ChrisHegarty commented on code in PR #14426:
URL: https://github.com/apache/lucene/pull/14426#discussion_r2028417528
##########
lucene/core/src/java/org/apache/lucene/codecs/lucene102/Lucene102BinaryQuantizedVectorsReader.java:
##########
@@ -257,6 +259,19 @@ public long ramBytesUsed() {
return size;
}
+ @Override
+ public Map<String, Long> getOffHeapByteSize(FieldInfo fieldInfo) {
+ Objects.requireNonNull(fieldInfo);
+ var raw = rawVectorsReader.getOffHeapByteSize(fieldInfo);
+ var fieldEntry = fields.get(fieldInfo.name);
+ if (fieldEntry == null) {
+ assert fieldInfo.getVectorEncoding() == VectorEncoding.BYTE;
Review Comment:
I did think that too, however both this format and the ScalarQuantizedFormat
can be used directly with bytes - in which case there is no auto-quantization,
just a byte vector store.
--
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]
