Maurício Maia
Maurício Maia
Add ability to filter pgvector documents by metadata.
The `CollectionStore` for `PGVector` has a `cmetadata` field but it's never used. This PR add the ability to save metadata information to the collection.
It would be nice to support [pgvector](https://github.com/pgvector/pgvector) as a data store.
Closes #36 by adding PostgreSQL pgvector as a datastore option. - Supports any PostgreSQL standard connection (self-hosted or [hosted providers](https://github.com/pgvector/pgvector/issues/54)) - Uses SQAlchemy for abstraction - Uses a `JSONB` field...
I believe the recently released [Cohere's Wikipedia Embedding Archives ](https://txt.cohere.com/embedding-archives-wikipedia/)could be a good addition to the benchmarks dataset. It's note worth the multi language nature of the dataset. Wikipedia |...