Using Opik with CrewAI

This notebook showcases how to use Opik with CrewAI. CrewAI is a cutting-edge framework for orchestrating autonomous AI agents.

CrewAI enables you to create AI teams where each agent has specific roles, tools, and goals, working together to accomplish complex tasks.

Think of it as assembling your dream team - each member (agent) brings unique skills and expertise, collaborating seamlessly to achieve your objectives.

For this guide we will use CrewAI’s quickstart example.

Creating an account on Comet.com

Comet provides a hosted version of the Opik platform, simply create an account and grab you API Key.

You can also run the Opik platform locally, see the installation guide for more information.

1%pip install crewai crewai-tools opik --upgrade
1import opik
2
3opik.configure(use_local=False)

Preparing our environment

First, we set up our API keys for our LLM-provider as environment variables:

1import os
2import getpass
3
4if "OPENAI_API_KEY" not in os.environ:
5    os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter your OpenAI API key: ")

Using CrewAI

The first step is to create our project. We will use an example from CrewAI’s documentation:

1from crewai import Agent, Crew, Task, Process
2
3
4class YourCrewName:
5    def agent_one(self) -> Agent:
6        return Agent(
7            role="Data Analyst",
8            goal="Analyze data trends in the market",
9            backstory="An experienced data analyst with a background in economics",
10            verbose=True,
11        )
12
13    def agent_two(self) -> Agent:
14        return Agent(
15            role="Market Researcher",
16            goal="Gather information on market dynamics",
17            backstory="A diligent researcher with a keen eye for detail",
18            verbose=True,
19        )
20
21    def task_one(self) -> Task:
22        return Task(
23            name="Collect Data Task",
24            description="Collect recent market data and identify trends.",
25            expected_output="A report summarizing key trends in the market.",
26            agent=self.agent_one(),
27        )
28
29    def task_two(self) -> Task:
30        return Task(
31            name="Market Research Task",
32            description="Research factors affecting market dynamics.",
33            expected_output="An analysis of factors influencing the market.",
34            agent=self.agent_two(),
35        )
36
37    def crew(self) -> Crew:
38        return Crew(
39            agents=[self.agent_one(), self.agent_two()],
40            tasks=[self.task_one(), self.task_two()],
41            process=Process.sequential,
42            verbose=True,
43        )

Now we can import Opik’s tracker and run our crew:

1from opik.integrations.crewai import track_crewai
2
3track_crewai(project_name="crewai-integration-demo")
4
5my_crew = YourCrewName().crew()
6result = my_crew.kickoff()
7
8print(result)

You can now go to the Opik app to see the trace:

CrewAI trace in Opik

Built with