Module org.elasticsearch.simdvec
Package org.elasticsearch.simdvec

Class ESNextOSQVectorsScorer

java.lang.Object
org.elasticsearch.simdvec.ESNextOSQVectorsScorer
public class ESNextOSQVectorsScorer extends Object
Scorer for quantized vectors stored as an IndexInput.

  • Field Summary

    Fields
    Modifier and Type
    Field
    Description
    protected final float[]
    additionalCorrections
     
    protected static final float[]
    BIT_SCALES
     
    static final int
    BULK_SIZE
     
    protected final int
    dimensions
     
    protected final org.apache.lucene.store.IndexInput
    in
    The wrapper IndexInput.
    protected final byte
    indexBits
     
    protected final int
    length
     
    protected final float[]
    lowerIntervals
     
    protected final byte
    queryBits
     
    protected final int[]
    targetComponentSums
     
    protected final float[]
    upperIntervals
     

  • Constructor Summary

    Constructors
    Constructor
    Description
    ESNextOSQVectorsScorer(org.apache.lucene.store.IndexInput in, byte queryBits, byte indexBits, int dimensions, int dataLength)
    Sole constructor, called by sub-classes.

  • Method Summary

    Modifier and Type
    Method
    Description
    long
    quantizeScore(byte[] q)
    compute the quantize distance between the provided quantized query and the quantized vector that is read from the wrapped IndexInput.
    void
    quantizeScoreBulk(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.
    float
    score(float queryLowerInterval, float queryUpperInterval, int queryComponentSum, float queryAdditionalCorrection, org.apache.lucene.index.VectorSimilarityFunction similarityFunction, float centroidDp, float lowerInterval, float upperInterval, int targetComponentSum, float additionalCorrection, float qcDist)
    Computes the score by applying the necessary corrections to the provided quantized distance.
    float
    scoreBulk(byte[] q, float queryLowerInterval, float queryUpperInterval, int queryComponentSum, float queryAdditionalCorrection, org.apache.lucene.index.VectorSimilarityFunction similarityFunction, float centroidDp, float[] scores)
    compute the distance between the provided quantized query and the quantized vectors that are read from the wrapped IndexInput.

    Methods inherited from class java.lang.Object

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

  • Field Details

    • BULK_SIZE

      public static final int BULK_SIZE
      See Also:

    • BIT_SCALES

      protected static final float[] BIT_SCALES

    • in

      protected final org.apache.lucene.store.IndexInput in
      The wrapper IndexInput.

    • queryBits

      protected final byte queryBits

    • indexBits

      protected final byte indexBits

    • length

      protected final int length

    • dimensions

      protected final int dimensions

    • lowerIntervals

      protected final float[] lowerIntervals

    • upperIntervals

      protected final float[] upperIntervals

    • targetComponentSums

      protected final int[] targetComponentSums

    • additionalCorrections

      protected final float[] additionalCorrections

  • Constructor Details

    • ESNextOSQVectorsScorer

      public ESNextOSQVectorsScorer(org.apache.lucene.store.IndexInput in, byte queryBits, byte indexBits, int dimensions, int dataLength)
      Sole constructor, called by sub-classes.

  • Method Details

    • quantizeScore

      public long quantizeScore(byte[] q) throws IOException
      compute the quantize distance between the provided quantized query and the quantized vector that is read from the wrapped IndexInput.
      Throws:
      IOException

    • quantizeScoreBulk

      public void quantizeScoreBulk(byte[] q, int count, float[] scores) throws IOException
      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.
      Throws:
      IOException

    • score

      public float score(float queryLowerInterval, float queryUpperInterval, int queryComponentSum, float queryAdditionalCorrection, org.apache.lucene.index.VectorSimilarityFunction similarityFunction, float centroidDp, float lowerInterval, float upperInterval, int targetComponentSum, float additionalCorrection, float qcDist)
      Computes the score by applying the necessary corrections to the provided quantized distance.

    • scoreBulk

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

      Throws:
      IOException