Package co.elastic.clients.elasticsearch.ml

Class StartTrainedModelDeploymentRequest.Builder

java.lang.Object

co.elastic.clients.util.ObjectBuilderBase

co.elastic.clients.util.WithJsonObjectBuilderBase<BuilderT>

co.elastic.clients.elasticsearch._types.RequestBase.AbstractBuilder<StartTrainedModelDeploymentRequest.Builder>

co.elastic.clients.elasticsearch.ml.StartTrainedModelDeploymentRequest.Builder

All Implemented Interfaces:

WithJson<StartTrainedModelDeploymentRequest.Builder>, ObjectBuilder<StartTrainedModelDeploymentRequest>

Enclosing class:

StartTrainedModelDeploymentRequest

public static class StartTrainedModelDeploymentRequest.Builder
extends RequestBase.AbstractBuilder<StartTrainedModelDeploymentRequest.Builder>
implements ObjectBuilder<StartTrainedModelDeploymentRequest>

Builder for StartTrainedModelDeploymentRequest.

Constructor Summary

Constructors

Constructor	Description
Builder()

Method Summary

Modifier and Type	Method	Description
StartTrainedModelDeploymentRequest	build()	Builds a StartTrainedModelDeploymentRequest.
StartTrainedModelDeploymentRequest.Builder	cacheSize(java.lang.String value)	The inference cache size (in memory outside the JVM heap) per node for the model.
StartTrainedModelDeploymentRequest.Builder	modelId(java.lang.String value)	Required - The unique identifier of the trained model.
StartTrainedModelDeploymentRequest.Builder	numberOfAllocations(java.lang.Integer value)	The number of model allocations on each node where the model is deployed.
StartTrainedModelDeploymentRequest.Builder	queueCapacity(java.lang.Integer value)	Specifies the number of inference requests that are allowed in the queue.
protected StartTrainedModelDeploymentRequest.Builder	self()
StartTrainedModelDeploymentRequest.Builder	threadsPerAllocation(java.lang.Integer value)	Sets the number of threads used by each model allocation during inference.
StartTrainedModelDeploymentRequest.Builder	timeout(Time value)	Specifies the amount of time to wait for the model to deploy.
StartTrainedModelDeploymentRequest.Builder	timeout(java.util.function.Function<Time.Builder,ObjectBuilder<Time>> fn)	Specifies the amount of time to wait for the model to deploy.
StartTrainedModelDeploymentRequest.Builder	waitFor(DeploymentAllocationState value)	Specifies the allocation status to wait for before returning.

Methods inherited from class co.elastic.clients.util.WithJsonObjectBuilderBase

withJson

Methods inherited from class co.elastic.clients.util.ObjectBuilderBase

_checkSingleUse, _listAdd, _listAddAll, _mapPut, _mapPutAll

Methods inherited from class java.lang.Object

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

Methods inherited from interface co.elastic.clients.json.WithJson

withJson, withJson

Constructor Details

Builder

public Builder()

Method Details

cacheSize

public final StartTrainedModelDeploymentRequest.Builder cacheSize(@Nullable
java.lang.String value)

The inference cache size (in memory outside the JVM heap) per node for the model. The default value is the same size as the model_size_bytes. To disable the cache, 0b can be provided.

API name: cache_size

modelId

public final StartTrainedModelDeploymentRequest.Builder modelId(java.lang.String value)

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

API name: model_id

numberOfAllocations

public final StartTrainedModelDeploymentRequest.Builder numberOfAllocations(@Nullable
java.lang.Integer value)

The number of model allocations on each node where the model is deployed. All allocations on a node share the same copy of the model in memory but use a separate set of threads to evaluate the model. Increasing this value generally increases the throughput. If this setting is greater than the number of hardware threads it will automatically be changed to a value less than the number of hardware threads.

API name: number_of_allocations

queueCapacity

public final StartTrainedModelDeploymentRequest.Builder queueCapacity(@Nullable
java.lang.Integer value)

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

threadsPerAllocation

public final StartTrainedModelDeploymentRequest.Builder threadsPerAllocation(@Nullable
java.lang.Integer value)

Sets the number of threads used by each model allocation during inference. This generally increases the inference speed. The inference process is a compute-bound process; any number greater than the number of available hardware threads on the machine does not increase the inference speed. If this setting is greater than the number of hardware threads it will automatically be changed to a value less than the number of hardware threads.

API name: threads_per_allocation

timeout

public final StartTrainedModelDeploymentRequest.Builder timeout(@Nullable
Time value)

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

API name: timeout

timeout

public final StartTrainedModelDeploymentRequest.Builder timeout(java.util.function.Function<Time.Builder,ObjectBuilder<Time>> fn)

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

API name: timeout

waitFor

public final StartTrainedModelDeploymentRequest.Builder waitFor(@Nullable
DeploymentAllocationState value)

Specifies the allocation status to wait for before returning.

API name: wait_for

self

protected StartTrainedModelDeploymentRequest.Builder self()

Specified by:

self in class RequestBase.AbstractBuilder<StartTrainedModelDeploymentRequest.Builder>

build

public StartTrainedModelDeploymentRequest build()

Builds a StartTrainedModelDeploymentRequest.

Specified by:

build in interface ObjectBuilder<StartTrainedModelDeploymentRequest>

Throws:

java.lang.NullPointerException - if some of the required fields are null.