Share via

BinaryQuantizationCompression interface

Package:
@azure/search-documents

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

Extends
BaseVectorSearchCompression

Properties

kind

Polymorphic discriminator, which specifies the different types this object can be

Inherited Properties

compressionName

The name to associate with this particular configuration.
defaultOversampling

Default oversampling factor. Oversampling will internally request more documents (specified by this multiplier) in the initial search. This increases the set of results that will be reranked using recomputed similarity scores from full-precision vectors. Minimum value is 1, meaning no oversampling (1x). This parameter can only be set when rerankWithOriginalVectors is true. Higher values improve recall at the expense of latency.
rerankWithOriginalVectors

If set to true, once the ordered set of results calculated using compressed vectors are obtained, they will be reranked again by recalculating the full-precision similarity scores. This will improve recall at the expense of latency.
rescoringOptions

Contains the options for rescoring.
truncationDimension

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.

Property Details

kind

Polymorphic discriminator, which specifies the different types this object can be

kind: "binaryQuantization"

Property Value

"binaryQuantization"

Inherited Property Details

compressionName

The name to associate with this particular configuration.

compressionName: string

Property Value

string

Inherited From VectorSearchCompression.compressionName

defaultOversampling

Default oversampling factor. Oversampling will internally request more documents (specified by this multiplier) in the initial search. This increases the set of results that will be reranked using recomputed similarity scores from full-precision vectors. Minimum value is 1, meaning no oversampling (1x). This parameter can only be set when rerankWithOriginalVectors is true. Higher values improve recall at the expense of latency.

defaultOversampling?: number

Property Value

number

Inherited From VectorSearchCompression.defaultOversampling

rerankWithOriginalVectors

If set to true, once the ordered set of results calculated using compressed vectors are obtained, they will be reranked again by recalculating the full-precision similarity scores. This will improve recall at the expense of latency.

rerankWithOriginalVectors?: boolean

Property Value

boolean

Inherited From VectorSearchCompression.rerankWithOriginalVectors

rescoringOptions

Contains the options for rescoring.

rescoringOptions?: RescoringOptions

Property Value

RescoringOptions

Inherited From VectorSearchCompression.rescoringOptions

truncationDimension

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.

truncationDimension?: number

Property Value

number

Inherited From VectorSearchCompression.truncationDimension