Celery Integration

Async task processing wired up and ready for background LLM jobs.

FastAPI AI Kit ships with Celery + Redis pre-configured. Offload long-running LLM chains, document processing, or email sending to workers — with retry logic and failure handling.

Setup in 4 steps

1REDIS_URL is the Celery broker — set it in your .env
2Workers start via docker-compose or `celery -A app.worker worker`
3Decorate functions with @celery.task to run in the background
4Job status queryable via the included status endpoint

What's included

Celery app pre-configured with Redis broker and result backend
Retry logic with exponential backoff on failures
Beat scheduler for cron-style recurring jobs
Task progress updates via Redis pub/sub
Flower dashboard wiring included for task monitoring

Code example

example.py

# Offload long LLM tasks to Celery workers
@celery.task(bind=True, max_retries=3)
def process_large_document(self, doc_id: str):
    try:
        text = storage.read(doc_id)
        chunks = splitter.split(text)
        for chunk in chunks:
            embedding = openai.embed(chunk)
            vector_store.upsert(doc_id, chunk, embedding)
    except Exception as exc:
        self.retry(exc=exc, countdown=2 ** self.request.retries)

# Enqueue from your API endpoint (non-blocking)
@router.post("/v1/documents/ingest")
async def ingest(file: UploadFile):
    doc_id = await storage.upload(file)
    process_large_document.delay(doc_id)
    return {"doc_id": doc_id, "status": "processing"}

Full documentation: /docs/project-structure

Celery integration pre-wired and ready.

FastAPI AI Kit ships with Celery configured out of the box. No manual setup required.

Ready to ship your AI backend this weekend?

Join developers who skipped weeks of boilerplate and went straight to building.

Read the docs

No subscriptions · One-time payment · Lifetime updates