CrewAI

Instrument LLM applications using the CrewAI framework

Follow our Colab guide
See the source code

In this example, we will instrument a multi agent automation using the CrewAI framework.

This code requires an OpenAI API key and a Serper.dev API key.

Install the following packages

pip install openinference-instrumentation-crewai openinference-instrumentation-langchain crewai crewai-tools arize-otel opentelemetry-sdk opentelemetry-exporter-otlp

Set up CrewAIInstrumentor to trace your CrewAI application and sends the traces to Arize at the endpoint defined below. Optionally you can also set up the LangChainInstrumentor to get even deeper visibility into your Crew

from openinference.instrumentation.crewai import CrewAIInstrumentor
from openinference.instrumentation.langchain import LangChainInstrumentor
# Import open-telemetry dependencies
from arize.otel import register

# Setup OTel via our convenience function
tracer_provider = register(
    space_id = "your-space-id", # in app space settings page
    api_key = "your-api-key", # in app space settings page
    project_name = "your-project-name", # name this to whatever you would like
)

CrewAIInstrumentor().instrument(tracer_provider=tracer_provider)
LangChainInstrumentor().instrument(tracer_provider=tracer_provider)

To test, run the following code and observe your traces in Arize.

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

os.environ["OPENAI_API_KEY"] = "YOUR_OPENAI_API_KEY"
os.environ["SERPER_API_KEY"] = "YOUR_SERPER_API_KEY" 
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=False, # You can set it to True or False to different logging levels
  process = Process.sequential
)

# Get your crew to work!
result = crew.kickoff()

print("######################")
print(result)

Last updated

Was this helpful?