uv add braintrust[otel] crewai crewai-tools opentelemetry-instrumentation-openai opentelemetry-instrumentation-crewai python-dotenv

import os
from getpass import getpass

# Get your Braintrust credentials
BRAINTRUST_API_KEY = getpass("🔑 Enter your Braintrust API Key: ")

# Get API keys for services
OPENAI_API_KEY = getpass("🔑 Enter your OpenAI API key: ")

# Set environment variables
os.environ["BRAINTRUST_API_KEY"] = BRAINTRUST_API_KEY
os.environ["BRAINTRUST_PARENT"] = "project_name:crewai-demo"
os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY

import os
from typing import Any, Dict

from braintrust.otel import BraintrustSpanProcessor
from crewai import Agent, Crew, Task
from crewai.llm import LLM
from opentelemetry import trace
from opentelemetry.instrumentation.crewai import CrewAIInstrumentor
from opentelemetry.instrumentation.openai import OpenAIInstrumentor
from opentelemetry.sdk.trace import TracerProvider

def setup_tracing() -> None:
    """Setup OpenTelemetry tracing with Braintrust."""
    current_provider = trace.get_tracer_provider()
    if isinstance(current_provider, TracerProvider):
        provider = current_provider
    else:
        provider = TracerProvider()
        trace.set_tracer_provider(provider)

    provider.add_span_processor(BraintrustSpanProcessor())
    CrewAIInstrumentor().instrument(tracer_provider=provider)
    OpenAIInstrumentor().instrument(tracer_provider=provider)


setup_tracing()

from crewai import Agent, Crew, Process, Task
from crewai_tools import SerperDevTool

def create_crew() -> Crew:
    """Create a crew with multiple agents for comprehensive tracing."""
    llm = LLM(model="gpt-4o-mini")
    search_tool = SerperDevTool()

    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,
        llm=llm,
        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,
        llm=llm,
    )

    research_task = Task(
        description="""Conduct a comprehensive analysis of the latest advancements in {topic}.
        Identify key trends, breakthrough technologies, and potential industry impacts.""",
        expected_output="Full analysis report in bullet points",
        agent=researcher,
    )

    writing_task = Task(
        description="""Using the insights provided, develop an engaging blog
        post that highlights the most significant {topic} 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,
        context=[research_task],
    )

    crew = Crew(
        agents=[researcher, writer],
        tasks=[research_task, writing_task],
        verbose=True,
        process=Process.sequential
    )

    return crew

def run_crew():
    """Run the crew and return results."""
    crew = create_crew()
    result = crew.kickoff(inputs={"topic": "AI developments"})
    return result

if __name__ == "__main__":
    result = run_crew()
    print(result)

# eval_crew.py
from braintrust import Eval
from autoevals import Levenshtein

def evaluate_crew_task(input_data):
    """Task function that wraps our crew for evaluation."""
    crew = create_crew()
    result = crew.kickoff(inputs={"topic": input_data["topic"]})
    return str(result)

Eval(
    "AI Research Crew",
    {
        "data": lambda: [
            {"topic": "artificial intelligence trends 2024"},
            {"topic": "machine learning breakthroughs"},
            {"topic": "AI ethics and governance"},
        ],
        "task": evaluate_crew_task,
        "scores": [Levenshtein],
    },
)

export BRAINTRUST_API_KEY="YOUR_API_KEY"
braintrust eval eval_crew.py