Class VectorSearchCompression
java.lang.Object
com.azure.search.documents.indexes.models.VectorSearchCompression
- All Implemented Interfaces:
com.azure.json.JsonSerializable<VectorSearchCompression>
- Direct Known Subclasses:
BinaryQuantizationCompression,ScalarQuantizationCompression
public class VectorSearchCompression
extends Object
implements com.azure.json.JsonSerializable<VectorSearchCompression>
Contains configuration options specific to the compression method used during indexing or querying.
-
Constructor Summary
ConstructorsConstructorDescriptionVectorSearchCompression(String compressionName) Creates an instance of VectorSearchCompression class. -
Method Summary
Modifier and TypeMethodDescriptionstatic VectorSearchCompressionfromJson(com.azure.json.JsonReader jsonReader) Reads an instance of VectorSearchCompression from the JsonReader.Get the compressionName property: The name to associate with this particular configuration.Get the defaultOversampling property: Default oversampling factor.getKind()Get the kind property: The name of the kind of compression method being configured for use with vector search.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.setDefaultOversampling(Double defaultOversampling) Set the defaultOversampling property: Default oversampling factor.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.com.azure.json.JsonWritertoJson(com.azure.json.JsonWriter jsonWriter) Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitMethods inherited from interface com.azure.json.JsonSerializable
toJson, toJson, toJsonBytes, toJsonString
-
Constructor Details
-
VectorSearchCompression
Creates an instance of VectorSearchCompression class.- Parameters:
compressionName- the compressionName value to set.
-
-
Method Details
-
getKind
Get the kind property: The name of the kind of compression method being configured for use with vector search.- Returns:
- the kind value.
-
getCompressionName
Get the compressionName property: The name to associate with this particular configuration.- Returns:
- the compressionName value.
-
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.- Returns:
- the rerankWithOriginalVectors value.
-
setRerankWithOriginalVectors
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.- Parameters:
rerankWithOriginalVectors- the rerankWithOriginalVectors value to set.- Returns:
- the VectorSearchCompression object itself.
-
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.- Returns:
- the defaultOversampling value.
-
setDefaultOversampling
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.- Parameters:
defaultOversampling- the defaultOversampling value to set.- Returns:
- the VectorSearchCompression object itself.
-
toJson
- Specified by:
toJsonin interfacecom.azure.json.JsonSerializable<VectorSearchCompression>- Throws:
IOException
-
fromJson
public static VectorSearchCompression fromJson(com.azure.json.JsonReader jsonReader) throws IOException Reads an instance of VectorSearchCompression from the JsonReader.- Parameters:
jsonReader- The JsonReader being read.- Returns:
- An instance of VectorSearchCompression if the JsonReader was pointing to an instance of it, or null if it was pointing to JSON null.
- Throws:
IllegalStateException- If the deserialized JSON object was missing any required properties.IOException- If an error occurs while reading the VectorSearchCompression.
-