VectorSearchCompression Class
- java.
lang. Object - com.
azure. search. documents. indexes. models. VectorSearchCompression
- com.
Implements
public class VectorSearchCompression
implements JsonSerializable<VectorSearchCompression>
Contains configuration options specific to the compression method used during indexing or querying.
Constructor Summary
| Constructor | Description |
|---|---|
| VectorSearchCompression(String compressionName) |
Creates an instance of Vector |
Method Summary
| Modifier and Type | Method and Description |
|---|---|
|
static
Vector |
fromJson(JsonReader jsonReader)
Reads an instance of Vector |
| String |
getCompressionName()
Get the compression |
| Double |
getDefaultOversampling()
Get the default |
|
Vector |
getKind()
Get the kind property: The name of the kind of compression method being configured for use with vector search. |
|
Rescoring |
getRescoringOptions()
Get the rescoring |
| Integer |
getTruncationDimension()
Get the truncation |
| Boolean |
isRerankWithOriginalVectors()
Get the rerank |
|
Vector |
setDefaultOversampling(Double defaultOversampling)
Set the default |
|
Vector |
setRerankWithOriginalVectors(Boolean rerankWithOriginalVectors)
Set the rerank |
|
Vector |
setRescoringOptions(RescoringOptions rescoringOptions)
Set the rescoring |
|
Vector |
setTruncationDimension(Integer truncationDimension)
Set the truncation |
|
Json |
toJson(JsonWriter jsonWriter) |
Methods inherited from java.lang.Object
Constructor Details
VectorSearchCompression
public VectorSearchCompression(String compressionName)
Creates an instance of VectorSearchCompression class.
Parameters:
Method Details
fromJson
public static VectorSearchCompression fromJson(JsonReader jsonReader)
Reads an instance of VectorSearchCompression from the JsonReader.
Parameters:
Returns:
Throws:
getCompressionName
public String getCompressionName()
Get the compressionName property: The name to associate with this particular configuration.
Returns:
getDefaultOversampling
public Double getDefaultOversampling()
Get the defaultOversampling property: 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. For use with only service version 2024-07-01. If using 2025-09-01 or later, use RescoringOptions.defaultOversampling.
Returns:
getKind
public VectorSearchCompressionKind getKind()
Get the kind property: The name of the kind of compression method being configured for use with vector search.
Returns:
getRescoringOptions
public RescoringOptions getRescoringOptions()
Get the rescoringOptions property: Contains the options for rescoring.
Returns:
getTruncationDimension
public Integer getTruncationDimension()
Get 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.
Returns:
isRerankWithOriginalVectors
public Boolean isRerankWithOriginalVectors()
Get the rerankWithOriginalVectors property: 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. For use with only service version 2024-07-01. If using 2025-09-01 or later, use RescoringOptions.rescoringEnabled.
Returns:
setDefaultOversampling
public VectorSearchCompression setDefaultOversampling(Double defaultOversampling)
Set the defaultOversampling property: 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. For use with only service version 2024-07-01. If using 2025-09-01 or later, use RescoringOptions.defaultOversampling.
Parameters:
Returns:
setRerankWithOriginalVectors
public VectorSearchCompression setRerankWithOriginalVectors(Boolean rerankWithOriginalVectors)
Set the rerankWithOriginalVectors property: 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. For use with only service version 2024-07-01. If using 2025-09-01 or later, use RescoringOptions.rescoringEnabled.
Parameters:
Returns:
setRescoringOptions
public VectorSearchCompression setRescoringOptions(RescoringOptions rescoringOptions)
Set the rescoringOptions property: Contains the options for rescoring.
Parameters:
Returns:
setTruncationDimension
public VectorSearchCompression 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.
Parameters:
Returns:
