Class QuantizedByteVectorValues

java.lang.Object
org.apache.lucene.search.DocIdSetIterator
org.apache.lucene.util.quantization.QuantizedByteVectorValues
Direct Known Subclasses:
OffHeapQuantizedByteVectorValues

public abstract class QuantizedByteVectorValues extends DocIdSetIterator
A version of ByteVectorValues, but additionally retrieving score correction offset for Scalar quantization scores.
WARNING: This API is experimental and might change in incompatible ways in the next release.
  • Constructor Details

    • QuantizedByteVectorValues

      public QuantizedByteVectorValues()
  • Method Details

    • getScoreCorrectionConstant

      public abstract float getScoreCorrectionConstant() throws IOException
      Throws:
      IOException
    • vectorValue

      public abstract byte[] vectorValue() throws IOException
      Throws:
      IOException
    • dimension

      public abstract int dimension()
      Return the dimension of the vectors
    • size

      public abstract int size()
      Return the number of vectors for this field.
      Returns:
      the number of vectors returned by this iterator
    • cost

      public final long cost()
      Description copied from class: DocIdSetIterator
      Returns the estimated cost of this DocIdSetIterator.

      This is generally an upper bound of the number of documents this iterator might match, but may be a rough heuristic, hardcoded value, or otherwise completely inaccurate.

      Specified by:
      cost in class DocIdSetIterator
    • 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