aws-sdk-sagemakerruntime 1.54.0 → 1.56.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9f21de9b72cc1eeaea95502e8968924a9473a20d3a81944f04180cc71aea7eec
-  data.tar.gz: 8c101dc28cfaee84f907c4b1c4bc8ec3ae8e37f245c18ad6bbdec6021aff9208
+  metadata.gz: 69c3165f42413efed12d84d750651ff552988f08644a9017ca730a704b161fc8
+  data.tar.gz: 54cdac76d78ebf92c584aa256c0eb709813dfab164a57aaf6933347dbdd39100
 SHA512:
-  metadata.gz: 5477be891a298896bf2e4c371e37a55ac640b1b5ee8fb76a5e348a893a904a8b712230d32816bc9c741a07440f4c0caeeaa2eec21684b32ec70a5fa613249b0e
-  data.tar.gz: d74bf3109fd065cd3c9812e95e24da78d71d02940ac8af1f04a2108408b8e4f9a014a2f38787f99ffb130d747ed1ed5b7d94bccabd194621d34182f2371e4bd4
+  metadata.gz: 9202ac77cab11e6ef4b0134fae4c5a059a406adde5d596da6eccec4f5f5dec9fde70e7fe59733e863b3933ecdbe9f317ab3852038d93d88a92ba785fdd325d0e
+  data.tar.gz: ab5dd093eeadc255912c18932e0d5147101c297e016c89701d283bb08f8878535b6c1f03b9d6e9c6abc02a1d97d66abbdccf3849fade07531f6718fee1c37922

data/CHANGELOG.md

@@ -1,6 +1,16 @@
 Unreleased Changes
 ------------------
 
+1.56.0 (2023-09-27)
+------------------
+
+* Feature - Code Generated Changes, see `./build_tools` or `aws-sdk-core`'s CHANGELOG.md for details.
+
+1.55.0 (2023-08-31)
+------------------
+
+* Feature - This release adds a new InvokeEndpointWithResponseStream API to support streaming of model responses.
+
 1.54.0 (2023-07-11)
 ------------------
 

data/VERSION

@@ -1 +1 @@
-1.54.0
+1.56.0

data/lib/aws-sdk-sagemakerruntime/client.rb

@@ -33,6 +33,7 @@ require 'aws-sdk-core/plugins/defaults_mode.rb'
 require 'aws-sdk-core/plugins/recursion_detection.rb'
 require 'aws-sdk-core/plugins/sign.rb'
 require 'aws-sdk-core/plugins/protocols/rest_json.rb'
+require 'aws-sdk-core/plugins/event_stream_configuration.rb'
 
 Aws::Plugins::GlobalConfiguration.add_identifier(:sagemakerruntime)
 
@@ -83,6 +84,7 @@ module Aws::SageMakerRuntime
     add_plugin(Aws::Plugins::RecursionDetection)
     add_plugin(Aws::Plugins::Sign)
     add_plugin(Aws::Plugins::Protocols::RestJson)
+    add_plugin(Aws::Plugins::EventStreamConfiguration)
     add_plugin(Aws::SageMakerRuntime::Plugins::Endpoints)
 
