Skip to main content
FastAPI AI Kit
All integrationsVector Store

Qdrant Integration

Production vector search with Qdrant — swap from pgvector with one env var.

FastAPI AI Kit supports both pgvector and Qdrant for vector storage. Switch between them by changing VECTOR_STORE in your config — no code changes required.

Setup in 4 steps

  1. 1Set VECTOR_STORE=qdrant and QDRANT_URL in your .env
  2. 2The RAG pipeline automatically routes to Qdrant collections
  3. 3Create collections via the kit's management CLI or API
  4. 4Batch ingest and incremental indexing work unchanged

What's included

  • Drop-in swap from pgvector — same RAG API, different backend
  • Qdrant collections managed via kit's config and admin endpoints
  • Filtered vector search (metadata + similarity) supported
  • Async Qdrant client with connection pooling
  • Payload indexing for efficient metadata filtering

Code example

example.py
# .env — just change the vector store
VECTOR_STORE=qdrant
QDRANT_URL=http://localhost:6333
QDRANT_API_KEY=optional-key

# Same RAG API — zero code changes
await rag.ingest(source="doc.pdf", collection="my-kb")
result = await rag.query(question="...", collection="my-kb")

Full documentation: /docs/llm-providers

Qdrant integration pre-wired and ready.

FastAPI AI Kit ships with Qdrant 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