[GitHub] [lucene] mayya-sharipova commented on a diff in pull request #947: LUCENE-10577: enable quantization of HNSW vectors to 8 bits

[GitBox]

mayya-sharipova commented on code in PR #947:
URL: https://github.com/apache/lucene/pull/947#discussion_r923672692


##########
lucene/core/src/java/org/apache/lucene/codecs/lucene93/Lucene93HnswVectorsReader.java:
##########
@@ -169,7 +173,12 @@ private void validateFieldEntry(FieldInfo info, FieldEntry 
fieldEntry) {
               + fieldEntry.dimension);
     }
 
-    long numBytes = (long) fieldEntry.size() * dimension * Float.BYTES;
+    long numBytes;
+    switch (fieldEntry.vectorEncoding) {
+      case BYTE -> numBytes = (long) fieldEntry.size() * dimension;
+      case FLOAT32 -> numBytes = (long) fieldEntry.size() * dimension * 
Float.BYTES;
+      default -> throw new AssertionError("unknown vector encoding " + 
fieldEntry.vectorEncoding);

Review Comment:
   Should we also update the error message that follows for `BYTE` case?



-- 
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