     # @overload initialize(options)
@@ -216,10 +218,16 @@ module Aws::SageMakerRuntime
     #   @option options [Boolean] :endpoint_discovery (false)
     #     When set to `true`, endpoint discovery will be enabled for operations when available.
     #
+    #   @option options [Proc] :event_stream_handler
+    #     When an EventStream or Proc object is provided, it will be used as callback for each chunk of event stream response received along the way.
+    #
     #   @option options [Boolean] :ignore_configured_endpoint_urls
     #     Setting to true disables use of endpoint URLs provided via environment
     #     variables and the shared configuration file.
     #
+    #   @option options [Proc] :input_event_stream_handler
+    #     When an EventStream or Proc object is provided, it can be used for sending events for the event stream.
+    #
     #   @option options [Aws::Log::Formatter] :log_formatter (Aws::Log::Formatter.default)
     #     The log formatter.
     #
@@ -236,6 +244,9 @@ module Aws::SageMakerRuntime
     #     setting this value to 5 will result in a request being retried up to
     #     4 times. Used in `standard` and `adaptive` retry modes.
     #
+    #   @option options [Proc] :output_event_stream_handler
+    #     When an EventStream or Proc object is provided, it will be used as callback for each chunk of event stream response received along the way.
+    #
     #   @option options [String] :profile ("default")
     #     Used when loading credentials from the shared credentials file
     #     at HOME/.aws/credentials.  When not specified, 'default' is used.
@@ -446,7 +457,8 @@ module Aws::SageMakerRuntime
     #   The MIME type of the input data in the request body.
     #
     # @option params [String] :accept
-    #   The desired MIME type of the inference in the response.
+    #   The desired MIME type of the inference response from the model
+    #   container.
     #
     # @option params [String] :custom_attributes
     #   Provides additional information about a request for an inference
@@ -469,7 +481,7 @@ module Aws::SageMakerRuntime
     #
     #
     #
-    #   [1]: https://tools.ietf.org/html/rfc7230#section-3.2.6
+    #   [1]: https://datatracker.ietf.org/doc/html/rfc7230#section-3.2.6
     #
     # @option params [String] :target_model
     #   The model to request for inference when invoking a multi-model
@@ -561,8 +573,8 @@ module Aws::SageMakerRuntime
     # from this API will not contain the result of the inference request but
     # contain information about where you can locate it.
     #
-    # Amazon SageMaker strips all `POST` headers except those supported by
-    # the API. Amazon SageMaker might add additional headers. You should not
+    # 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.
     #
@@ -577,17 +589,18 @@ module Aws::SageMakerRuntime
     #
     # @option params [required, String] :endpoint_name
     #   The name of the endpoint that you specified when you created the
-    #   endpoint using the [ `CreateEndpoint` ][1] API.
+    #   endpoint using the [CreateEndpoint][1] API.
     #
     #
     #
-    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/API_CreateEndpoint.html
     #
     # @option params [String] :content_type
     #   The MIME type of the input data in the request body.
     #
     # @option params [String] :accept
-    #   The desired MIME type of the inference in the response.
+    #   The desired MIME type of the inference response from the model
+    #   container.
     #
     # @option params [String] :custom_attributes
     #   Provides additional information about a request for an inference
@@ -603,7 +616,7 @@ module Aws::SageMakerRuntime
     #   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.
+    #   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.
@@ -661,6 +674,278 @@ module Aws::SageMakerRuntime
       req.send_request(options)
     end
 
