AWS.Tools.SageMakerRuntime.XML
|
<?xml version="1.0"?>
<doc> <assembly> <name>AWS.Tools.SageMakerRuntime</name> </assembly> <members> <member name="T:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointCmdlet"> <summary> 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. <para> For an overview of Amazon SageMaker, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/how-it-works.html">How It Works</a>. </para><para> 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. </para><para> Calls to <code>InvokeEndpoint</code> are authenticated by using AWS Signature Version 4. For information, see <a href="https://docs.aws.amazon.com/AmazonS3/latest/API/sig-v4-authenticating-requests.html">Authenticating Requests (AWS Signature Version 4)</a> in the <i>Amazon S3 API Reference</i>. </para><para> 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. </para><note><para> 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. </para></note> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointCmdlet.Accept"> <summary> <para> <para>The desired MIME type of the inference in the response.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointCmdlet.Body"> <summary> <para> <para>Provides input data, in the format specified in the <code>ContentType</code> request header. Amazon SageMaker passes all of the data in the body to the model. </para><para>For information about the format of the request body, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html">Common Data Formats-Inference</a>.</para> </para> <para>The cmdlet will automatically convert the supplied parameter of type string, string[], System.IO.FileInfo or System.IO.Stream to byte[] before supplying it to the service.</para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointCmdlet.ContentType"> <summary> <para> <para>The MIME type of the input data in the request body.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointCmdlet.CustomAttribute"> <summary> <para> <para>Provides additional information about a request for an inference submitted to a model hosted at an Amazon SageMaker endpoint. The information is an opaque value that is forwarded verbatim. You could use this value, for example, to provide an ID that you can use to track a request or to provide other metadata that a service endpoint was programmed to process. The value must consist of no more than 1024 visible US-ASCII characters as specified in <a href="https://tools.ietf.org/html/rfc7230#section-3.2.6">Section 3.3.6. Field Value Components</a> of the Hypertext Transfer Protocol (HTTP/1.1). </para><para>The code in your model is responsible for setting or updating any custom attributes in the response. If your code does not set this value in the response, an empty value is returned. For example, if a custom attribute represents the trace ID, your model can prepend the custom attribute with <code>Trace ID:</code> in your post-processing function.</para><para>This feature is currently supported in the AWS SDKs but not in the Amazon SageMaker Python SDK.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointCmdlet.EndpointName"> <summary> <para> <para>The name of the endpoint that you specified when you created the endpoint using the <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/API_CreateEndpoint.html">CreateEndpoint</a> API. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointCmdlet.InferenceId"> <summary> <para> <para>If you provide a value, it is added to the captured data when you enable data capture on the endpoint. For information about data capture, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/model-monitor-data-capture.html">Capture Data</a>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointCmdlet.TargetContainerHostname"> <summary> <para> <para>If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointCmdlet.TargetModel"> <summary> <para> <para>The model to request for inference when invoking a multi-model endpoint.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointCmdlet.TargetVariant"> <summary> <para> <para>Specify the production variant to send the inference request to when invoking an endpoint that is running two or more variants. Note that this parameter overrides the default behavior for the endpoint, which is to distribute the invocation traffic based on the variant weights.</para><para>For information about how to use variant targeting to perform a/b testing, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/model-ab-testing.html">Test models in production</a></para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointCmdlet.Select"> <summary> Use the -Select parameter to control the cmdlet output. The default value is '*'. Specifying -Select '*' will result in the cmdlet returning the whole service response (Amazon.SageMakerRuntime.Model.InvokeEndpointResponse). Specifying the name of a property of type Amazon.SageMakerRuntime.Model.InvokeEndpointResponse will result in that property being returned. Specifying -Select '^ParameterName' will result in the cmdlet returning the selected cmdlet parameter value. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointCmdlet.PassThru"> <summary> Changes the cmdlet behavior to return the value passed to the EndpointName parameter. The -PassThru parameter is deprecated, use -Select '^EndpointName' instead. This parameter will be removed in a future version. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointCmdlet.Force"> <summary> This parameter overrides confirmation prompts to force the cmdlet to continue its operation. This parameter should always be used with caution. </summary> </member> <member name="T:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointAsyncCmdlet"> <summary> 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. <para> Inference requests sent to this API are enqueued for asynchronous processing. The processing of the inference request may or may not complete before the 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. </para><para> Amazon SageMaker strips all <code>POST</code> 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. </para><para> Calls to <code>InvokeEndpointAsync</code> are authenticated by using AWS Signature Version 4. For information, see <a href="https://docs.aws.amazon.com/AmazonS3/latest/API/sig-v4-authenticating-requests.html">Authenticating Requests (AWS Signature Version 4)</a> in the <i>Amazon S3 API Reference</i>. </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointAsyncCmdlet.Accept"> <summary> <para> <para>The desired MIME type of the inference in the response.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointAsyncCmdlet.ContentType"> <summary> <para> <para>The MIME type of the input data in the request body.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointAsyncCmdlet.CustomAttribute"> <summary> <para> <para>Provides additional information about a request for an inference submitted to a model hosted at an Amazon SageMaker endpoint. The information is an opaque value that is forwarded verbatim. You could use this value, for example, to provide an ID that you can use to track a request or to provide other metadata that a service endpoint was programmed to process. The value must consist of no more than 1024 visible US-ASCII characters as specified in <a href="https://datatracker.ietf.org/doc/html/rfc7230#section-3.2.6">Section 3.3.6. Field Value Components</a> of the Hypertext Transfer Protocol (HTTP/1.1). </para><para>The code in your model is responsible for setting or updating any custom attributes in the response. If your code does not set this value in the response, an empty value is returned. For example, if a custom attribute represents the trace ID, your model can prepend the custom attribute with <code>Trace ID</code>: in your post-processing function. </para><para>This feature is currently supported in the AWS SDKs but not in the Amazon SageMaker Python SDK. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointAsyncCmdlet.EndpointName"> <summary> <para> <para>The name of the endpoint that you specified when you created the endpoint using the <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html"><code>CreateEndpoint</code></a> API.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointAsyncCmdlet.InferenceId"> <summary> <para> <para>The identifier for the inference request. Amazon SageMaker will generate an identifier for you if none is specified. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointAsyncCmdlet.InputLocation"> <summary> <para> <para>The Amazon S3 URI where the inference request payload is stored.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointAsyncCmdlet.RequestTTLSecond"> <summary> <para> <para>Maximum age in seconds a request can be in the queue before it is marked as expired.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointAsyncCmdlet.Select"> <summary> Use the -Select parameter to control the cmdlet output. The default value is '*'. Specifying -Select '*' will result in the cmdlet returning the whole service response (Amazon.SageMakerRuntime.Model.InvokeEndpointAsyncResponse). Specifying the name of a property of type Amazon.SageMakerRuntime.Model.InvokeEndpointAsyncResponse will result in that property being returned. Specifying -Select '^ParameterName' will result in the cmdlet returning the selected cmdlet parameter value. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointAsyncCmdlet.PassThru"> <summary> Changes the cmdlet behavior to return the value passed to the EndpointName parameter. The -PassThru parameter is deprecated, use -Select '^EndpointName' instead. This parameter will be removed in a future version. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.SMR.InvokeSMREndpointAsyncCmdlet.Force"> <summary> This parameter overrides confirmation prompts to force the cmdlet to continue its operation. This parameter should always be used with caution. </summary> </member> </members> </doc> |