Module org.elasticsearch.simdvec

Package org.elasticsearch.simdvec.internal

Class MemorySegmentES92PanamaInt7VectorsScorer

java.lang.Object

org.elasticsearch.simdvec.ES92Int7VectorsScorer

org.elasticsearch.simdvec.internal.MemorySegmentES92PanamaInt7VectorsScorer

Direct Known Subclasses:

MemorySegmentES92NativeInt7VectorsScorer

public sealed class MemorySegmentES92PanamaInt7VectorsScorer
extends ES92Int7VectorsScorer
permits MemorySegmentES92NativeInt7VectorsScorer

Panamized scorer for 7-bit quantized vectors stored as an IndexInput.

Field Summary

Fields inherited from class org.elasticsearch.simdvec.ES92Int7VectorsScorer

dimensions, in, SEVEN_BIT_SCALE

Constructor Summary

Constructors

Constructor	Description
MemorySegmentES92PanamaInt7VectorsScorer(org.apache.lucene.store.IndexInput in, int dimensions, int bulkSize)

Method Summary

Modifier and Type	Method	Description
protected byte[]	getScratch(int len)
long	int7DotProduct(byte[] q)	compute the quantize distance between the provided quantized query and the quantized vector that is read from the wrapped IndexInput.
void	int7DotProductBulk(byte[] q, int count, float[] scores)	compute the quantize distance between the provided quantized query and the quantized vectors that are read from the wrapped IndexInput.
void	scoreBulk(byte[] q, float queryLowerInterval, float queryUpperInterval, int queryComponentSum, float queryAdditionalCorrection, org.apache.lucene.index.VectorSimilarityFunction similarityFunction, float centroidDp, float[] scores, int bulkSize)	compute the distance between the provided quantized query and the quantized vectors that are read from the wrapped IndexInput.

Methods inherited from class org.elasticsearch.simdvec.ES92Int7VectorsScorer

applyCorrections, score

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

MemorySegmentES92PanamaInt7VectorsScorer

public MemorySegmentES92PanamaInt7VectorsScorer(org.apache.lucene.store.IndexInput in,
 int dimensions,
 int bulkSize)

Method Details

getScratch

protected byte[] getScratch(int len)

int7DotProduct

public long int7DotProduct(byte[] q)
                    throws IOException

Description copied from class: ES92Int7VectorsScorer

compute the quantize distance between the provided quantized query and the quantized vector that is read from the wrapped IndexInput.

Overrides:

int7DotProduct in class ES92Int7VectorsScorer

Throws:

IOException

int7DotProductBulk

public void int7DotProductBulk(byte[] q,
 int count,
 float[] scores)
                        throws IOException

Description copied from class: ES92Int7VectorsScorer

compute the quantize distance between the provided quantized query and the quantized vectors that are read from the wrapped IndexInput. The number of quantized vectors to read is determined by {code count} and the results are stored in the provided scores array.

Overrides:

int7DotProductBulk in class ES92Int7VectorsScorer

Throws:

IOException

scoreBulk

public void scoreBulk(byte[] q,
 float queryLowerInterval,
 float queryUpperInterval,
 int queryComponentSum,
 float queryAdditionalCorrection,
 org.apache.lucene.index.VectorSimilarityFunction similarityFunction,
 float centroidDp,
 float[] scores,
 int bulkSize)
               throws IOException

Description copied from class: ES92Int7VectorsScorer

compute the distance between the provided quantized query and the quantized vectors that are read from the wrapped IndexInput.

The number of vectors to score is defined by #bulkSize. The expected format of the input is as follows: First the quantized vectors are read from the input,then all the lower intervals as floats, then all the upper intervals as floats, then all the target component sums as shorts, and finally all the additional corrections as floats.

The results are stored in the provided scores array.

Overrides:

scoreBulk in class ES92Int7VectorsScorer

Throws:

IOException