You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@lucene.apache.org by GitBox <gi...@apache.org> on 2022/06/08 15:05:42 UTC

[GitHub] [lucene] msokolov commented on pull request #947: LUCENE-10577: enable quantization of HNSW vectors to 8 bits

msokolov commented on PR #947:
URL: https://github.com/apache/lucene/pull/947#issuecomment-1150043099

   If folks have time to review, that would be great. The main thing to focus on I think is 
   
   1. how the HnswGraphSearcher/Writer implementation is forked into `float[]` and `BytesRef` using generics
   2. adding a VERSION to the index format so we can handle back-compat in a reasonable way
   3. the fact that some of the details of VectorSimilarityFunction are now directly handled in util.hnsw -- I didn't see a better way, but it blurs the abstraction boundary


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: issues-unsubscribe@lucene.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@lucene.apache.org
For additional commands, e-mail: issues-help@lucene.apache.org