mrkutin/mcp-server-qdrant
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
e9f0a1fa4ad1e4ffb5ca59e76b3996add2f29b45
mcp-server-qdrant/src/mcp_server_qdrant/embeddings
History
Mr. Kutin e9f0a1fa4a
Some checks failed
pre-commit / main (push) Has been cancelled
Details
Run Tests / Python 3.10 (push) Has been cancelled
Details
Run Tests / Python 3.11 (push) Has been cancelled
Details
Run Tests / Python 3.12 (push) Has been cancelled
Details
Run Tests / Python 3.13 (push) Has been cancelled
Details
Add BM25 hybrid search (dense + sparse vectors with RRF) 
- Add SparseTextEmbedding("Qdrant/bm25") to FastEmbedProvider for BM25 tokenization
- Add sparse vector config (IDF modifier) to collection creation
- Store both dense and sparse vectors per document
- Use Qdrant prefetch + Reciprocal Rank Fusion for hybrid search
- Add HYBRID_SEARCH env var (default: false) for backward compatibility

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-03 10:27:52 +03:00
..
__init__.py
Handle parameters with environmental variables only (#24)
2025-03-10 16:36:31 +01:00
base.py
Add BM25 hybrid search (dense + sparse vectors with RRF)
2026-04-03 10:27:52 +03:00
factory.py
Add BM25 hybrid search (dense + sparse vectors with RRF)
2026-04-03 10:27:52 +03:00
fastembed.py
Add BM25 hybrid search (dense + sparse vectors with RRF)
2026-04-03 10:27:52 +03:00
types.py
Handle parameters with environmental variables only (#24)
2025-03-10 16:36:31 +01:00