| Package | Description |
|---|---|
| com.amazonaws.services.sagemakerruntime |
The Amazon SageMaker runtime API.
|
| com.amazonaws.services.sagemakerruntime.model |
| Modifier and Type | Method and Description |
|---|---|
InvokeEndpointAsyncResult |
AmazonSageMakerRuntimeClient.invokeEndpointAsync(InvokeEndpointAsyncRequest request)
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 in an asynchronous manner.
|
InvokeEndpointAsyncResult |
AmazonSageMakerRuntime.invokeEndpointAsync(InvokeEndpointAsyncRequest invokeEndpointAsyncRequest)
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 in an asynchronous manner.
|
InvokeEndpointAsyncResult |
AbstractAmazonSageMakerRuntime.invokeEndpointAsync(InvokeEndpointAsyncRequest request) |
| Modifier and Type | Method and Description |
|---|---|
Future<InvokeEndpointAsyncResult> |
AmazonSageMakerRuntimeAsyncClient.invokeEndpointAsyncAsync(InvokeEndpointAsyncRequest request) |
Future<InvokeEndpointAsyncResult> |
AmazonSageMakerRuntimeAsync.invokeEndpointAsyncAsync(InvokeEndpointAsyncRequest invokeEndpointAsyncRequest)
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 in an asynchronous manner.
|
Future<InvokeEndpointAsyncResult> |
AbstractAmazonSageMakerRuntimeAsync.invokeEndpointAsyncAsync(InvokeEndpointAsyncRequest request) |
Future<InvokeEndpointAsyncResult> |
AmazonSageMakerRuntimeAsyncClient.invokeEndpointAsyncAsync(InvokeEndpointAsyncRequest request,
AsyncHandler<InvokeEndpointAsyncRequest,InvokeEndpointAsyncResult> asyncHandler) |
Future<InvokeEndpointAsyncResult> |
AmazonSageMakerRuntimeAsync.invokeEndpointAsyncAsync(InvokeEndpointAsyncRequest invokeEndpointAsyncRequest,
AsyncHandler<InvokeEndpointAsyncRequest,InvokeEndpointAsyncResult> asyncHandler)
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 in an asynchronous manner.
|
Future<InvokeEndpointAsyncResult> |
AbstractAmazonSageMakerRuntimeAsync.invokeEndpointAsyncAsync(InvokeEndpointAsyncRequest request,
AsyncHandler<InvokeEndpointAsyncRequest,InvokeEndpointAsyncResult> asyncHandler) |
| Modifier and Type | Method and Description |
|---|---|
Future<InvokeEndpointAsyncResult> |
AmazonSageMakerRuntimeAsyncClient.invokeEndpointAsyncAsync(InvokeEndpointAsyncRequest request,
AsyncHandler<InvokeEndpointAsyncRequest,InvokeEndpointAsyncResult> asyncHandler) |
Future<InvokeEndpointAsyncResult> |
AmazonSageMakerRuntimeAsync.invokeEndpointAsyncAsync(InvokeEndpointAsyncRequest invokeEndpointAsyncRequest,
AsyncHandler<InvokeEndpointAsyncRequest,InvokeEndpointAsyncResult> asyncHandler)
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 in an asynchronous manner.
|
Future<InvokeEndpointAsyncResult> |
AbstractAmazonSageMakerRuntimeAsync.invokeEndpointAsyncAsync(InvokeEndpointAsyncRequest request,
AsyncHandler<InvokeEndpointAsyncRequest,InvokeEndpointAsyncResult> asyncHandler) |
| Modifier and Type | Method and Description |
|---|---|
InvokeEndpointAsyncResult |
InvokeEndpointAsyncResult.clone() |
InvokeEndpointAsyncResult |
InvokeEndpointAsyncResult.withInferenceId(String inferenceId)
Identifier for an inference request.
|
InvokeEndpointAsyncResult |
InvokeEndpointAsyncResult.withOutputLocation(String outputLocation)
The Amazon S3 URI where the inference response payload is stored.
|
Copyright © 2022. All rights reserved.