How to beginner · 3 min read

Composio key concepts

Quick answer

Composio is a Python toolkit that enables seamless integration of AI tools with the OpenAI API using the tools parameter for function calling. It provides a ComposioToolSet to manage tools and handle tool calls from AI chat completions, enhancing AI agent capabilities with external actions.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install openai>=1.0
pip install composio-core composio-openai

Setup

Install the required packages and set your OpenAI API key in the environment. Composio works with the OpenAI SDK v1+ and requires composio-core and composio-openai packages.

bash

pip install openai>=1.0 composio-core composio-openai

output

Collecting openai
Collecting composio-core
Collecting composio-openai
Successfully installed openai composio-core composio-openai

Step by step

Use ComposioToolSet to get tools and pass them to the OpenAI chat completion call via the tools parameter. Then handle tool calls from the response using handle_tool_calls.

python

import os
from openai import OpenAI
from composio_openai import ComposioToolSet, Action

# Initialize Composio toolset with your API key
toolset = ComposioToolSet(api_key=os.environ["OPENAI_API_KEY"])

# Get tools for specific actions
tools = toolset.get_tools(actions=[Action.GITHUB_STAR_A_REPOSITORY])

# Initialize OpenAI client
client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

# Create chat completion with tools parameter
response = client.chat.completions.create(
    model="gpt-4o-mini",
    tools=tools,
    messages=[{"role": "user", "content": "Star the openai/openai-python repo"}]
)

print("AI response:", response.choices[0].message.content)

# Handle any tool calls from the response
toolset.handle_tool_calls(response)

output

AI response: I have initiated the process to star the openai/openai-python repository.
# (Tool call handled successfully)

Common variations

Use different Action enums to access other tools.
Switch to async calls by using asyncio and await with the OpenAI client.
Use other OpenAI models like gpt-4o or gpt-4o-mini depending on your use case.

python

import asyncio

async def async_example():
    from openai import OpenAI
    from composio_openai import ComposioToolSet, Action

    toolset = ComposioToolSet(api_key=os.environ["OPENAI_API_KEY"])
    tools = toolset.get_tools(actions=[Action.GITHUB_STAR_A_REPOSITORY])
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

    response = await client.chat.completions.acreate(
        model="gpt-4o",
        tools=tools,
        messages=[{"role": "user", "content": "Star the openai/openai-python repo"}]
    )

    print("Async AI response:", response.choices[0].message.content)
    toolset.handle_tool_calls(response)

asyncio.run(async_example())

output

Async AI response: I have started the process to star the openai/openai-python repository.
# (Tool call handled successfully)

Troubleshooting

If you see no tool calls handled, verify that the tools parameter is correctly passed and that the model supports tool use.
Ensure your API key has permissions for Composio tools.
Check for network issues if tool calls fail to execute.

✅

Key Takeaways

Use ComposioToolSet to manage and retrieve AI tools for OpenAI chat completions.
Pass tools via the tools parameter in client.chat.completions.create to enable function calling.
Handle tool calls from AI responses with handle_tool_calls to execute external actions.
Composio integrates seamlessly with OpenAI SDK v1+ and supports async usage.
Verify API key permissions and model compatibility when troubleshooting tool call issues.

Verified 2026-04 · gpt-4o-mini, gpt-4o

Verify ↗