Marvin Files

What's New

OpenAI Observability Integration (Beta)

Added marvin.beta.observability.openai module that enables tracing Marvin agent calls to OpenAI's observability dashboard. When running inside Prefect flows/tasks, it automatically captures runtime context (flow_run_id, task_run_id, deployment info) and sends it as request metadata.

Usage:

:::python
from prefect import flow, task
import marvin
from marvin.beta.observability.openai import observable

agent = marvin.Agent(name="analyst", model="openai:gpt-4o")

@task
async def summarize(text: str) -> str:
    return await observable(agent).run_async(f"Summarize: {text}")

@flow
async def my_pipeline(document: str):
    return await summarize(document)

View requests at https://platform.openai.com/logs and filter by prefect.flow_run.id to see all AI calls from one flow run.

Installation:

:::bash
uv add "marvin[prefect]"

Full Changelog

https://github.com/PrefectHQ/marvin/compare/v3.2.5...v3.2.6