Getting Started

Python

Build durable workflows and AI agents in Python with the Vercel SDK.

The Python SDK is currently in beta. APIs and behavior may change.

You can build durable workflows in Python using the vercel Python SDK. Your workflow code can pause, resume, and maintain state, just like the JavaScript and TypeScript Workflow SDK.

Getting started

Add the vercel package and workflow entrypoint to pyproject.toml:

[project]
requires-python = ">=3.12"
dependencies = ["vercel"]

[[tool.vercel.workflows]]
entrypoint = "app.workflows:wf"

The workflow entrypoint uses the module:object format and points to the exported Workflows registry.

Workflows

A workflow is a stateful function that coordinates multi-step logic over time. Create a Workflows instance and use the @wf.workflow decorator to mark a function as durable:

from vercel import workflow

wf = workflow.Workflows()
from app.workflow import wf

@wf.workflow
async def ai_content_workflow(*, topic: str):
    draft = await generate_draft(topic=topic)
    summary = await summarize_draft(draft=draft)

    return {
        "draft": draft,
        "summary": summary,
    }

Export the registry from the workflow package and import the module containing your workflow so its definitions are registered:

from app.workflow import wf
from app.workflows import ai_content_workflow

__all__ = ["ai_content_workflow", "wf"]

Under the hood, the workflow compiles into a route that orchestrates execution. All inputs and outputs are recorded in an event log. If a deploy or crash happens, the system replays execution deterministically from where it stopped.

Steps

A step is a stateless function that runs a unit of durable work inside a workflow. Use @wf.step to mark a function as a step:

import random
from app.workflow import wf

@wf.step
async def generate_draft(*, topic: str):
    return await ai_generate(prompt=f"Write a blog post about {topic}")

@wf.step
async def summarize_draft(*, draft: str):
    summary = await ai_summarize(text=draft)

    # Simulate a transient error. The step automatically retries.
    if random.random() < 0.3:
        raise Exception("Transient AI provider error")

    return summary

Each step compiles into an isolated route. While the step executes, the workflow suspends without consuming resources. When the step completes, the workflow resumes automatically where it left off.

Sleep

Sleep pauses a workflow for a specified duration without consuming compute resources:

from datetime import timedelta

from app.workflow import wf
from vercel import workflow

@wf.workflow
async def ai_refine_workflow(*, draft_id: str):
    draft = await fetch_draft(draft_id)

    await workflow.sleep(timedelta(days=7))  # Wait 7 days to gather more signals.

    refined = await refine_draft(draft)

    return {
        "draft_id": draft_id,
        "refined": refined,
    }

The parameter accepts four forms:

FormDescriptionExample
strHuman-readable duration string"2 days", "1w", "1h 30m"
int or floatSeconds from now5 (5 seconds)
datetime.timedeltaDuration from nowtimedelta(days=7)
datetime.datetimeAbsolute wake-up time (must be timezone-aware)datetime(2025, 1, 1, tzinfo=UTC)

The string form accepts one or more <value><unit> pairs. Supported units:

DurationUnit
Millisecondsms
Secondss, second, seconds
Minutesm, minute, minutes
Hoursh, hour, hours
Daysd, day, days
Weeksw, week, weeks

sleep() must be called from the workflow body, not from inside a step. Calling it from a step raises a RuntimeError.

The sleep consumes no resources. The workflow resumes automatically when the time expires.

Hooks

A hook lets a workflow wait for external events such as user actions, webhooks, or third-party API responses.

Define a hook model with Pydantic and workflow.BaseHook:

import typing

import pydantic
from app.workflow import wf
from vercel import workflow

class Approval(pydantic.BaseModel, workflow.BaseHook):
    """Human approval for AI-generated drafts"""

    decision: typing.Literal["approved", "changes"]
    notes: str | None = None

@wf.workflow
async def ai_approval_workflow(*, topic: str):
    draft = await generate_draft(topic=topic)

    # Wait for human approval events
    async for event in Approval.wait(token="draft-123"):
        if event.decision == "approved":
            await publish_draft(draft)
            break

        revised = await refine_draft(draft, event.notes)
        await publish_draft(revised)

Resume the workflow when data arrives:

from app.workflows.approval import Approval

@app.post("/api/resume")
async def resume(approval: Approval):
    """Resume the workflow when an approval is received"""

    await approval.resume("draft-123")
    return {"ok": True}

When a hook receives data, the workflow resumes automatically. You don't need polling, message queues, or manual state management.

Next steps

PreviousViteNextFoundations