Package io.qdrant.client.grpc

Interface Points.QuantizationSearchParamsOrBuilder

All Superinterfaces:
com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder
All Known Implementing Classes:
Points.QuantizationSearchParams, Points.QuantizationSearchParams.Builder
Enclosing class:
Points
public static interface Points.QuantizationSearchParamsOrBuilder extends com.google.protobuf.MessageOrBuilder

  • Method Summary

    Modifier and Type
    Method
    Description
    boolean
    getIgnore()
    If set to true, search will ignore quantized vector data
    double
    getOversampling()
    Oversampling factor for quantization.
    boolean
    getRescore()
    If true, use original vectors to re-score top-k results.
    boolean
    hasIgnore()
    If set to true, search will ignore quantized vector data
    boolean
    hasOversampling()
    Oversampling factor for quantization.
    boolean
    hasRescore()
    If true, use original vectors to re-score top-k results.

    Methods inherited from interface com.google.protobuf.MessageLiteOrBuilder

    isInitialized

    Methods inherited from interface com.google.protobuf.MessageOrBuilder

    findInitializationErrors, getAllFields, getDefaultInstanceForType, getDescriptorForType, getField, getInitializationErrorString, getOneofFieldDescriptor, getRepeatedField, getRepeatedFieldCount, getUnknownFields, hasField, hasOneof

  • Method Details

    • hasIgnore

      boolean hasIgnore()
      
If set to true, search will ignore quantized vector data
      optional bool ignore = 1;
      Returns:
      Whether the ignore field is set.

    • getIgnore

      boolean getIgnore()
      
If set to true, search will ignore quantized vector data
      optional bool ignore = 1;
      Returns:
      The ignore.

    • hasRescore

      boolean hasRescore()
      
If true, use original vectors to re-score top-k results. If ignored, qdrant decides automatically does rescore enabled or not.
      optional bool rescore = 2;
      Returns:
      Whether the rescore field is set.

    • getRescore

      boolean getRescore()
      
If true, use original vectors to re-score top-k results. If ignored, qdrant decides automatically does rescore enabled or not.
      optional bool rescore = 2;
      Returns:
      The rescore.

    • hasOversampling

      boolean hasOversampling()
      
Oversampling factor for quantization.

Defines how many extra vectors should be pre-selected using quantized index,
and then re-scored using original vectors.

For example, if `oversampling` is 2.4 and `limit` is 100, then 240 vectors will be pre-selected using quantized index,
and then top-100 will be returned after re-scoring.
      optional double oversampling = 3;
      Returns:
      Whether the oversampling field is set.

    • getOversampling

      double getOversampling()
      
Oversampling factor for quantization.

Defines how many extra vectors should be pre-selected using quantized index,
and then re-scored using original vectors.

For example, if `oversampling` is 2.4 and `limit` is 100, then 240 vectors will be pre-selected using quantized index,
and then top-100 will be returned after re-scoring.
      optional double oversampling = 3;
      Returns:
      The oversampling.