Skip to content

Add fallback support to Lucene104ScalarQuantizedVectorsFormat getFloatVectorValues when there are no full-precision vectors present #15415

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Nov 13, 2025
Merged

Add fallback support to Lucene104ScalarQuantizedVectorsFormat getFloatVectorValues when there are no full-precision vectors present #15415

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
02701df
Add fallback support to Lucene104ScalarQuantizedVectorsFormat.getFloa…
Nov 11, 2025
baa8968
Removed some unused params and tidy changes
Nov 11, 2025
7077781
Added entry in Changes.txt
Nov 11, 2025
8c9da62
Added name in Changes.txt log
Nov 11, 2025
fc00b21
Addressed comments
Nov 12, 2025
30559bc
Renamed function params
Nov 12, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions lucene/CHANGES.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,6 +176,9 @@ New Features
`Lucene104HnswScalarQuantizedVectorsFormat(ScalarEncoding.SINGLE_BIT_QUERY_NIBBLE, int, int)`
(Ben Trent)

* GITHUB#15415: Add fallback support to Lucene104ScalarQuantizedVectorsFormat getFloatVectorValues when there are
no full-precision vectors present
Copy link
Member

@benwtrent benwtrent Nov 12, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please add your name for posterity :)

Copy link
Contributor Author

@Pulkitg64 Pulkitg64 Nov 12, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh I missed it. Fixed in next revision.


Improvements
---------------------
* GITHUB#15148: Add support uint8 distance and allow 8 bit scalar quantization (Trevor McCulloch)
Expand Down
19 changes: 18 additions & 1 deletion ...re/src/java/org/apache/lucene/codecs/lucene104/Lucene104ScalarQuantizedVectorsReader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,6 +210,23 @@ public FloatVectorValues getFloatVectorValues(String field) throws IOException {
+ " expected: "
+ VectorEncoding.FLOAT32);
}

FloatVectorValues rawFloatVectorValues = rawVectorsReader.getFloatVectorValues(field);

if (rawFloatVectorValues.size() == 0) {
return OffHeapScalarQuantizedFloatVectorValues.load(
fi.ordToDocDISIReaderConfiguration,
fi.dimension,
fi.size,
fi.scalarEncoding,
fi.similarityFunction,
vectorScorer,
fi.centroid,
fi.vectorDataOffset,
fi.vectorDataLength,
quantizedVectorData);
}

OffHeapScalarQuantizedVectorValues sqvv =
OffHeapScalarQuantizedVectorValues.load(
fi.ordToDocDISIReaderConfiguration,
Expand All @@ -224,7 +241,7 @@ public FloatVectorValues getFloatVectorValues(String field) throws IOException {
fi.vectorDataOffset,
fi.vectorDataLength,
quantizedVectorData);
return new ScalarQuantizedVectorValues(rawVectorsReader.getFloatVectorValues(field), sqvv);
return new ScalarQuantizedVectorValues(rawFloatVectorValues, sqvv);
}

@Override
Expand Down
Loading