com.amazonaws.services.sagemakerruntime

Interface AmazonSageMakerRuntime

All Known Subinterfaces:

AmazonSageMakerRuntimeAsync

All Known Implementing Classes:

AbstractAmazonSageMakerRuntime, AbstractAmazonSageMakerRuntimeAsync, AmazonSageMakerRuntimeAsyncClient, AmazonSageMakerRuntimeClient

@Generated(value="com.amazonaws:aws-java-sdk-code-generator")
public interface AmazonSageMakerRuntime

Interface for accessing Amazon SageMaker Runtime.

Note: Do not directly implement this interface, new methods are added to it regularly. Extend from AbstractAmazonSageMakerRuntime instead.

The Amazon SageMaker runtime API.

Field Summary

Fields

Modifier and Type	Field and Description
static String	ENDPOINT_PREFIX The region metadata service name for computing region endpoints.

Method Summary

Modifier and Type	Method and Description
ResponseMetadata	getCachedResponseMetadata(AmazonWebServiceRequest request) Returns additional metadata for a previously executed successful request, typically used for debugging issues where a service isn't acting as expected.
InvokeEndpointResult	invokeEndpoint(InvokeEndpointRequest invokeEndpointRequest) After you deploy a model into production using Amazon SageMaker hosting services, your client applications use this API to get inferences from the model hosted at the specified endpoint.
void	shutdown() Shuts down this client object, releasing any resources that might be held open.

Field Detail

ENDPOINT_PREFIX

static final String ENDPOINT_PREFIX

The region metadata service name for computing region endpoints. You can use this value to retrieve metadata (such as supported regions) of the service.

See Also:

RegionUtils.getRegionsForService(String), Constant Field Values

Method Detail

invokeEndpoint

InvokeEndpointResult invokeEndpoint(InvokeEndpointRequest invokeEndpointRequest)

After you deploy a model into production using Amazon SageMaker 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, see How It Works.

Amazon SageMaker strips all POST headers except those supported by the API. Amazon SageMaker 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 AWS Signature Version 4. For information, see Authenticating Requests (AWS 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 the /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 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.

Throws:

InternalFailureException - An internal failure occurred.

ServiceUnavailableException - The service is unavailable. Try your call again.

ValidationErrorException - Inspect your request and try again.

ModelErrorException - Model (owned by the customer in the container) returned 4xx or 5xx error code.

See Also:

AWS API Documentation

shutdown

void shutdown()

Shuts down this client object, releasing any resources that might be held open. This is an optional method, and callers are not expected to call it, but can if they want to explicitly release any open resources. Once a client has been shutdown, it should not be used to make any more requests.

getCachedResponseMetadata

ResponseMetadata getCachedResponseMetadata(AmazonWebServiceRequest request)

Returns additional metadata for a previously executed successful request, typically used for debugging issues where a service isn't acting as expected. This data isn't considered part of the result data returned by an operation, so it's available through this separate, diagnostic interface.

Response metadata is only cached for a limited period of time, so if you need to access this extra diagnostic information for an executed request, you should use this method to retrieve it as soon as possible after executing a request.

Parameters:

request - The originally executed request.

Returns:

The response metadata for the specified request, or null if none is available.