Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
Mirrored from https://github.com/Camo67/composio.git
Synced Nov 21, 04:45 UTC
| 1 | # composio-openai |
| 2 | |
| 3 | Adapts Composio tools to OpenAI function calling, for both the Responses API and the Chat Completions API. |
| 4 | |
| 5 | ## Installation |
| 6 | |
| 7 | ```bash |
| 8 | pip install composio composio-openai openai |
| 9 | ``` |
| 10 | |
| 11 | Set `COMPOSIO_API_KEY` (create one at https://dashboard.composio.dev/settings) and `OPENAI_API_KEY` in your environment. |
| 12 | |
| 13 | ## Quickstart |
| 14 | |
| 15 | This package exports two providers: `OpenAIResponsesProvider` for the [Responses API](https://platform.openai.com/docs/api-reference/responses) and `OpenAIProvider` for Chat Completions. Both are non-agentic: the model returns tool calls, you execute them with `handle_tool_calls`, and you feed the results back. |
| 16 | |
| 17 | ```python |
| 18 | import json |
| 19 | from openai import OpenAI |
| 20 | from composio import Composio |
| 21 | from composio_openai import OpenAIResponsesProvider |
| 22 | |
| 23 | composio = Composio(provider=OpenAIResponsesProvider()) |
| 24 | client = OpenAI() |
| 25 | |
| 26 | # Create a session for your user |
| 27 | session = composio.create(user_id="user_123") |
| 28 | tools = session.tools() |
| 29 | |
| 30 | response = client.responses.create( |
| 31 | model="gpt-5.2", |
| 32 | tools=tools, |
| 33 | input=[ |
| 34 | { |
| 35 | "role": "user", |
| 36 | "content": "Send an email to john@example.com with the subject 'Hello' and body 'Hello from Composio!'" |
| 37 | } |
| 38 | ] |
| 39 | ) |
| 40 | |
| 41 | # Agentic loop: keep executing tool calls until the model responds with text |
| 42 | while True: |
| 43 | tool_calls = [o for o in response.output if o.type == "function_call"] |
| 44 | if not tool_calls: |
| 45 | break |
| 46 | results = composio.provider.handle_tool_calls(response=response, session=session) |
| 47 | response = client.responses.create( |
| 48 | model="gpt-5.2", |
| 49 | tools=tools, |
| 50 | previous_response_id=response.id, |
| 51 | input=[ |
| 52 | {"type": "function_call_output", "call_id": tool_calls[i].call_id, "output": json.dumps(result)} |
| 53 | for i, result in enumerate(results) |
| 54 | ] |
| 55 | ) |
| 56 | |
| 57 | # Print final response |
| 58 | for item in response.output: |
| 59 | if item.type == "message": |
| 60 | print(item.content[0].text) |
| 61 | ``` |
| 62 | |
| 63 | ## Chat Completions |
| 64 | |
| 65 | `OpenAIProvider` targets `client.chat.completions.create` and is the Composio SDK default, so `Composio()` with no provider uses it. The loop is the same shape: call `handle_tool_calls(response=response, session=session)`, append the results as `tool` messages, and call the API again. Pass `user_id` instead for tools fetched with `tools.get()`. See the [docs page](https://docs.composio.dev/docs/providers/openai) for the full example. |
| 66 | |
| 67 | ## Links |
| 68 | |
| 69 | - OpenAI provider docs: https://docs.composio.dev/docs/providers/openai |
| 70 | - Composio docs: https://docs.composio.dev |