Vamshi Vijay Nakkirtha

Good catch! This seem to have potential to cut down large memory footprint. Agree let's prioritize for faiss. Am assuming this feature will be similar to incremental graph construction in...

LGTM! Thanks for the deep dive. Looking forward to benchmarks to quantify the savings!

@navneet1v exciting results. Did we verify the recall is intact and what is the observation on the build times with and with out the fix?

@shashank-sachan If you are referring to issue with elasticsearch-js client, we do not own this client and we would recommend migrate to opensearch-js client.

+1 to Jack's comment above. Its high time we see vector data type as first class citizen(part of core) for the OpenSearch similar to what Lucene has done. I would...

@nknize I would prefer just keeping the field name same ```knn_vector``` to avoid any confusion and keep it smooth migration. But open to suggestions.

@pajuric thats right. Can we create like a parter blog?

@BobakMariusz will you be able to help contribute?

Good catch!! Thanks @heemin32

Moving to 2.16.