Interface InvokeEndpointRequest.Builder
- All Superinterfaces:
AwsRequest.Builder
,Buildable
,CopyableBuilder<InvokeEndpointRequest.Builder,
,InvokeEndpointRequest> SageMakerRuntimeRequest.Builder
,SdkBuilder<InvokeEndpointRequest.Builder,
,InvokeEndpointRequest> SdkPojo
,SdkRequest.Builder
- Enclosing class:
InvokeEndpointRequest
-
Method Summary
Modifier and TypeMethodDescriptionThe desired MIME type of the inference response from the model container.Provides input data, in the format specified in theContentType
request header.contentType
(String contentType) The MIME type of the input data in the request body.customAttributes
(String customAttributes) Provides additional information about a request for an inference submitted to a model hosted at an Amazon SageMaker endpoint.enableExplanations
(String enableExplanations) An optional JMESPath expression used to override theEnableExplanations
parameter of theClarifyExplainerConfig
API.endpointName
(String endpointName) The name of the endpoint that you specified when you created the endpoint using the CreateEndpoint API.inferenceComponentName
(String inferenceComponentName) If the endpoint hosts one or more inference components, this parameter specifies the name of inference component to invoke.inferenceId
(String inferenceId) If you provide a value, it is added to the captured data when you enable data capture on the endpoint.overrideConfiguration
(Consumer<AwsRequestOverrideConfiguration.Builder> builderConsumer) Add an optional request override configuration.overrideConfiguration
(AwsRequestOverrideConfiguration overrideConfiguration) Add an optional request override configuration.targetContainerHostname
(String targetContainerHostname) If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.targetModel
(String targetModel) The model to request for inference when invoking a multi-model endpoint.targetVariant
(String targetVariant) Specify the production variant to send the inference request to when invoking an endpoint that is running two or more variants.Methods inherited from interface software.amazon.awssdk.awscore.AwsRequest.Builder
overrideConfiguration
Methods inherited from interface software.amazon.awssdk.utils.builder.CopyableBuilder
copy
Methods inherited from interface software.amazon.awssdk.services.sagemakerruntime.model.SageMakerRuntimeRequest.Builder
build
Methods inherited from interface software.amazon.awssdk.utils.builder.SdkBuilder
applyMutation, build
Methods inherited from interface software.amazon.awssdk.core.SdkPojo
equalsBySdkFields, sdkFields
-
Method Details
-
endpointName
The name of the endpoint that you specified when you created the endpoint using the CreateEndpoint API.
- Parameters:
endpointName
- The name of the endpoint that you specified when you created the endpoint using the CreateEndpoint API.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
body
Provides input data, in the format specified in the
ContentType
request header. Amazon SageMaker passes all of the data in the body to the model.For information about the format of the request body, see Common Data Formats-Inference.
- Parameters:
body
- Provides input data, in the format specified in theContentType
request header. Amazon SageMaker passes all of the data in the body to the model.For information about the format of the request body, see Common Data Formats-Inference.
- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
contentType
The MIME type of the input data in the request body.
- Parameters:
contentType
- The MIME type of the input data in the request body.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
accept
The desired MIME type of the inference response from the model container.
- Parameters:
accept
- The desired MIME type of the inference response from the model container.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
customAttributes
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 Section 3.3.6. Field Value Components of the Hypertext Transfer Protocol (HTTP/1.1).
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
Trace ID:
in your post-processing function.This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker Python SDK.
- Parameters:
customAttributes
- 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 Section 3.3.6. Field Value Components of the Hypertext Transfer Protocol (HTTP/1.1).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
Trace ID:
in your post-processing function.This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker Python SDK.
- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
targetModel
The model to request for inference when invoking a multi-model endpoint.
- Parameters:
targetModel
- The model to request for inference when invoking a multi-model endpoint.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
targetVariant
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.
For information about how to use variant targeting to perform a/b testing, see Test models in production
- Parameters:
targetVariant
- 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.For information about how to use variant targeting to perform a/b testing, see Test models in production
- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
targetContainerHostname
If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.
- Parameters:
targetContainerHostname
- If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
inferenceId
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 Capture Data.
- Parameters:
inferenceId
- 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 Capture Data.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
enableExplanations
An optional JMESPath expression used to override the
EnableExplanations
parameter of theClarifyExplainerConfig
API. See the EnableExplanations section in the developer guide for more information.- Parameters:
enableExplanations
- An optional JMESPath expression used to override theEnableExplanations
parameter of theClarifyExplainerConfig
API. See the EnableExplanations section in the developer guide for more information.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
inferenceComponentName
If the endpoint hosts one or more inference components, this parameter specifies the name of inference component to invoke.
- Parameters:
inferenceComponentName
- If the endpoint hosts one or more inference components, this parameter specifies the name of inference component to invoke.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
overrideConfiguration
InvokeEndpointRequest.Builder overrideConfiguration(AwsRequestOverrideConfiguration overrideConfiguration) Description copied from interface:AwsRequest.Builder
Add an optional request override configuration.- Specified by:
overrideConfiguration
in interfaceAwsRequest.Builder
- Parameters:
overrideConfiguration
- The override configuration.- Returns:
- This object for method chaining.
-
overrideConfiguration
InvokeEndpointRequest.Builder overrideConfiguration(Consumer<AwsRequestOverrideConfiguration.Builder> builderConsumer) Description copied from interface:AwsRequest.Builder
Add an optional request override configuration.- Specified by:
overrideConfiguration
in interfaceAwsRequest.Builder
- Parameters:
builderConsumer
- AConsumer
to which an emptyAwsRequestOverrideConfiguration.Builder
will be given.- Returns:
- This object for method chaining.
-