SageMakerRuntime

Service object for interacting with AWS SageMakerRuntime service.

public struct SageMakerRuntime: AWSService

The Amazon SageMaker runtime API.

Inheritance

AWSService

Initializers

init(client:region:partition:endpoint:timeout:byteBufferAllocator:options:)

Initialize the SageMakerRuntime client

public init(client: AWSClient, region: SotoCore.Region? = nil, partition: AWSPartition = .aws, endpoint: String? = nil, timeout: TimeAmount? = nil, byteBufferAllocator: ByteBufferAllocator = ByteBufferAllocator(), options: AWSServiceConfig.Options = [])

Parameters

• client: AWSClient used to process requests
• region: Region of server you want to communicate with. This will override the partition parameter.
• partition: AWS partition where service resides, standard (.aws), china (.awscn), government (.awsusgov).
• endpoint: Custom endpoint URL to use instead of standard AWS servers
• timeout: Timeout value for HTTP requests

init(from:patch:)

Initializer required by AWSService.with(middlewares:​timeout:​byteBufferAllocator:​options). You are not able to use this initializer directly as there are no public initializers for AWSServiceConfig.Patch. Please use AWSService.with(middlewares:​timeout:​byteBufferAllocator:​options) instead.

public init(from: SageMakerRuntime, patch: AWSServiceConfig.Patch)

Properties

client

Client used for communication with AWS

let client: AWSClient

config

Service configuration

let config: AWSServiceConfig

Methods

invokeEndpoint(_:logger:on:)

public func invokeEndpoint(_ input: InvokeEndpointInput, logger: Logger = AWSClient.loggingDisabled, on eventLoop: EventLoop? = nil) -> EventLoopFuture<InvokeEndpointOutput>

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.