+    # 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 hosting services, and the container for that
+    # model must support inference streaming.
+    #
+    # For more information that can help you use this API, see the following
+    # sections in the *Amazon SageMaker Developer Guide*:
+    #
+    # * For information about how to add streaming support to a model, see
+    #   [How Containers Serve Requests][1].
+    #
+    # * For information about how to process the streaming response, see
+    #   [Invoke real-time endpoints][2].
+    #
+    # 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.
+    #
+    # Calls to `InvokeEndpointWithResponseStream` are authenticated by using
+    # Amazon Web Services Signature Version 4. For information, see
+    # [Authenticating Requests (Amazon Web Services Signature Version 4)][3]
+    # in the *Amazon S3 API Reference*.
+    #
+    #
+    #
+    # [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-inference-code.html#your-algorithms-inference-code-how-containe-serves-requests
+    # [2]: https://docs.aws.amazon.com/sagemaker/latest/dg/realtime-endpoints-test-endpoints.html
+    # [3]: https://docs.aws.amazon.com/AmazonS3/latest/API/sig-v4-authenticating-requests.html
+    #
+    # @option params [required, String] :endpoint_name
+    #   The name of the endpoint that you specified when you created the
+    #   endpoint using the [CreateEndpoint][1] API.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/API_CreateEndpoint.html
+    #
+    # @option params [required, String, StringIO, File] :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][1].
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html
+    #
+    # @option params [String] :content_type
+    #   The MIME type of the input data in the request body.
+    #
+    # @option params [String] :accept
+    #   The desired MIME type of the inference response from the model
+    #   container.
+    #
+    # @option params [String] :custom_attributes
+    #   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][1] 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.
+    #
+    #
+    #
+    #   [1]: https://datatracker.ietf.org/doc/html/rfc7230#section-3.2.6
+    #
+    # @option params [String] :target_variant
+    #   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]
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/model-ab-testing.html
+    #
+    # @option params [String] :target_container_hostname
+    #   If the endpoint hosts multiple containers and is configured to use
+    #   direct invocation, this parameter specifies the host name of the
+    #   container to invoke.
+    #
+    # @option params [String] :inference_id
+    #   An identifier that you assign to your request.
+    #
+    # @return [Types::InvokeEndpointWithResponseStreamOutput] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
+    #
+    #   * {Types::InvokeEndpointWithResponseStreamOutput#body #body} => Types::ResponseStream
+    #   * {Types::InvokeEndpointWithResponseStreamOutput#content_type #content_type} => String
+    #   * {Types::InvokeEndpointWithResponseStreamOutput#invoked_production_variant #invoked_production_variant} => String
+    #   * {Types::InvokeEndpointWithResponseStreamOutput#custom_attributes #custom_attributes} => String
+    #
+    # @example EventStream Operation Example
+    #
+    #   You can process event once it arrives immediately, or wait until
+    #   full response complete and iterate through eventstream enumerator.
+    #
+    #   To interact with event immediately, you need to register #invoke_endpoint_with_response_stream
+    #   with callbacks, callbacks can be register for specifc events or for all events,
+    #   callback for errors in the event stream is also available for register.
+    #
+    #   Callbacks can be passed in by `:event_stream_handler` option or within block
+    #   statement attached to #invoke_endpoint_with_response_stream call directly. Hybrid pattern of both
+    #   is also supported.
+    #
+    #   `:event_stream_handler` option takes in either Proc object or
+    #   Aws::SageMakerRuntime::EventStreams::ResponseStream object.
+    #
+    #   Usage pattern a): callbacks with a block attached to #invoke_endpoint_with_response_stream
+    #     Example for registering callbacks for all event types and error event
+    #
+    #     client.invoke_endpoint_with_response_stream( # params input# ) do |stream|
+    #       stream.on_error_event do |event|
+    #         # catch unmodeled error event in the stream
+    #         raise event
+    #         # => Aws::Errors::EventError
+    #         # event.event_type => :error
+    #         # event.error_code => String
+    #         # event.error_message => String
+    #       end
+    #
+    #       stream.on_event do |event|
+    #         # process all events arrive
+    #         puts event.event_type
+    #         ...
+    #       end
+    #
+    #     end
+    #
+    #   Usage pattern b): pass in `:event_stream_handler` for #invoke_endpoint_with_response_stream
+    #
+    #     1) create a Aws::SageMakerRuntime::EventStreams::ResponseStream object
+    #     Example for registering callbacks with specific events
+    #
+    #       handler = Aws::SageMakerRuntime::EventStreams::ResponseStream.new
