Uses of Class
org.apache.lucene.util.quantization.ScalarQuantizer

Packages that use ScalarQuantizer

Package	Description
org.apache.lucene.codecs.hnsw	HNSW vector helper classes.
org.apache.lucene.codecs.lucene99	Lucene 9.9 file format.
org.apache.lucene.util.quantization	Provides quantization methods for scaling vector values to smaller data types and possibly fewer dimensions

Uses of ScalarQuantizer in org.apache.lucene.codecs.hnsw

Methods in org.apache.lucene.codecs.hnsw with parameters of type ScalarQuantizer

Modifier and Type	Method	Description
static float	ScalarQuantizedVectorScorer.quantizeQuery(float[] query, byte[] quantizedQuery, VectorSimilarityFunction similarityFunction, ScalarQuantizer scalarQuantizer)

Constructors in org.apache.lucene.codecs.hnsw with parameters of type ScalarQuantizer

Modifier	Constructor	Description
	ScalarQuantizedRandomVectorScorerSupplier(VectorSimilarityFunction similarityFunction, ScalarQuantizer scalarQuantizer, RandomAccessQuantizedByteVectorValues values)

Uses of ScalarQuantizer in org.apache.lucene.codecs.lucene99

Fields in org.apache.lucene.codecs.lucene99 declared as ScalarQuantizer

Modifier and Type	Field	Description
private final ScalarQuantizer	Lucene99ScalarQuantizedVectorsWriter.OffsetCorrectedQuantizedByteVectorValues.oldScalarQuantizer
private final ScalarQuantizer	Lucene99ScalarQuantizedVectorsWriter.QuantizedFloatVectorValues.quantizer
(package private) final ScalarQuantizer	Lucene99ScalarQuantizedVectorsReader.FieldEntry.scalarQuantizer
private final ScalarQuantizer	Lucene99ScalarQuantizedVectorsWriter.OffsetCorrectedQuantizedByteVectorValues.scalarQuantizer
protected final ScalarQuantizer	OffHeapQuantizedByteVectorValues.scalarQuantizer

Methods in org.apache.lucene.codecs.lucene99 that return ScalarQuantizer

Modifier and Type	Method	Description
(package private) static ScalarQuantizer	Lucene99ScalarQuantizedVectorsWriter.buildScalarQuantizer(FloatVectorValues floatVectorValues, int numVectors, VectorSimilarityFunction vectorSimilarityFunction, Float confidenceInterval, byte bits)
(package private) ScalarQuantizer	Lucene99ScalarQuantizedVectorsWriter.FieldWriter.createQuantizer()
ScalarQuantizer	Lucene99HnswVectorsReader.getQuantizationState(String field)
ScalarQuantizer	Lucene99ScalarQuantizedVectorsReader.getQuantizationState(String fieldName)
private static ScalarQuantizer	Lucene99ScalarQuantizedVectorsWriter.getQuantizedState(KnnVectorsReader vectorsReader, String fieldName)
ScalarQuantizer	OffHeapQuantizedByteVectorValues.getScalarQuantizer()
static ScalarQuantizer	Lucene99ScalarQuantizedVectorsWriter.mergeAndRecalculateQuantiles(MergeState mergeState, FieldInfo fieldInfo, Float confidenceInterval, byte bits)	Merges the quantiles of the segments and recalculates the quantiles if necessary.
(package private) static ScalarQuantizer	Lucene99ScalarQuantizedVectorsWriter.mergeQuantiles(List<ScalarQuantizer> quantizationStates, IntArrayList segmentSizes, byte bits)

Methods in org.apache.lucene.codecs.lucene99 with parameters of type ScalarQuantizer

