iprithv commented on code in PR #16065:
URL: https://github.com/apache/lucene/pull/16065#discussion_r3270628699
##########
lucene/sandbox/src/java/org/apache/lucene/sandbox/codecs/faiss/FaissLibraryNativeImpl.java:
##########
@@ -275,31 +268,34 @@ private interface FloatToFloatFunction {
private final Arena arena;
private final MemorySegment indexPointer;
private final FloatToFloatFunction scaler;
+ private final VectorSimilarityFunction function;
+ private final int dimension;
private boolean closed;
- private Index(MemorySegment indexPointer) {
+ private Index(MemorySegment indexPointer, VectorSimilarityFunction
function) {
this.arena = Arena.ofShared();
this.indexPointer =
indexPointer
// Ensure timely cleanup
.reinterpret(arena, wrapper::faiss_Index_free);
-
- // Get underlying function
- int metricType = wrapper.faiss_Index_metric_type(indexPointer);
- VectorSimilarityFunction function = metricToFunction(metricType);
Review Comment:
so both are faiss based, not lucene native.
in faiss terms:
flat = exact search (just brute force)
hnsw = approximate search using faiss’s own hnsw graph
both use the same build params (efConstruction=128, M=16) and search params
(efSearch=64). flat is mainly there as a baseline to show recall is ~1.0, so
cosine setup is working correctly.
--
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]
