BinaryQuantizationCompression Class

Package:
com.azure.search.documents.indexes.models
Maven Artifact:
com.azure:azure-search-documents:12.0.0

public final class BinaryQuantizationCompression
extends VectorSearchCompression

Contains configuration options specific to the binary quantization compression method used during indexing and querying.

Constructor Summary

Constructor Description
BinaryQuantizationCompression(String compressionName)

Creates an instance of BinaryQuantizationCompression class.

Method Summary

Modifier and Type Method and Description
static BinaryQuantizationCompression fromJson(JsonReader jsonReader)

Reads an instance of BinaryQuantizationCompression from the JsonReader.
VectorSearchCompressionKind getKind()

Get the kind property: Type of VectorSearchCompression.
BinaryQuantizationCompression setRescoringOptions(RescoringOptions rescoringOptions)

Set the rescoringOptions property: Contains the options for rescoring.
BinaryQuantizationCompression setTruncationDimension(Integer truncationDimension)

Set the truncationDimension property: The number of dimensions to truncate the vectors to.
JsonWriter toJson(JsonWriter jsonWriter)

Methods inherited from VectorSearchCompression

fromJson getCompressionName getKind getRescoringOptions getTruncationDimension setRescoringOptions setTruncationDimension toJson

Methods inherited from java.lang.Object

clone equals finalize getClass hashCode notify notifyAll toString wait wait wait

Constructor Details

BinaryQuantizationCompression

public BinaryQuantizationCompression(String compressionName)

Creates an instance of BinaryQuantizationCompression class.

Parameters:

compressionName - the compressionName value to set.

Method Details

fromJson

public static BinaryQuantizationCompression fromJson(JsonReader jsonReader)

Reads an instance of BinaryQuantizationCompression from the JsonReader.

Parameters:

jsonReader - The JsonReader being read.

Returns:

An instance of BinaryQuantizationCompression if the JsonReader was pointing to an instance of it, or null if it was pointing to JSON null.

Throws:

IOException

 - If the deserialized JSON object was missing any required properties.

getKind

public VectorSearchCompressionKind getKind()

Get the kind property: Type of VectorSearchCompression.

Overrides:

BinaryQuantizationCompression.getKind()

Returns:

the kind value.

setRescoringOptions

public BinaryQuantizationCompression setRescoringOptions(RescoringOptions rescoringOptions)

Set the rescoringOptions property: Contains the options for rescoring.

Overrides:

BinaryQuantizationCompression.setRescoringOptions(RescoringOptions rescoringOptions)

Parameters:

rescoringOptions

setTruncationDimension

public BinaryQuantizationCompression setTruncationDimension(Integer truncationDimension)

Set the truncationDimension property: The number of dimensions to truncate the vectors to. Truncating the vectors reduces the size of the vectors and the amount of data that needs to be transferred during search. This can save storage cost and improve search performance at the expense of recall. It should be only used for embeddings trained with Matryoshka Representation Learning (MRL) such as OpenAI text-embedding-3-large (small). The default value is null, which means no truncation.

Overrides:

BinaryQuantizationCompression.setTruncationDimension(Integer truncationDimension)

Parameters:

truncationDimension

toJson

public JsonWriter toJson(JsonWriter jsonWriter)

Overrides:

BinaryQuantizationCompression.toJson(JsonWriter jsonWriter)

Parameters:

jsonWriter

Throws:

Applies to