Package co.elastic.clients.elasticsearch.ml

Class StartTrainedModelDeploymentRequest

java.lang.Object

co.elastic.clients.elasticsearch._types.RequestBase

co.elastic.clients.elasticsearch.ml.StartTrainedModelDeploymentRequest

public class StartTrainedModelDeploymentRequest
extends RequestBase

Starts a trained model deployment, which allocates the model to every machine learning node.

See Also:

API specification

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	StartTrainedModelDeploymentRequest.Builder	Builder for StartTrainedModelDeploymentRequest.

Nested classes/interfaces inherited from class co.elastic.clients.elasticsearch._types.RequestBase

RequestBase.AbstractBuilder<BuilderT extends RequestBase.AbstractBuilder<BuilderT>>

Field Summary

Fields

Modifier and Type	Field	Description
static Endpoint<StartTrainedModelDeploymentRequest,StartTrainedModelDeploymentResponse,ErrorResponse>	_ENDPOINT	Endpoint "ml.start_trained_model_deployment".

Method Summary

Modifier and Type	Method	Description
java.lang.Integer	inferenceThreads()	Specifies the number of threads that are used by the inference process.
java.lang.String	modelId()	Required - The unique identifier of the trained model.
java.lang.Integer	modelThreads()	Specifies the number of threads that are used when sending inference requests to the model.
static StartTrainedModelDeploymentRequest	of(java.util.function.Function<StartTrainedModelDeploymentRequest.Builder,ObjectBuilder<StartTrainedModelDeploymentRequest>> fn)
java.lang.Integer	queueCapacity()	Specifies the number of inference requests that are allowed in the queue.
Time	timeout()	Specifies the amount of time to wait for the model to deploy.
DeploymentAllocationState	waitFor()	Specifies the allocation status to wait for before returning.

Methods inherited from class co.elastic.clients.elasticsearch._types.RequestBase

toString

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Details

_ENDPOINT

public static final Endpoint<StartTrainedModelDeploymentRequest,StartTrainedModelDeploymentResponse,ErrorResponse> _ENDPOINT

Endpoint "ml.start_trained_model_deployment".

Method Details

of

public static StartTrainedModelDeploymentRequest of(java.util.function.Function<StartTrainedModelDeploymentRequest.Builder,ObjectBuilder<StartTrainedModelDeploymentRequest>> fn)

inferenceThreads

@Nullable
public final java.lang.Integer inferenceThreads()

Specifies the number of threads that are used by the inference process. If you increase this value, inference speed generally increases. However, the actual number of threads is limited by the number of available CPU cores.

API name: inference_threads

modelId

public final java.lang.String modelId()

Required - The unique identifier of the trained model. Currently, only PyTorch models are supported.

API name: model_id

modelThreads

@Nullable
public final java.lang.Integer modelThreads()

Specifies the number of threads that are used when sending inference requests to the model. If you increase this value, throughput generally increases.

API name: model_threads

queueCapacity

@Nullable
public final java.lang.Integer queueCapacity()

Specifies the number of inference requests that are allowed in the queue. After the number of requests exceeds this value, new requests are rejected with a 429 error.

API name: queue_capacity

timeout

@Nullable
public final Time timeout()

Specifies the amount of time to wait for the model to deploy.

API name: timeout

waitFor

@Nullable
public final DeploymentAllocationState waitFor()

Specifies the allocation status to wait for before returning.

API name: wait_for