Milvus Vector Database
An open-source vector database with configurable indexes and scalar fields for filtering retrieval.
Published by Milvus Project
How to use it
Store document IDs and passage text as fields so a search hit can be traced back to a source. Set up a scalar filter for access scope before comparing retrieval relevance.
For a first local prototype, use Milvus Lite through PyMilvus on a supported platform or run the standalone Milvus service. Index and memory needs vary with vector dimensions and search configuration.
- Compatibility
- Python, Docker, PyMilvus
- Components
- Vector database, Metadata filtering, Vector indexes
- Access
- Local library or server. Managed options are separate.