+    #       handler.on_payload_part_event do |event|
+    #         event # => Aws::SageMakerRuntime::Types::PayloadPart
+    #       end
+    #       handler.on_model_stream_error_event do |event|
+    #         event # => Aws::SageMakerRuntime::Types::ModelStreamError
+    #       end
+    #       handler.on_internal_stream_failure_event do |event|
+    #         event # => Aws::SageMakerRuntime::Types::InternalStreamFailure
+    #       end
+    #
+    #     client.invoke_endpoint_with_response_stream( # params input #, event_stream_handler: handler)
+    #
+    #     2) use a Ruby Proc object
+    #     Example for registering callbacks with specific events
+    #
+    #     handler = Proc.new do |stream|
+    #       stream.on_payload_part_event do |event|
+    #         event # => Aws::SageMakerRuntime::Types::PayloadPart
+    #       end
+    #       stream.on_model_stream_error_event do |event|
+    #         event # => Aws::SageMakerRuntime::Types::ModelStreamError
+    #       end
+    #       stream.on_internal_stream_failure_event do |event|
+    #         event # => Aws::SageMakerRuntime::Types::InternalStreamFailure
+    #       end
+    #     end
+    #
+    #     client.invoke_endpoint_with_response_stream( # params input #, event_stream_handler: handler)
+    #
+    #   Usage pattern c): hybird pattern of a) and b)
+    #
+    #       handler = Aws::SageMakerRuntime::EventStreams::ResponseStream.new
+    #       handler.on_payload_part_event do |event|
+    #         event # => Aws::SageMakerRuntime::Types::PayloadPart
+    #       end
+    #       handler.on_model_stream_error_event do |event|
+    #         event # => Aws::SageMakerRuntime::Types::ModelStreamError
+    #       end
+    #       handler.on_internal_stream_failure_event do |event|
+    #         event # => Aws::SageMakerRuntime::Types::InternalStreamFailure
+    #       end
+    #
+    #     client.invoke_endpoint_with_response_stream( # params input #, event_stream_handler: handler) do |stream|
+    #       stream.on_error_event do |event|
+    #         # catch unmodeled error event in the stream
+    #         raise event
+    #         # => Aws::Errors::EventError
+    #         # event.event_type => :error
+    #         # event.error_code => String
+    #         # event.error_message => String
+    #       end
+    #     end
+    #
+    #   Besides above usage patterns for process events when they arrive immediately, you can also
+    #   iterate through events after response complete.
+    #
+    #   Events are available at resp.body # => Enumerator
+    #   For parameter input example, please refer to following request syntax
+    #
+    # @example Request syntax with placeholder values
+    #
+    #   resp = client.invoke_endpoint_with_response_stream({
+    #     endpoint_name: "EndpointName", # required
+    #     body: "data", # required
+    #     content_type: "Header",
+    #     accept: "Header",
+    #     custom_attributes: "CustomAttributesHeader",
+    #     target_variant: "TargetVariantHeader",
+    #     target_container_hostname: "TargetContainerHostnameHeader",
+    #     inference_id: "InferenceId",
+    #   })
+    #
+    # @example Response structure
+    #
+    #   All events are available at resp.body:
+    #   resp.body #=> Enumerator
+    #   resp.body.event_types #=> [:payload_part, :model_stream_error, :internal_stream_failure]
+    #
+    #   For :payload_part event available at #on_payload_part_event callback and response eventstream enumerator:
+    #   event.bytes #=> String
+    #
+    #   For :model_stream_error event available at #on_model_stream_error_event callback and response eventstream enumerator:
+    #   event.message #=> String
+    #   event.error_code #=> String
+    #
+    #   For :internal_stream_failure event available at #on_internal_stream_failure_event callback and response eventstream enumerator:
+    #   event.message #=> String
+    #
+    #   resp.content_type #=> String
+    #   resp.invoked_production_variant #=> String
+    #   resp.custom_attributes #=> String
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/runtime.sagemaker-2017-05-13/InvokeEndpointWithResponseStream AWS API Documentation
+    #
+    # @overload invoke_endpoint_with_response_stream(params = {})
+    # @param [Hash] params ({})
+    def invoke_endpoint_with_response_stream(params = {}, options = {}, &block)
+      params = params.dup
+      event_stream_handler = case handler = params.delete(:event_stream_handler)
+        when EventStreams::ResponseStream then handler
+        when Proc then EventStreams::ResponseStream.new.tap(&handler)
+        when nil then EventStreams::ResponseStream.new
+        else
+          msg = "expected :event_stream_handler to be a block or "\
+                "instance of Aws::SageMakerRuntime::EventStreams::ResponseStream"\
+                ", got `#{handler.inspect}` instead"
+          raise ArgumentError, msg
+        end
+
+      yield(event_stream_handler) if block_given?
+
+      req = build_request(:invoke_endpoint_with_response_stream, params)
+
+      req.context[:event_stream_handler] = event_stream_handler
+      req.handlers.add(Aws::Binary::DecodeHandler, priority: 95)
+
+      req.send_request(options, &block)
+    end
+
     # @!endgroup
 
