sagemakerruntime/aws.sdk.kotlin.services.sagemakerruntime/SageMakerRuntimeClient

SageMakerRuntimeClient

interface SageMakerRuntimeClient : SdkClient

The Amazon SageMaker AI runtime API.

Types

class Builder : AbstractSdkClientBuilder<SageMakerRuntimeClient.Config, SageMakerRuntimeClient.Config.Builder, SageMakerRuntimeClient>

Companion

object Companion : AbstractAwsSdkClientFactory<SageMakerRuntimeClient.Config, SageMakerRuntimeClient.Config.Builder, SageMakerRuntimeClient, SageMakerRuntimeClient.Builder>

Config

class Config : AwsSdkClientConfig, CredentialsProviderConfig, HttpAuthConfig, HttpClientConfig, HttpEngineConfig, RetryClientConfig, RetryStrategyClientConfig, SdkClientConfig, TelemetryConfig, TimeoutConfig

Properties

config

abstract override val config: SageMakerRuntimeClient.Config

SageMakerRuntimeClient's configuration

Functions

invokeEndpoint

abstract suspend fun invokeEndpoint(input: InvokeEndpointRequest): InvokeEndpointResponse

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.

invokeEndpointAsync

abstract suspend fun invokeEndpointAsync(input: InvokeEndpointAsyncRequest): InvokeEndpointAsyncResponse

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.

invokeEndpointWithResponseStream

abstract suspend fun <T> invokeEndpointWithResponseStream(input: InvokeEndpointWithResponseStreamRequest, block: suspend (InvokeEndpointWithResponseStreamResponse) -> T): T

Invokes a model at the specified endpoint to return the inference response as a stream. The inference stream provides the response payload incrementally as a series of parts. Before you can get an inference stream, you must have access to a model that's deployed using Amazon SageMaker AI hosting services, and the container for that model must support inference streaming.

Inherited functions

expect abstract fun close()

invokeEndpoint

inline suspend fun SageMakerRuntimeClient.invokeEndpoint(crossinline block: InvokeEndpointRequest.Builder.() -> Unit): InvokeEndpointResponse

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.

invokeEndpointAsync

inline suspend fun SageMakerRuntimeClient.invokeEndpointAsync(crossinline block: InvokeEndpointAsyncRequest.Builder.() -> Unit): InvokeEndpointAsyncResponse

withConfig

fun SageMakerRuntimeClient.withConfig(block: SageMakerRuntimeClient.Config.Builder.() -> Unit): SageMakerRuntimeClient

Create a copy of the client with one or more configuration values overridden. This method allows the caller to perform scoped config overrides for one or more client operations.