Deploypod Python SDK

The Python client for the Deploypod API. Run your AI agents from code, and manage their instructions, tools and knowledge bases.

pip install deploypod

Python 3.9 or newer.

Sign in

Ask your Deploypod administrator for an application (app_id, app_secret) and your organization's number. The client gets the access token itself and renews it before it expires.

from deploypod import DeploypodClient

client = DeploypodClient(
    org_id="42",
    app_id="YOUR_APP_ID",
    app_secret="YOUR_APP_SECRET",
)

Keep app_secret out of your code: read it from the environment.

export DEPLOYPOD_ORG_ID=42
export DEPLOYPOD_APP_ID=...
export DEPLOYPOD_APP_SECRET=...

from deploypod import get_client_from_env

client = get_client_from_env()

Already have an access token? Pass token="..." instead of the app credentials. For an on-premises installation, pass base_url="https://your-host/api".

Run an agent

for agent in client.agents.list():
    print(agent.uuid, agent.name)

result = client.agents.run(
    "AGENT_UUID",
    "How many days of annual leave do I have?",
    run_exploration=True,
    timeout=300,
)
print(result["result_summary"])

run waits for the answer. Other request fields go in as keyword arguments, for example output_schema={...} to get the answer as JSON in result["final_emit"]. Requests through deploypod.ai are cut after 100 seconds; for longer work (web research, presentations) use the WebSocket API.

Errors

Every error is a deploypod.DeploypodError with status_code and detail. Subclasses: AuthenticationError (401/403), NotFoundError, ValidationError, ConflictError, LicenseError, ServerError.

Documentation

Full guides, the REST and WebSocket APIs, and the chat widget: https://docs.deploypod.ai/en/

License

MIT