     # @param params ({})
@@ -674,7 +959,7 @@ module Aws::SageMakerRuntime
         params: params,
         config: config)
       context[:gem_name] = 'aws-sdk-sagemakerruntime'
-      context[:gem_version] = '1.54.0'
+      context[:gem_version] = '1.56.0'
       Seahorse::Client::Request.new(handlers, context)
     end
 

data/lib/aws-sdk-sagemakerruntime/client_api.rb

@@ -17,21 +17,29 @@ module Aws::SageMakerRuntime
     CustomAttributesHeader = Shapes::StringShape.new(name: 'CustomAttributesHeader')
     EnableExplanationsHeader = Shapes::StringShape.new(name: 'EnableExplanationsHeader')
     EndpointName = Shapes::StringShape.new(name: 'EndpointName')
+    ErrorCode = Shapes::StringShape.new(name: 'ErrorCode')
     Header = Shapes::StringShape.new(name: 'Header')
     InferenceId = Shapes::StringShape.new(name: 'InferenceId')
     InputLocationHeader = Shapes::StringShape.new(name: 'InputLocationHeader')
     InternalDependencyException = Shapes::StructureShape.new(name: 'InternalDependencyException')
     InternalFailure = Shapes::StructureShape.new(name: 'InternalFailure')
+    InternalStreamFailure = Shapes::StructureShape.new(name: 'InternalStreamFailure')
     InvocationTimeoutSecondsHeader = Shapes::IntegerShape.new(name: 'InvocationTimeoutSecondsHeader')
     InvokeEndpointAsyncInput = Shapes::StructureShape.new(name: 'InvokeEndpointAsyncInput')
     InvokeEndpointAsyncOutput = Shapes::StructureShape.new(name: 'InvokeEndpointAsyncOutput')
     InvokeEndpointInput = Shapes::StructureShape.new(name: 'InvokeEndpointInput')
     InvokeEndpointOutput = Shapes::StructureShape.new(name: 'InvokeEndpointOutput')
+    InvokeEndpointWithResponseStreamInput = Shapes::StructureShape.new(name: 'InvokeEndpointWithResponseStreamInput')
+    InvokeEndpointWithResponseStreamOutput = Shapes::StructureShape.new(name: 'InvokeEndpointWithResponseStreamOutput')
     LogStreamArn = Shapes::StringShape.new(name: 'LogStreamArn')
     Message = Shapes::StringShape.new(name: 'Message')
     ModelError = Shapes::StructureShape.new(name: 'ModelError')
     ModelNotReadyException = Shapes::StructureShape.new(name: 'ModelNotReadyException')
+    ModelStreamError = Shapes::StructureShape.new(name: 'ModelStreamError')
+    PartBlob = Shapes::BlobShape.new(name: 'PartBlob')
+    PayloadPart = Shapes::StructureShape.new(name: 'PayloadPart')
     RequestTTLSecondsHeader = Shapes::IntegerShape.new(name: 'RequestTTLSecondsHeader')
+    ResponseStream = Shapes::StructureShape.new(name: 'ResponseStream')
     ServiceUnavailable = Shapes::StructureShape.new(name: 'ServiceUnavailable')
     StatusCode = Shapes::IntegerShape.new(name: 'StatusCode')
     TargetContainerHostnameHeader = Shapes::StringShape.new(name: 'TargetContainerHostnameHeader')
@@ -45,6 +53,9 @@ module Aws::SageMakerRuntime
     InternalFailure.add_member(:message, Shapes::ShapeRef.new(shape: Message, location_name: "Message"))
     InternalFailure.struct_class = Types::InternalFailure
 
+    InternalStreamFailure.add_member(:message, Shapes::ShapeRef.new(shape: Message, location_name: "Message"))
+    InternalStreamFailure.struct_class = Types::InternalStreamFailure
+
     InvokeEndpointAsyncInput.add_member(:endpoint_name, Shapes::ShapeRef.new(shape: EndpointName, required: true, location: "uri", location_name: "EndpointName"))
     InvokeEndpointAsyncInput.add_member(:content_type, Shapes::ShapeRef.new(shape: Header, location: "header", location_name: "X-Amzn-SageMaker-Content-Type"))
     InvokeEndpointAsyncInput.add_member(:accept, Shapes::ShapeRef.new(shape: Header, location: "header", location_name: "X-Amzn-SageMaker-Accept"))
@@ -82,6 +93,26 @@ module Aws::SageMakerRuntime
     InvokeEndpointOutput[:payload] = :body
     InvokeEndpointOutput[:payload_member] = InvokeEndpointOutput.member(:body)
 
