RescoringOptions Class
- java.
lang. Object - com.
azure. search. documents. indexes. models. RescoringOptions
- com.
Implements
public final class RescoringOptions
implements JsonSerializable<RescoringOptions>
Contains the options for rescoring.
Constructor Summary
| Constructor | Description |
|---|---|
| RescoringOptions() |
Creates an instance of Rescoring |
Method Summary
| Modifier and Type | Method and Description |
|---|---|
|
static
Rescoring |
fromJson(JsonReader jsonReader)
Reads an instance of Rescoring |
| Double |
getDefaultOversampling()
Get the default |
|
Vector |
getRescoreStorageMethod()
Get the rescore |
| Boolean |
isRescoringEnabled()
Get the rescoring |
|
Rescoring |
setDefaultOversampling(Double defaultOversampling)
Set the default |
|
Rescoring |
setRescoreStorageMethod(VectorSearchCompressionRescoreStorageMethod rescoreStorageMethod)
Set the rescore |
|
Rescoring |
setRescoringEnabled(Boolean rescoringEnabled)
Set the rescoring |
|
Json |
toJson(JsonWriter jsonWriter) |
Methods inherited from java.lang.Object
Constructor Details
RescoringOptions
public RescoringOptions()
Creates an instance of RescoringOptions class.
Method Details
fromJson
public static RescoringOptions fromJson(JsonReader jsonReader)
Reads an instance of RescoringOptions from the JsonReader.
Parameters:
Returns:
Throws:
getDefaultOversampling
public Double getDefaultOversampling()
Get the defaultOversampling property: Default oversampling factor. Oversampling retrieves a greater set of potential documents to offset the resolution loss due to quantization. This increases the set of results that will be rescored on full-precision vectors. Minimum value is 1, meaning no oversampling (1x). This parameter can only be set when 'enableRescoring' is true. Higher values improve recall at the expense of latency.
Returns:
getRescoreStorageMethod
public VectorSearchCompressionRescoreStorageMethod getRescoreStorageMethod()
Get the rescoreStorageMethod property: Controls the storage method for original vectors. This setting is immutable.
Returns:
isRescoringEnabled
public Boolean isRescoringEnabled()
Get the rescoringEnabled property: If set to true, after the initial search on the compressed vectors, the similarity scores are recalculated using the full-precision vectors. This will improve recall at the expense of latency.
Returns:
setDefaultOversampling
public RescoringOptions setDefaultOversampling(Double defaultOversampling)
Set the defaultOversampling property: Default oversampling factor. Oversampling retrieves a greater set of potential documents to offset the resolution loss due to quantization. This increases the set of results that will be rescored on full-precision vectors. Minimum value is 1, meaning no oversampling (1x). This parameter can only be set when 'enableRescoring' is true. Higher values improve recall at the expense of latency.
Parameters:
Returns:
setRescoreStorageMethod
public RescoringOptions setRescoreStorageMethod(VectorSearchCompressionRescoreStorageMethod rescoreStorageMethod)
Set the rescoreStorageMethod property: Controls the storage method for original vectors. This setting is immutable.
Parameters:
Returns:
setRescoringEnabled
public RescoringOptions setRescoringEnabled(Boolean rescoringEnabled)
Set the rescoringEnabled property: If set to true, after the initial search on the compressed vectors, the similarity scores are recalculated using the full-precision vectors. This will improve recall at the expense of latency.
Parameters:
Returns: