Interface SageMakerRuntimeClient

All Superinterfaces:

AutoCloseable, AwsClient, SdkAutoCloseable, SdkClient

@Generated("software.amazon.awssdk:codegen")
@SdkPublicApi
@ThreadSafe
public interface SageMakerRuntimeClient
extends AwsClient

Service client for accessing Amazon SageMaker Runtime. This can be created using the static builder() method.

The Amazon SageMaker AI runtime API.

Field Summary

Fields

Modifier and Type	Field	Description
static final String	SERVICE_METADATA_ID	Value for looking up the service's metadata from the ServiceMetadataProvider.
static final String	SERVICE_NAME

Method Summary

Modifier and Type	Method	Description
static SageMakerRuntimeClientBuilder	builder()	Create a builder that can be used to configure and create a SageMakerRuntimeClient.
static SageMakerRuntimeClient	create()	Create a SageMakerRuntimeClient with the region loaded from the DefaultAwsRegionProviderChain and credentials loaded from the DefaultCredentialsProvider.
default InvokeEndpointResponse	invokeEndpoint(Consumer<InvokeEndpointRequest.Builder> invokeEndpointRequest)	After you deploy a model into production using Amazon SageMaker AI hosting services, your client applications use this API to get inferences from the model hosted at the specified endpoint.
default InvokeEndpointResponse	invokeEndpoint(InvokeEndpointRequest invokeEndpointRequest)	After you deploy a model into production using Amazon SageMaker AI hosting services, your client applications use this API to get inferences from the model hosted at the specified endpoint.
default InvokeEndpointAsyncResponse	invokeEndpointAsync(Consumer<InvokeEndpointAsyncRequest.Builder> invokeEndpointAsyncRequest)	After you deploy a model into production using Amazon SageMaker AI hosting services, your client applications use this API to get inferences from the model hosted at the specified endpoint in an asynchronous manner.
default InvokeEndpointAsyncResponse	invokeEndpointAsync(InvokeEndpointAsyncRequest invokeEndpointAsyncRequest)	After you deploy a model into production using Amazon SageMaker AI hosting services, your client applications use this API to get inferences from the model hosted at the specified endpoint in an asynchronous manner.
default SageMakerRuntimeServiceClientConfiguration	serviceClientConfiguration()	The SDK service client configuration exposes client settings to the user, e.g., ClientOverrideConfiguration
static ServiceMetadata	serviceMetadata()

Methods inherited from interface software.amazon.awssdk.utils.SdkAutoCloseable

close

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

serviceName

Field Details

SERVICE_NAME

static final String SERVICE_NAME

See Also:

• Constant Field Values

SERVICE_METADATA_ID

static final String SERVICE_METADATA_ID

Value for looking up the service's metadata from the ServiceMetadataProvider.

See Also:

• Constant Field Values

Method Details

invokeEndpoint

default InvokeEndpointResponse invokeEndpoint(InvokeEndpointRequest invokeEndpointRequest)
                                       throws InternalFailureException,
ServiceUnavailableException,
ValidationErrorException,
ModelErrorException,
InternalDependencyException,
ModelNotReadyException,
AwsServiceException,
SdkClientException,
SageMakerRuntimeException

After you deploy a model into production using Amazon SageMaker AI hosting services, your client applications use this API to get inferences from the model hosted at the specified endpoint.

For an overview of Amazon SageMaker AI, see How It Works.

Amazon SageMaker AI strips all POST headers except those supported by the API. Amazon SageMaker AI might add additional headers. You should not rely on the behavior of headers outside those enumerated in the request syntax.

Calls to InvokeEndpoint are authenticated by using Amazon Web Services Signature Version 4. For information, see Authenticating Requests (Amazon Web Services Signature Version 4) in the Amazon S3 API Reference.

A customer's model containers must respond to requests within 60 seconds. The model itself can have a maximum processing time of 60 seconds before responding to invocations. If your model is going to take 50-60 seconds of processing time, the SDK socket timeout should be set to be 70 seconds.

Endpoints are scoped to an individual account, and are not public. The URL does not contain the account ID, but Amazon SageMaker AI determines the account ID from the authentication token that is supplied by the caller.

Parameters:

invokeEndpointRequest -

Returns:

Result of the InvokeEndpoint operation returned by the service.

See Also:

• AWS API Documentation

invokeEndpoint

default InvokeEndpointResponse invokeEndpoint(Consumer<InvokeEndpointRequest.Builder> invokeEndpointRequest)
                                       throws InternalFailureException,
ServiceUnavailableException,
ValidationErrorException,
ModelErrorException,
InternalDependencyException,
ModelNotReadyException,
AwsServiceException,
SdkClientException,
SageMakerRuntimeException

After you deploy a model into production using Amazon SageMaker AI hosting services, your client applications use this API to get inferences from the model hosted at the specified endpoint.