+    InvokeEndpointWithResponseStreamInput.add_member(:endpoint_name, Shapes::ShapeRef.new(shape: EndpointName, required: true, location: "uri", location_name: "EndpointName"))
+    InvokeEndpointWithResponseStreamInput.add_member(:body, Shapes::ShapeRef.new(shape: BodyBlob, required: true, location_name: "Body"))
+    InvokeEndpointWithResponseStreamInput.add_member(:content_type, Shapes::ShapeRef.new(shape: Header, location: "header", location_name: "Content-Type"))
+    InvokeEndpointWithResponseStreamInput.add_member(:accept, Shapes::ShapeRef.new(shape: Header, location: "header", location_name: "X-Amzn-SageMaker-Accept"))
+    InvokeEndpointWithResponseStreamInput.add_member(:custom_attributes, Shapes::ShapeRef.new(shape: CustomAttributesHeader, location: "header", location_name: "X-Amzn-SageMaker-Custom-Attributes"))
+    InvokeEndpointWithResponseStreamInput.add_member(:target_variant, Shapes::ShapeRef.new(shape: TargetVariantHeader, location: "header", location_name: "X-Amzn-SageMaker-Target-Variant"))
+    InvokeEndpointWithResponseStreamInput.add_member(:target_container_hostname, Shapes::ShapeRef.new(shape: TargetContainerHostnameHeader, location: "header", location_name: "X-Amzn-SageMaker-Target-Container-Hostname"))
+    InvokeEndpointWithResponseStreamInput.add_member(:inference_id, Shapes::ShapeRef.new(shape: InferenceId, location: "header", location_name: "X-Amzn-SageMaker-Inference-Id"))
+    InvokeEndpointWithResponseStreamInput.struct_class = Types::InvokeEndpointWithResponseStreamInput
+    InvokeEndpointWithResponseStreamInput[:payload] = :body
+    InvokeEndpointWithResponseStreamInput[:payload_member] = InvokeEndpointWithResponseStreamInput.member(:body)
+
+    InvokeEndpointWithResponseStreamOutput.add_member(:body, Shapes::ShapeRef.new(shape: ResponseStream, required: true, eventstream: true, location_name: "Body"))
+    InvokeEndpointWithResponseStreamOutput.add_member(:content_type, Shapes::ShapeRef.new(shape: Header, location: "header", location_name: "X-Amzn-SageMaker-Content-Type"))
+    InvokeEndpointWithResponseStreamOutput.add_member(:invoked_production_variant, Shapes::ShapeRef.new(shape: Header, location: "header", location_name: "x-Amzn-Invoked-Production-Variant"))
+    InvokeEndpointWithResponseStreamOutput.add_member(:custom_attributes, Shapes::ShapeRef.new(shape: CustomAttributesHeader, location: "header", location_name: "X-Amzn-SageMaker-Custom-Attributes"))
+    InvokeEndpointWithResponseStreamOutput.struct_class = Types::InvokeEndpointWithResponseStreamOutput
+    InvokeEndpointWithResponseStreamOutput[:payload] = :body
+    InvokeEndpointWithResponseStreamOutput[:payload_member] = InvokeEndpointWithResponseStreamOutput.member(:body)
+
     ModelError.add_member(:message, Shapes::ShapeRef.new(shape: Message, location_name: "Message"))
     ModelError.add_member(:original_status_code, Shapes::ShapeRef.new(shape: StatusCode, location_name: "OriginalStatusCode"))
     ModelError.add_member(:original_message, Shapes::ShapeRef.new(shape: Message, location_name: "OriginalMessage"))
@@ -91,6 +122,18 @@ module Aws::SageMakerRuntime
     ModelNotReadyException.add_member(:message, Shapes::ShapeRef.new(shape: Message, location_name: "Message"))
     ModelNotReadyException.struct_class = Types::ModelNotReadyException
 
+    ModelStreamError.add_member(:message, Shapes::ShapeRef.new(shape: Message, location_name: "Message"))
+    ModelStreamError.add_member(:error_code, Shapes::ShapeRef.new(shape: ErrorCode, location_name: "ErrorCode"))
+    ModelStreamError.struct_class = Types::ModelStreamError
+
+    PayloadPart.add_member(:bytes, Shapes::ShapeRef.new(shape: PartBlob, eventpayload: true, eventpayload_type: 'blob', location_name: "Bytes", metadata: {"eventpayload"=>true}))
+    PayloadPart.struct_class = Types::PayloadPart
+
+    ResponseStream.add_member(:payload_part, Shapes::ShapeRef.new(shape: PayloadPart, event: true, location_name: "PayloadPart"))
+    ResponseStream.add_member(:model_stream_error, Shapes::ShapeRef.new(shape: ModelStreamError, location_name: "ModelStreamError"))
+    ResponseStream.add_member(:internal_stream_failure, Shapes::ShapeRef.new(shape: InternalStreamFailure, location_name: "InternalStreamFailure"))
+    ResponseStream.struct_class = Types::ResponseStream
+
     ServiceUnavailable.add_member(:message, Shapes::ShapeRef.new(shape: Message, location_name: "Message"))
     ServiceUnavailable.struct_class = Types::ServiceUnavailable
 
