Open
Description
Currently, Ragbits supports sparse embeddings (via the SparseVector
and SparseEmbedder
classes) but none of our vector stores supports this.
- Change the typing of
VectorStoreResult
to acceptSparseVector
(should now be `list[float] | SparseVector) - Add support for sparse embeddings to Qdrant and in_memory vector stores. They should be able to take
Embedder
orSparseEmbedder
and then return the vector aslist[float]
orSparseVector
(depending ont he type of embedder). - Write HOW-TO documentation on using sparse vectors with vector stores
- Update the HOW-TO documentation on hybrid search - resolve both the TODO comments that reference sparse vectors.
Metadata
Metadata
Assignees
Labels
Type
Projects
Status
Ready