benwtrent opened a new pull request, #13197:
URL: https://github.com/apache/lucene/pull/13197
So, there are a handful of new and interesting things that this PR adds:
- Confidence interval optimizations, unlocked even smaller quantization
bytes
- New int4 codec which is 8x smaller than float32 with exceptionally good
recall & faster search
But, its not complete yet. While I was finishing up the code here, it came
to my mind, why is this its own codec? Why shouldn't we add a new option to
`Lucene99ScalarQuantizedVectorsFormat` (really it would be
`Lucene911ScalarQuantizedVectorsFormat`) that allows the quantization `bits` to
be set. I know we don't want a ton of configuration for each codec, but to me
this seemed reasonable.
What do you think @jpountz?
--
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