Modifier and Type	Method	Description
static OffHeapQuantizedByteVectorValues	OffHeapQuantizedByteVectorValues.load(OrdToDocDISIReaderConfiguration configuration, int dimension, int size, ScalarQuantizer scalarQuantizer, VectorSimilarityFunction similarityFunction, FlatVectorsScorer vectorsScorer, boolean compress, long quantizedVectorDataOffset, long quantizedVectorDataLength, IndexInput vectorData)
private Lucene99ScalarQuantizedVectorsWriter.ScalarQuantizedCloseableRandomVectorScorerSupplier	Lucene99ScalarQuantizedVectorsWriter.mergeOneFieldToIndex(SegmentWriteState segmentWriteState, FieldInfo fieldInfo, MergeState mergeState, ScalarQuantizer mergedQuantizationState)
static Lucene99ScalarQuantizedVectorsWriter.MergedQuantizedVectorValues	Lucene99ScalarQuantizedVectorsWriter.MergedQuantizedVectorValues.mergeQuantizedByteVectorValues(FieldInfo fieldInfo, MergeState mergeState, ScalarQuantizer scalarQuantizer)
(package private) static boolean	Lucene99ScalarQuantizedVectorsWriter.shouldRecomputeQuantiles(ScalarQuantizer mergedQuantizationState, List<ScalarQuantizer> quantizationStates)	Returns true if the quantiles of the merged state are too far from the quantiles of the individual states.
(package private) static boolean	Lucene99ScalarQuantizedVectorsWriter.shouldRequantize(ScalarQuantizer existingQuantiles, ScalarQuantizer newQuantiles)	Returns true if the quantiles of the new quantization state are too far from the quantiles of the existing quantization state.

Method parameters in org.apache.lucene.codecs.lucene99 with type arguments of type ScalarQuantizer

Modifier and Type	Method	Description
(package private) static ScalarQuantizer	Lucene99ScalarQuantizedVectorsWriter.mergeQuantiles(List<ScalarQuantizer> quantizationStates, IntArrayList segmentSizes, byte bits)
(package private) static boolean	Lucene99ScalarQuantizedVectorsWriter.shouldRecomputeQuantiles(ScalarQuantizer mergedQuantizationState, List<ScalarQuantizer> quantizationStates)	Returns true if the quantiles of the merged state are too far from the quantiles of the individual states.

Constructors in org.apache.lucene.codecs.lucene99 with parameters of type ScalarQuantizer

Modifier	Constructor	Description
	DenseOffHeapVectorValues(int dimension, int size, ScalarQuantizer scalarQuantizer, boolean compress, VectorSimilarityFunction similarityFunction, FlatVectorsScorer vectorsScorer, IndexInput slice)
(package private)	OffHeapQuantizedByteVectorValues(int dimension, int size, ScalarQuantizer scalarQuantizer, VectorSimilarityFunction similarityFunction, FlatVectorsScorer vectorsScorer, boolean compress, IndexInput slice)
(package private)	OffsetCorrectedQuantizedByteVectorValues(QuantizedByteVectorValues in, VectorSimilarityFunction vectorSimilarityFunction, ScalarQuantizer scalarQuantizer, ScalarQuantizer oldScalarQuantizer)
	QuantizedFloatVectorValues(FloatVectorValues values, VectorSimilarityFunction vectorSimilarityFunction, ScalarQuantizer quantizer)
	SparseOffHeapVectorValues(OrdToDocDISIReaderConfiguration configuration, int dimension, int size, ScalarQuantizer scalarQuantizer, boolean compress, IndexInput dataIn, VectorSimilarityFunction similarityFunction, FlatVectorsScorer vectorsScorer, IndexInput slice)

Uses of ScalarQuantizer in org.apache.lucene.util.quantization

Methods in org.apache.lucene.util.quantization that return ScalarQuantizer

Modifier and Type	Method	Description
static ScalarQuantizer	ScalarQuantizer.fromVectors(FloatVectorValues floatVectorValues, float confidenceInterval, int totalVectorCount, byte bits)	This will read the float vector values and calculate the quantiles.
(package private) static ScalarQuantizer	ScalarQuantizer.fromVectors(FloatVectorValues floatVectorValues, float confidenceInterval, int totalVectorCount, byte bits, int quantizationSampleSize)
static ScalarQuantizer	ScalarQuantizer.fromVectorsAutoInterval(FloatVectorValues floatVectorValues, VectorSimilarityFunction function, int totalVectorCount, byte bits)
ScalarQuantizer	QuantizedVectorsReader.getQuantizationState(String fieldName)
ScalarQuantizer	RandomAccessQuantizedByteVectorValues.getScalarQuantizer()

Methods in org.apache.lucene.util.quantization with parameters of type ScalarQuantizer

Modifier and Type	Method	Description
float	ScalarQuantizer.recalculateCorrectiveOffset(byte[] quantizedVector, ScalarQuantizer oldQuantizer, VectorSimilarityFunction similarityFunction)	Recalculate the old score corrective value given new current quantiles