Back to GigaRAG

Connect an agent

Give an AI tool access to your GigaRAG Workspace, so it can search, read and write your memos while it works.

Mistral API

Register GigaRAG as a connector and use it from the Mistral Agents and Conversations API.

Use it in code

The snippet has your key in it so it runs as pasted. Move it to an environment variable before the code is committed or shared.

  1. 1.

    Install the SDK

    pip install mistralai
  2. 2.

    Register GigaRAG once, then use it in a conversation

    import os
from mistralai import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"])

client.beta.connectors.create(
    name="gigarag",
    server="https://mcp.gigarag.com/mcp",
    visibility="private",
    headers={"Authorization": "Bearer <api-key>"},
)

response = client.beta.conversations.start(
    model="mistral-medium-latest",
    inputs="List my GigaRAG buckets.",
    tools=[{"type": "connector", "connector_id": "gigarag"}],
)
print(response.outputs)

Check it worked

Send this once it is connected. An answer drawn from your workspace means the connection is live.

Run it. The model should answer with your GigaRAG buckets.

Written from the official docs: Connectors