Package org.apache.lucene.codecs.lucene102

Class OffHeapBinarizedVectorValues

java.lang.Object
org.apache.lucene.index.KnnVectorValues
org.apache.lucene.index.ByteVectorValues
org.apache.lucene.codecs.lucene102.OffHeapBinarizedVectorValues
public abstract class OffHeapBinarizedVectorValues extends ByteVectorValues
Binarized vector values loaded from off-heap
NOTE: This API is for internal purposes only and might change in incompatible ways in the next release.

  • Method Details

    • dimension

      public int dimension()
      Description copied from class: KnnVectorValues
      Return the dimension of the vectors
      Specified by:
      dimension in class KnnVectorValues

    • size

      public int size()
      Description copied from class: KnnVectorValues
      Return the number of vectors for this field.
      Specified by:
      size in class KnnVectorValues
      Returns:
      the number of vectors returned by this iterator

    • vectorValue

      public byte[] vectorValue(int targetOrd) throws IOException
      Description copied from class: ByteVectorValues
      Return the vector value for the given vector ordinal which must be in [0, size() - 1], otherwise IndexOutOfBoundsException is thrown. The returned array may be shared across calls.
      Specified by:
      vectorValue in class ByteVectorValues
      Returns:
      the vector value
      Throws:
      IOException

    • discretizedDimensions

      public int discretizedDimensions()

    • getCentroidDP

      public float getCentroidDP()

    • getCorrectiveTerms

      public OptimizedScalarQuantizer.QuantizationResult getCorrectiveTerms(int targetOrd) throws IOException
      Retrieve the corrective terms for the given vector ordinal. For the dot-product family of distances, the corrective terms are, in order
      • the lower optimized interval
      • the upper optimized interval
      • the dot-product of the non-centered vector with the centroid
      • the sum of quantized components
      For euclidean:
      • the lower optimized interval
      • the upper optimized interval
      • the l2norm of the centered vector
      • the sum of quantized components
      Parameters:
      targetOrd - the vector ordinal
      Returns:
      the corrective terms
      Throws:
      IOException - if an I/O error occurs

    • getQuantizer

      public OptimizedScalarQuantizer getQuantizer()
      Returns:
      the quantizer used to quantize the vectors

    • getCentroid

      public float[] getCentroid()

    • getVectorByteLength

      public int getVectorByteLength()
      Description copied from class: KnnVectorValues
      Returns the vector byte length, defaults to dimension multiplied by float byte size
      Overrides:
      getVectorByteLength in class KnnVectorValues

    • scorer

      public abstract VectorScorer scorer(float[] query) throws IOException
      Return a VectorScorer for the given query vector.
      Parameters:
      query - the query vector
      Returns:
      a VectorScorer instance or null
      Throws:
      IOException

    • copy

      public abstract org.apache.lucene.codecs.lucene102.BinarizedByteVectorValues copy() throws IOException
      Description copied from class: KnnVectorValues
      Creates a new copy of this KnnVectorValues. This is helpful when you need to access different values at once, to avoid overwriting the underlying vector returned.
      Specified by:
      copy in class ByteVectorValues
      Throws:
      IOException