Rewrite README to highlight the two fork-specific features:
- BM25 hybrid search (dense + sparse vectors with RRF)
- Automatic project tagging with metadata.project index
Also update the environment variables table with all current options.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add explicit `project` parameter to qdrant-store tool (default: "global")
- Auto-inject project name into metadata for every stored record
- Create keyword payload index on metadata.project for efficient filtering
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- 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
* add configurable filters
* hello to hr department
* rollback debug code
* add arbitrary filter
* dont consider fields without conditions
* in and except condition
* proper annotation types for optional and list fields
* fix types import
* skip non-required fields
* fix: fix match except condition, fix boolean filter
* fix: apply ruff
* fix: make condition optional in filterable field
* fix: do not set default value for required fields (#63)
* fix: do not set default value for required fields
* fix: temp fix fastmcp to <2.8.0 cause of the breaking changes in the api
* fix: add missing changes to pyproject.toml
* fix: downgrade fastmcp even further to <2.7.0
---------
Co-authored-by: George Panchuk <george.panchuk@qdrant.tech>
Co-authored-by: George <panchuk.george@outlook.com>
* add developer mode instruction to readme
* Make a custom MCP wrapper around FastMCP add more settings, some improvements
* upd test and readme
* review fixes
* 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>
* Allow setting up the tool descriptions with env variables
* Document the env variables as a table in README
* Link settings.py in README.md
* Allow to choose transport protocol: stdio or sse
* Fix metadata handling in Cursor
* Improve README to cover more cases
* Add info about Cursor rules
* Fix Github note type
- 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
