Dense and sparse retrieval with Qdrant Query API
A retrieval recipe for merging candidate lists from multiple vector representations in one request.
Published by Qdrant
How to use it
Index dense and sparse vectors under the same chunk IDs. Use separate prefetch queries, then fuse their ranked hits at the final query stage.
Compare dense-only and sparse-only baselines before enabling rank fusion. Keep the filters and candidate limits the same across runs so the improvement can be attributed to the merge.
- Compatibility
- Qdrant, Python, REST
- Components
- Hybrid retrieval, Sparse vectors, Reciprocal rank fusion
- Access
- Local or managed Qdrant with compatible Query API and embedding models.