Package org.apache.lucene.util.quantization
package org.apache.lucene.util.quantization
Provides quantization methods for scaling vector values to smaller data types and possibly fewer
dimensions
-
ClassDescriptionA version of
ByteVectorValuesfor Scalar quantization scores.A version ofBaseQuantizedByteVectorValues, but additionally retrieving score correction offset for Scalar quantization scores.This is a scalar quantizer that optimizes the quantization intervals for a given vector.Quantization result containing the lower and upper interval bounds, the additional correctionScalar quantized byte vector valuesAllowed encodings for scalar quantization.Quantized vector readerCalculates and adjust the scores correctly for quantized vectors given the scalar quantization parametersCompares two byte vectorsCalculates dot product on quantized vectors, applying the appropriate correctionsCalculates euclidean distance on quantized vectors, applying the appropriate correctionsCalculates max inner product on quantized vectors, applying the appropriate correctionsWill scalar quantize float vectors into `int8` byte values.