Interface InferenceComponentSpecification.Builder

All Superinterfaces:

Buildable, CopyableBuilder<InferenceComponentSpecification.Builder,InferenceComponentSpecification>, SdkBuilder<InferenceComponentSpecification.Builder,InferenceComponentSpecification>, SdkPojo

Enclosing class:

InferenceComponentSpecification

@Mutable
@NotThreadSafe
public static interface InferenceComponentSpecification.Builder
extends SdkPojo, CopyableBuilder<InferenceComponentSpecification.Builder,InferenceComponentSpecification>

Method Summary

Modifier and Type	Method	Description
InferenceComponentSpecification.Builder	baseInferenceComponentName(String baseInferenceComponentName)	The name of an existing inference component that is to contain the inference component that you're creating with your request.
default InferenceComponentSpecification.Builder	computeResourceRequirements(Consumer<InferenceComponentComputeResourceRequirements.Builder> computeResourceRequirements)	The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component.
InferenceComponentSpecification.Builder	computeResourceRequirements(InferenceComponentComputeResourceRequirements computeResourceRequirements)	The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component.
default InferenceComponentSpecification.Builder	container(Consumer<InferenceComponentContainerSpecification.Builder> container)	Defines a container that provides the runtime environment for a model that you deploy with an inference component.
InferenceComponentSpecification.Builder	container(InferenceComponentContainerSpecification container)	Defines a container that provides the runtime environment for a model that you deploy with an inference component.
InferenceComponentSpecification.Builder	modelName(String modelName)	The name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.
default InferenceComponentSpecification.Builder	startupParameters(Consumer<InferenceComponentStartupParameters.Builder> startupParameters)	Settings that take effect while the model container starts up.
InferenceComponentSpecification.Builder	startupParameters(InferenceComponentStartupParameters startupParameters)	Settings that take effect while the model container starts up.

Methods inherited from interface software.amazon.awssdk.utils.builder.CopyableBuilder

copy

Methods inherited from interface software.amazon.awssdk.utils.builder.SdkBuilder

applyMutation, build

Methods inherited from interface software.amazon.awssdk.core.SdkPojo

equalsBySdkFields, sdkFieldNameToField, sdkFields

Method Details

modelName

InferenceComponentSpecification.Builder modelName(String modelName)

The name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.

Parameters:

modelName - The name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.

Returns:

Returns a reference to this object so that method calls can be chained together.

container

InferenceComponentSpecification.Builder container(InferenceComponentContainerSpecification container)

Defines a container that provides the runtime environment for a model that you deploy with an inference component.

Parameters:

container - Defines a container that provides the runtime environment for a model that you deploy with an inference component.

Returns:

Returns a reference to this object so that method calls can be chained together.

container

default InferenceComponentSpecification.Builder container(Consumer<InferenceComponentContainerSpecification.Builder> container)

Defines a container that provides the runtime environment for a model that you deploy with an inference component.

This is a convenience method that creates an instance of the InferenceComponentContainerSpecification.Builder avoiding the need to create one manually via InferenceComponentContainerSpecification.builder().

When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to container(InferenceComponentContainerSpecification).

Parameters:

container - a consumer that will call methods on InferenceComponentContainerSpecification.Builder

Returns:

Returns a reference to this object so that method calls can be chained together.

See Also:

• container(InferenceComponentContainerSpecification)

startupParameters

InferenceComponentSpecification.Builder startupParameters(InferenceComponentStartupParameters startupParameters)

Settings that take effect while the model container starts up.

Parameters:

startupParameters - Settings that take effect while the model container starts up.

Returns:

Returns a reference to this object so that method calls can be chained together.

startupParameters

default InferenceComponentSpecification.Builder startupParameters(Consumer<InferenceComponentStartupParameters.Builder> startupParameters)

Settings that take effect while the model container starts up.

This is a convenience method that creates an instance of the InferenceComponentStartupParameters.Builder avoiding the need to create one manually via InferenceComponentStartupParameters.builder().

When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to startupParameters(InferenceComponentStartupParameters).

Parameters:

startupParameters - a consumer that will call methods on InferenceComponentStartupParameters.Builder

Returns:

Returns a reference to this object so that method calls can be chained together.

See Also:

• startupParameters(InferenceComponentStartupParameters)

computeResourceRequirements

InferenceComponentSpecification.Builder computeResourceRequirements(InferenceComponentComputeResourceRequirements computeResourceRequirements)

The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component.

Omit this parameter if your request is meant to create an adapter inference component. An adapter inference component is loaded by a base inference component, and it uses the compute resources of the base inference component.

Parameters:

computeResourceRequirements - The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component.

Omit this parameter if your request is meant to create an adapter inference component. An adapter inference component is loaded by a base inference component, and it uses the compute resources of the base inference component.

Returns:

Returns a reference to this object so that method calls can be chained together.

computeResourceRequirements

default InferenceComponentSpecification.Builder computeResourceRequirements(Consumer<InferenceComponentComputeResourceRequirements.Builder> computeResourceRequirements)

The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component.

Omit this parameter if your request is meant to create an adapter inference component. An adapter inference component is loaded by a base inference component, and it uses the compute resources of the base inference component.

This is a convenience method that creates an instance of the InferenceComponentComputeResourceRequirements.Builder avoiding the need to create one manually via InferenceComponentComputeResourceRequirements.builder().

When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to computeResourceRequirements(InferenceComponentComputeResourceRequirements).

Parameters:

computeResourceRequirements - a consumer that will call methods on InferenceComponentComputeResourceRequirements.Builder

Returns:

Returns a reference to this object so that method calls can be chained together.

See Also:

• computeResourceRequirements(InferenceComponentComputeResourceRequirements)

baseInferenceComponentName

InferenceComponentSpecification.Builder baseInferenceComponentName(String baseInferenceComponentName)

The name of an existing inference component that is to contain the inference component that you're creating with your request.

Specify this parameter only if your request is meant to create an adapter inference component. An adapter inference component contains the path to an adapter model. The purpose of the adapter model is to tailor the inference output of a base foundation model, which is hosted by the base inference component. The adapter inference component uses the compute resources that you assigned to the base inference component.

When you create an adapter inference component, use the Container parameter to specify the location of the adapter artifacts. In the parameter value, use the ArtifactUrl parameter of the InferenceComponentContainerSpecification data type.

Before you can create an adapter inference component, you must have an existing inference component that contains the foundation model that you want to adapt.

Parameters:

baseInferenceComponentName - The name of an existing inference component that is to contain the inference component that you're creating with your request.

Specify this parameter only if your request is meant to create an adapter inference component. An adapter inference component contains the path to an adapter model. The purpose of the adapter model is to tailor the inference output of a base foundation model, which is hosted by the base inference component. The adapter inference component uses the compute resources that you assigned to the base inference component.

When you create an adapter inference component, use the Container parameter to specify the location of the adapter artifacts. In the parameter value, use the ArtifactUrl parameter of the InferenceComponentContainerSpecification data type.

Before you can create an adapter inference component, you must have an existing inference component that contains the foundation model that you want to adapt.

Returns:

Returns a reference to this object so that method calls can be chained together.