Class AzureAiStudioTaskSettings
java.lang.Object
co.elastic.clients.elasticsearch.inference.AzureAiStudioTaskSettings
- All Implemented Interfaces:
JsonpSerializable
@JsonpDeserializable
public class AzureAiStudioTaskSettings
extends Object
implements JsonpSerializable
- See Also:
-
Nested Class Summary
Nested Classes -
Field Summary
FieldsModifier and TypeFieldDescriptionstatic final JsonpDeserializer<AzureAiStudioTaskSettings>Json deserializer forAzureAiStudioTaskSettings -
Method Summary
Modifier and TypeMethodDescriptionfinal FloatdoSample()For acompletiontask, instruct the inference process to perform sampling.final IntegerFor acompletiontask, provide a hint for the maximum number of output tokens to be generated.static AzureAiStudioTaskSettingsfinal BooleanFor areranktask, return doc text within the results.voidserialize(jakarta.json.stream.JsonGenerator generator, JsonpMapper mapper) Serialize this object to JSON.protected voidserializeInternal(jakarta.json.stream.JsonGenerator generator, JsonpMapper mapper) protected static voidsetupAzureAiStudioTaskSettingsDeserializer(ObjectDeserializer<AzureAiStudioTaskSettings.Builder> op) final FloatFor acompletiontask, control the apparent creativity of generated completions with a sampling temperature.final IntegertopN()For areranktask, the number of most relevant documents to return.final FloattopP()For acompletiontask, make the model consider the results of the tokens with nucleus sampling probability.toString()final Stringuser()For atext_embeddingtask, specify the user issuing the request.
-
Field Details
-
_DESERIALIZER
Json deserializer forAzureAiStudioTaskSettings
-
-
Method Details
-
of
public static AzureAiStudioTaskSettings of(Function<AzureAiStudioTaskSettings.Builder, ObjectBuilder<AzureAiStudioTaskSettings>> fn) -
doSample
For acompletiontask, instruct the inference process to perform sampling. It has no effect unlesstemperatureortop_pis specified.API name:
do_sample -
maxNewTokens
For acompletiontask, provide a hint for the maximum number of output tokens to be generated.API name:
max_new_tokens -
temperature
For acompletiontask, control the apparent creativity of generated completions with a sampling temperature. It must be a number in the range of 0.0 to 2.0. It should not be used iftop_pis specified.API name:
temperature -
topP
For acompletiontask, make the model consider the results of the tokens with nucleus sampling probability. It is an alternative value totemperatureand must be a number in the range of 0.0 to 2.0. It should not be used iftemperatureis specified.API name:
top_p -
user
For atext_embeddingtask, specify the user issuing the request. This information can be used for abuse detection.API name:
user -
returnDocuments
For areranktask, return doc text within the results.API name:
return_documents -
topN
For areranktask, the number of most relevant documents to return. It defaults to the number of the documents.API name:
top_n -
serialize
Serialize this object to JSON.- Specified by:
serializein interfaceJsonpSerializable
-
serializeInternal
-
toString
-
setupAzureAiStudioTaskSettingsDeserializer
protected static void setupAzureAiStudioTaskSettingsDeserializer(ObjectDeserializer<AzureAiStudioTaskSettings.Builder> op)
-