple Cache**: Perfect for exact matches
* **Semantic Cache**: Matches responses for requests that are semantically similar
[Learn more about Caching](https://portkey.ai/docs/product/ai-gateway/cache-simple-and-semantic)
```py
config = {
"cache": {
"mode": "semantic", # or "simple" for exact matching
}
}
```
### 3. Production Reliability
Portkey provides comprehensive reliability features:
* **Automatic Retries**: Handle temporary failures gracefully
* **Request Timeouts**: Prevent hanging operations
* **Conditional Routing**: Route requests based on specific conditions
* **Fallbacks**: Set up automatic provider failovers
* **Load Balancing**: Distribute requests efficiently
[Learn more about Reliability Features](https://portkey.ai/docs/product/ai-gateway/)
### 4. Metrics
Agent runs are complex. Portkey automatically logs **40+ comprehensive metrics** for your AI agents, including cost, tokens used, latency, etc. Whether you need a broad overview or granular insights into your agent runs, Portkey's customizable filters provide the metrics you need.
* Cost per agent interaction
* Response times and latency
* Token usage and efficiency
* Success/failure rates
* Cache hit rates
### 5. Detailed Logging
Logs are essential for understanding agent behavior, diagnosing issues, and improving performance. They provide a detailed record of agent activities and tool use, which is crucial for debugging and optimizing processes.
Access a dedicated section to view records of agent executions, including parameters, outcomes, function calls, and errors. Filter logs based on multiple parameters such as trace ID, model, tokens used, and metadata.
