shubhamvishu commented on code in PR #16092:
URL: https://github.com/apache/lucene/pull/16092#discussion_r3278674275
##########
lucene/core/src/java/org/apache/lucene/codecs/lucene104/Lucene104ScalarQuantizedVectorsReader.java:
##########
@@ -197,6 +213,14 @@ public RandomVectorScorer getRandomVectorScorer(String
field, float[] target) th
if (fi == null) {
return null;
}
+ // Rotate the query vector to match the rotated stored vectors.
+ float[] scoringTarget = target;
+ if (isRotationEnabled(field) && target != null) {
+ HadamardRotation rotation = rotationFor(field, fi.dimension);
+ float[] rotated = new float[target.length];
+ rotation.rotate(target, rotated);
Review Comment:
`rotate` is a `O(d log d)` operation here. I ran the luceneutil without
forceMerge too but I don't have the Cohere results handy anymore(I can pull
those up again). Though I have the results with 4K dim embeddings in multi
segment index. Sharing those below for you reference(will share the Cohere one
also soon). I didn't seem to regress the latency as such. We can do more JMH
benchmarking or whatever could give us more confidence but so far it appears to
be a cheap cost(Idk if the quantization overhead was significant in past).
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
