Class: Aws::SageMakerRuntime::Types::InvokeEndpointWithResponseStreamInput
- Inherits:
-
Struct
- Object
- Struct
- Aws::SageMakerRuntime::Types::InvokeEndpointWithResponseStreamInput
- Includes:
- Aws::Structure
- Defined in:
- lib/aws-sdk-sagemakerruntime/types.rb
Overview
Constant Summary collapse
- SENSITIVE =
[:body, :custom_attributes]
Instance Attribute Summary collapse
-
#accept ⇒ String
The desired MIME type of the inference response from the model container.
-
#body ⇒ String
Provides input data, in the format specified in the ‘ContentType` request header.
-
#content_type ⇒ String
The MIME type of the input data in the request body.
-
#custom_attributes ⇒ String
Provides additional information about a request for an inference submitted to a model hosted at an Amazon SageMaker endpoint.
-
#endpoint_name ⇒ String
The name of the endpoint that you specified when you created the endpoint using the [CreateEndpoint] API.
-
#inference_component_name ⇒ String
If the endpoint hosts one or more inference components, this parameter specifies the name of inference component to invoke for a streaming response.
-
#inference_id ⇒ String
An identifier that you assign to your request.
-
#session_id ⇒ String
The ID of a stateful session to handle your request.
-
#target_container_hostname ⇒ String
If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.
-
#target_variant ⇒ String
Specify the production variant to send the inference request to when invoking an endpoint that is running two or more variants.
Instance Attribute Details
#accept ⇒ String
The desired MIME type of the inference response from the model container.
477 478 479 480 481 482 483 484 485 486 487 488 489 490 |
# File 'lib/aws-sdk-sagemakerruntime/types.rb', line 477 class InvokeEndpointWithResponseStreamInput < Struct.new( :endpoint_name, :body, :content_type, :accept, :custom_attributes, :target_variant, :target_container_hostname, :inference_id, :inference_component_name, :session_id) SENSITIVE = [:body, :custom_attributes] include Aws::Structure end |
#body ⇒ String
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].
[1]: docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html
477 478 479 480 481 482 483 484 485 486 487 488 489 490 |
# File 'lib/aws-sdk-sagemakerruntime/types.rb', line 477 class InvokeEndpointWithResponseStreamInput < Struct.new( :endpoint_name, :body, :content_type, :accept, :custom_attributes, :target_variant, :target_container_hostname, :inference_id, :inference_component_name, :session_id) SENSITIVE = [:body, :custom_attributes] include Aws::Structure end |
#content_type ⇒ String
The MIME type of the input data in the request body.
477 478 479 480 481 482 483 484 485 486 487 488 489 490 |
# File 'lib/aws-sdk-sagemakerruntime/types.rb', line 477 class InvokeEndpointWithResponseStreamInput < Struct.new( :endpoint_name, :body, :content_type, :accept, :custom_attributes, :target_variant, :target_container_hostname, :inference_id, :inference_component_name, :session_id) SENSITIVE = [:body, :custom_attributes] include Aws::Structure end |
#custom_attributes ⇒ String
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.
477 478 479 480 481 482 483 484 485 486 487 488 489 490 |
# File 'lib/aws-sdk-sagemakerruntime/types.rb', line 477 class InvokeEndpointWithResponseStreamInput < Struct.new( :endpoint_name, :body, :content_type, :accept, :custom_attributes, :target_variant, :target_container_hostname, :inference_id, :inference_component_name, :session_id) SENSITIVE = [:body, :custom_attributes] include Aws::Structure end |
#endpoint_name ⇒ String
The name of the endpoint that you specified when you created the endpoint using the [CreateEndpoint] API.
[1]: docs.aws.amazon.com/sagemaker/latest/dg/API_CreateEndpoint.html
477 478 479 480 481 482 483 484 485 486 487 488 489 490 |
# File 'lib/aws-sdk-sagemakerruntime/types.rb', line 477 class InvokeEndpointWithResponseStreamInput < Struct.new( :endpoint_name, :body, :content_type, :accept, :custom_attributes, :target_variant, :target_container_hostname, :inference_id, :inference_component_name, :session_id) SENSITIVE = [:body, :custom_attributes] include Aws::Structure end |
#inference_component_name ⇒ String
If the endpoint hosts one or more inference components, this parameter specifies the name of inference component to invoke for a streaming response.
477 478 479 480 481 482 483 484 485 486 487 488 489 490 |
# File 'lib/aws-sdk-sagemakerruntime/types.rb', line 477 class InvokeEndpointWithResponseStreamInput < Struct.new( :endpoint_name, :body, :content_type, :accept, :custom_attributes, :target_variant, :target_container_hostname, :inference_id, :inference_component_name, :session_id) SENSITIVE = [:body, :custom_attributes] include Aws::Structure end |
#inference_id ⇒ String
An identifier that you assign to your request.
477 478 479 480 481 482 483 484 485 486 487 488 489 490 |
# File 'lib/aws-sdk-sagemakerruntime/types.rb', line 477 class InvokeEndpointWithResponseStreamInput < Struct.new( :endpoint_name, :body, :content_type, :accept, :custom_attributes, :target_variant, :target_container_hostname, :inference_id, :inference_component_name, :session_id) SENSITIVE = [:body, :custom_attributes] include Aws::Structure end |
#session_id ⇒ String
The ID of a stateful session to handle your request.
You can’t create a stateful session by using the ‘InvokeEndpointWithResponseStream` action. Instead, you can create one by using the ` InvokeEndpoint ` action. In your request, you specify `NEW_SESSION` for the `SessionId` request parameter. The response to that request provides the session ID for the `NewSessionId` response parameter.
477 478 479 480 481 482 483 484 485 486 487 488 489 490 |
# File 'lib/aws-sdk-sagemakerruntime/types.rb', line 477 class InvokeEndpointWithResponseStreamInput < Struct.new( :endpoint_name, :body, :content_type, :accept, :custom_attributes, :target_variant, :target_container_hostname, :inference_id, :inference_component_name, :session_id) SENSITIVE = [:body, :custom_attributes] include Aws::Structure end |
#target_container_hostname ⇒ String
If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.
477 478 479 480 481 482 483 484 485 486 487 488 489 490 |
# File 'lib/aws-sdk-sagemakerruntime/types.rb', line 477 class InvokeEndpointWithResponseStreamInput < Struct.new( :endpoint_name, :body, :content_type, :accept, :custom_attributes, :target_variant, :target_container_hostname, :inference_id, :inference_component_name, :session_id) SENSITIVE = [:body, :custom_attributes] include Aws::Structure end |
#target_variant ⇒ String
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]
[1]: docs.aws.amazon.com/sagemaker/latest/dg/model-ab-testing.html
477 478 479 480 481 482 483 484 485 486 487 488 489 490 |
# File 'lib/aws-sdk-sagemakerruntime/types.rb', line 477 class InvokeEndpointWithResponseStreamInput < Struct.new( :endpoint_name, :body, :content_type, :accept, :custom_attributes, :target_variant, :target_container_hostname, :inference_id, :inference_component_name, :session_id) SENSITIVE = [:body, :custom_attributes] include Aws::Structure end |