Class PutNvidiaRequest.Builder
java.lang.Object
co.elastic.clients.util.ObjectBuilderBase
co.elastic.clients.util.WithJsonObjectBuilderBase<BuilderT>
co.elastic.clients.elasticsearch._types.RequestBase.AbstractBuilder<PutNvidiaRequest.Builder>
co.elastic.clients.elasticsearch.inference.PutNvidiaRequest.Builder
- All Implemented Interfaces:
WithJson<PutNvidiaRequest.Builder>,ObjectBuilder<PutNvidiaRequest>
- Enclosing class:
- PutNvidiaRequest
public static class PutNvidiaRequest.Builder
extends RequestBase.AbstractBuilder<PutNvidiaRequest.Builder>
implements ObjectBuilder<PutNvidiaRequest>
Builder for
PutNvidiaRequest.-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionbuild()Builds aPutNvidiaRequest.final PutNvidiaRequest.BuilderThe chunking configuration object.final PutNvidiaRequest.BuilderchunkingSettings(Function<InferenceChunkingSettings.Builder, ObjectBuilder<InferenceChunkingSettings>> fn) The chunking configuration object.final PutNvidiaRequest.BuildernvidiaInferenceId(String value) Required - The unique identifier of the inference endpoint.protected PutNvidiaRequest.Builderself()final PutNvidiaRequest.Builderservice(NvidiaServiceType value) Required - The type of service supported for the specified task type.final PutNvidiaRequest.BuilderRequired - Settings used to install the inference model.final PutNvidiaRequest.BuilderRequired - Settings used to install the inference model.final PutNvidiaRequest.BuildertaskSettings(NvidiaTaskSettings value) Settings to configure the inference task.final PutNvidiaRequest.BuilderSettings to configure the inference task.final PutNvidiaRequest.BuildertaskType(NvidiaTaskType value) Required - The type of the inference task that the model will perform.final PutNvidiaRequest.BuilderSpecifies the amount of time to wait for the inference endpoint to be created.final PutNvidiaRequest.BuilderSpecifies the amount of time to wait for the inference endpoint to be created.Methods inherited from class co.elastic.clients.util.WithJsonObjectBuilderBase
withJsonMethods inherited from class co.elastic.clients.util.ObjectBuilderBase
_checkSingleUse, _listAdd, _listAddAll, _mapPut, _mapPutAll
-
Constructor Details
-
Builder
public Builder()
-
-
Method Details
-
chunkingSettings
The chunking configuration object. Applies only to thetext_embeddingtask type. Not applicable to thererank,completion, orchat_completiontask types.API name:
chunking_settings -
chunkingSettings
public final PutNvidiaRequest.Builder chunkingSettings(Function<InferenceChunkingSettings.Builder, ObjectBuilder<InferenceChunkingSettings>> fn) The chunking configuration object. Applies only to thetext_embeddingtask type. Not applicable to thererank,completion, orchat_completiontask types.API name:
chunking_settings -
nvidiaInferenceId
Required - The unique identifier of the inference endpoint.API name:
nvidia_inference_id -
service
Required - The type of service supported for the specified task type. In this case,nvidia.API name:
service -
serviceSettings
Required - Settings used to install the inference model. These settings are specific to thenvidiaservice.API name:
service_settings -
serviceSettings
public final PutNvidiaRequest.Builder serviceSettings(Function<NvidiaServiceSettings.Builder, ObjectBuilder<NvidiaServiceSettings>> fn) Required - Settings used to install the inference model. These settings are specific to thenvidiaservice.API name:
service_settings -
taskSettings
Settings to configure the inference task. Applies only to thetext_embeddingtask type. Not applicable to thererank,completion, orchat_completiontask types. These settings are specific to the task type you specified.API name:
task_settings -
taskSettings
public final PutNvidiaRequest.Builder taskSettings(Function<NvidiaTaskSettings.Builder, ObjectBuilder<NvidiaTaskSettings>> fn) Settings to configure the inference task. Applies only to thetext_embeddingtask type. Not applicable to thererank,completion, orchat_completiontask types. These settings are specific to the task type you specified.API name:
task_settings -
taskType
Required - The type of the inference task that the model will perform. NOTE: Thechat_completiontask type only supports streaming and only through the _stream API.API name:
task_type -
timeout
Specifies the amount of time to wait for the inference endpoint to be created.API name:
timeout -
timeout
Specifies the amount of time to wait for the inference endpoint to be created.API name:
timeout -
self
- Specified by:
selfin classRequestBase.AbstractBuilder<PutNvidiaRequest.Builder>
-
build
Builds aPutNvidiaRequest.- Specified by:
buildin interfaceObjectBuilder<PutNvidiaRequest>- Throws:
NullPointerException- if some of the required fields are null.
-