Add batch search

[Fanchouille]

First of all, thanks a lot for your work, it's really great !
In order to user the search on lots of documents, it would be great if we could :

• [ search batches of elements] : embeddings.search(queries, top_k) which would return a list of top_k results for each query in queries
• [use fastest lib to do so ] (I use hnsw implem of nmslib which provides a batch search and great implementation of hnsw).

Keep up the good work !

[davidmezzetti]

Thank you for the suggestion and kind words! Will look into batch search.

Regarding nmslib, the reason I went with the header library was that nmslib was fuzzy on the license. It mentioned a core piece was GPL. I'll research this further.

[Fanchouille]

Thanks for your answer
Sorry I did not look at the license issue.

As hnswlib is created by the same team, it provides batched queries with knn_query :

I believe Faiss supports it the same way by just passing matrix queries instead of vector query.
Annoy doesn't seem to expose such a functionality.

[davidmezzetti]

Better late than never but this is addressed in v2.0 of txtai