mayya-sharipova commented on PR #947: URL: https://github.com/apache/lucene/pull/947#issuecomment-1156532534
@msokolov Thanks for your work, this is a very exciting feature. Really looking forward to it. Extra benefit – less disk space used for vector values. Overall, this PR looks very good to me. I just have several questions - During merging when writing a merged vector field it looks like we first expand vector values only to again to compress them later? Would be nice to avoid this. - Not sure if possible at this stage, but it would be nice if `HnswGraphBuilder` and `HnswGraphSearcher` were not aware of different calculations needed for different similarity functions, and refer all this calculations (dotProduct(BytesRef a..)) to `VectorSimilarityFunction` -- 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-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