For an overview of Amazon SageMaker AI, see How It Works.

Amazon SageMaker AI strips all POST headers except those supported by the API. Amazon SageMaker AI might add additional headers. You should not rely on the behavior of headers outside those enumerated in the request syntax.

Calls to InvokeEndpoint are authenticated by using Amazon Web Services Signature Version 4. For information, see Authenticating Requests (Amazon Web Services Signature Version 4) in the Amazon S3 API Reference.

A customer's model containers must respond to requests within 60 seconds. The model itself can have a maximum processing time of 60 seconds before responding to invocations. If your model is going to take 50-60 seconds of processing time, the SDK socket timeout should be set to be 70 seconds.

Endpoints are scoped to an individual account, and are not public. The URL does not contain the account ID, but Amazon SageMaker AI determines the account ID from the authentication token that is supplied by the caller.

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

Parameters:

invokeEndpointRequest - A Consumer that will call methods on InvokeEndpointRequest.Builder to create a request.

Returns:

Result of the InvokeEndpoint operation returned by the service.

See Also:

• AWS API Documentation

invokeEndpointAsync

default InvokeEndpointAsyncResponse invokeEndpointAsync(InvokeEndpointAsyncRequest invokeEndpointAsyncRequest)
                                                 throws InternalFailureException,
ServiceUnavailableException,
ValidationErrorException,
AwsServiceException,
SdkClientException,
SageMakerRuntimeException

After you deploy a model into production using Amazon SageMaker AI hosting services, your client applications use this API to get inferences from the model hosted at the specified endpoint in an asynchronous manner.

Inference requests sent to this API are enqueued for asynchronous processing. The processing of the inference request may or may not complete before you receive a response from this API. The response from this API will not contain the result of the inference request but contain information about where you can locate it.

Amazon SageMaker AI strips all POST headers except those supported by the API. Amazon SageMaker AI might add additional headers. You should not rely on the behavior of headers outside those enumerated in the request syntax.

Calls to InvokeEndpointAsync are authenticated by using Amazon Web Services Signature Version 4. For information, see Authenticating Requests (Amazon Web Services Signature Version 4) in the Amazon S3 API Reference.

Parameters:

invokeEndpointAsyncRequest -

Returns:

Result of the InvokeEndpointAsync operation returned by the service.

See Also:

• AWS API Documentation

invokeEndpointAsync

default InvokeEndpointAsyncResponse invokeEndpointAsync(Consumer<InvokeEndpointAsyncRequest.Builder> invokeEndpointAsyncRequest)
                                                 throws InternalFailureException,
ServiceUnavailableException,
ValidationErrorException,
AwsServiceException,
SdkClientException,
SageMakerRuntimeException

After you deploy a model into production using Amazon SageMaker AI hosting services, your client applications use this API to get inferences from the model hosted at the specified endpoint in an asynchronous manner.

Inference requests sent to this API are enqueued for asynchronous processing. The processing of the inference request may or may not complete before you receive a response from this API. The response from this API will not contain the result of the inference request but contain information about where you can locate it.

Amazon SageMaker AI strips all POST headers except those supported by the API. Amazon SageMaker AI might add additional headers. You should not rely on the behavior of headers outside those enumerated in the request syntax.

Calls to InvokeEndpointAsync are authenticated by using Amazon Web Services Signature Version 4. For information, see Authenticating Requests (Amazon Web Services Signature Version 4) in the Amazon S3 API Reference.

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

Parameters:

invokeEndpointAsyncRequest - A Consumer that will call methods on InvokeEndpointAsyncRequest.Builder to create a request.

Returns:

Result of the InvokeEndpointAsync operation returned by the service.

See Also:

• AWS API Documentation

create

static SageMakerRuntimeClient create()

Create a SageMakerRuntimeClient with the region loaded from the DefaultAwsRegionProviderChain and credentials loaded from the DefaultCredentialsProvider.

builder

static SageMakerRuntimeClientBuilder builder()

Create a builder that can be used to configure and create a SageMakerRuntimeClient.

serviceMetadata

static ServiceMetadata serviceMetadata()

serviceClientConfiguration

default SageMakerRuntimeServiceClientConfiguration serviceClientConfiguration()

Description copied from interface: SdkClient

The SDK service client configuration exposes client settings to the user, e.g., ClientOverrideConfiguration

Specified by:

serviceClientConfiguration in interface AwsClient

Specified by:

serviceClientConfiguration in interface SdkClient

Returns:

SdkServiceClientConfiguration