Tavily Extractor Tool

uv add 'crewai[tools]' tavily-python

export TAVILY_API_KEY='your-tavily-api-key'

import os
from crewai import Agent, Task, Crew
from crewai_tools import TavilyExtractorTool

# Ensure TAVILY_API_KEY is set in your environment
# os.environ["TAVILY_API_KEY"] = "YOUR_API_KEY"

# Initialize the tool
tavily_tool = TavilyExtractorTool()

# Create an agent that uses the tool
extractor_agent = Agent(
    role='Web Content Extractor',
    goal='Extract key information from specified web pages',
    backstory='You are an expert at extracting relevant content from websites using the Tavily API.',
    tools=[tavily_tool],
    verbose=True
)

# Define a task for the agent
extract_task = Task(
    description='Extract the main content from the URL https://example.com using basic extraction depth.',
    expected_output='A JSON string containing the extracted content from the URL.',
    agent=extractor_agent
)

# Create and run the crew
crew = Crew(
    agents=[extractor_agent],
    tasks=[extract_task],
    verbose=2
)

result = crew.kickoff()
print(result)

# Example with multiple URLs and advanced extraction
multi_extract_task = Task(
    description='Extract content from https://example.com and https://anotherexample.org using advanced extraction.',
    expected_output='A JSON string containing the extracted content from both URLs.',
    agent=extractor_agent
)

# Configure the tool with custom parameters
custom_extractor = TavilyExtractorTool(
    extract_depth='advanced',
    include_images=True,
    timeout=120
)

agent_with_custom_tool = Agent(
    role="Advanced Content Extractor",
    goal="Extract comprehensive content with images",
    tools=[custom_extractor]
)

# Initialize with custom configuration
extractor_tool = TavilyExtractorTool(
    extract_depth='advanced',  # More comprehensive extraction
    include_images=True,       # Include image results
    timeout=90                 # Custom timeout
)