- 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>
* new: update type hints
* fix: do not pass location and path to qdrant client, and do not accept them together
* new: update settings tests
* fix: revert removal of local path
* Allow passing the collection name in each request to override the default
* Allow getting the collection names in QdrantConnector
* get vector size from model description
* ruff format
* add isort
* apply pre-commit hooks
---------
Co-authored-by: generall <andrey@vasnetsov.com>
- Modify `serve()` function to accept a pre-configured QdrantConnector
- Update `create_embedding_provider()` to simplify model name handling
- Improve error handling and parameter passing in server tools
- Restructure main function to create connector and server more explicitly