@@ -139,6 +182,20 @@ module Aws::SageMakerRuntime
         o.errors << Shapes::ShapeRef.new(shape: ServiceUnavailable)
         o.errors << Shapes::ShapeRef.new(shape: ValidationError)
       end)
+
+      api.add_operation(:invoke_endpoint_with_response_stream, Seahorse::Model::Operation.new.tap do |o|
+        o.name = "InvokeEndpointWithResponseStream"
+        o.http_method = "POST"
+        o.http_request_uri = "/endpoints/{EndpointName}/invocations-response-stream"
+        o.input = Shapes::ShapeRef.new(shape: InvokeEndpointWithResponseStreamInput)
+        o.output = Shapes::ShapeRef.new(shape: InvokeEndpointWithResponseStreamOutput)
+        o.errors << Shapes::ShapeRef.new(shape: InternalFailure)
+        o.errors << Shapes::ShapeRef.new(shape: ServiceUnavailable)
+        o.errors << Shapes::ShapeRef.new(shape: ValidationError)
+        o.errors << Shapes::ShapeRef.new(shape: ModelError)
+        o.errors << Shapes::ShapeRef.new(shape: ModelStreamError)
+        o.errors << Shapes::ShapeRef.new(shape: InternalStreamFailure)
+      end)
     end
 
   end

data/lib/aws-sdk-sagemakerruntime/endpoints.rb

@@ -40,5 +40,19 @@ module Aws::SageMakerRuntime
       end
     end
 
+    class InvokeEndpointWithResponseStream
+      def self.build(context)
+        unless context.config.regional_endpoint
+          endpoint = context.config.endpoint.to_s
+        end
+        Aws::SageMakerRuntime::EndpointParameters.new(
+          region: context.config.region,
+          use_dual_stack: context.config.use_dualstack_endpoint,
+          use_fips: context.config.use_fips_endpoint,
+          endpoint: endpoint,
+        )
+      end
+    end
+
   end
 end

data/lib/aws-sdk-sagemakerruntime/errors.rb

@@ -29,8 +29,10 @@ module Aws::SageMakerRuntime
   # ## Error Classes
   # * {InternalDependencyException}
   # * {InternalFailure}
+  # * {InternalStreamFailure}
   # * {ModelError}
   # * {ModelNotReadyException}
+  # * {ModelStreamError}
   # * {ServiceUnavailable}
   # * {ValidationError}
   #
@@ -70,6 +72,21 @@ module Aws::SageMakerRuntime
       end
     end
 
+    class InternalStreamFailure < ServiceError
+
+      # @param [Seahorse::Client::RequestContext] context
+      # @param [String] message
+      # @param [Aws::SageMakerRuntime::Types::InternalStreamFailure] data
+      def initialize(context, message, data = Aws::EmptyStructure.new)
+        super(context, message, data)
+      end
+
+      # @return [String]
+      def message
+        @message || @data[:message]
+      end
+    end
+
     class ModelError < ServiceError
 
       # @param [Seahorse::Client::RequestContext] context
@@ -115,6 +132,26 @@ module Aws::SageMakerRuntime
       end
     end
 
+    class ModelStreamError < ServiceError
+
+      # @param [Seahorse::Client::RequestContext] context
+      # @param [String] message
+      # @param [Aws::SageMakerRuntime::Types::ModelStreamError] data
+      def initialize(context, message, data = Aws::EmptyStructure.new)
+        super(context, message, data)
+      end
+
+      # @return [String]
+      def message
+        @message || @data[:message]
+      end
+
+      # @return [String]
+      def error_code
+        @data[:error_code]
+      end
+    end
+
     class ServiceUnavailable < ServiceError
 
       # @param [Seahorse::Client::RequestContext] context

data/lib/aws-sdk-sagemakerruntime/event_streams.rb

@@ -0,0 +1,59 @@
+# frozen_string_literal: true
+
+# WARNING ABOUT GENERATED CODE
+#
+# This file is generated. See the contributing guide for more information:
+# https://github.com/aws/aws-sdk-ruby/blob/version-3/CONTRIBUTING.md
+#
+# WARNING ABOUT GENERATED CODE
+
+module Aws::SageMakerRuntime
+  module EventStreams
+    class ResponseStream
+
+      def initialize
+        @event_emitter = Aws::EventEmitter.new
+      end
+
+      def on_payload_part_event(&block)
+        @event_emitter.on(:payload_part, block) if block_given?
+      end
+
+      def on_model_stream_error_event(&block)
+        @event_emitter.on(:model_stream_error, block) if block_given?
+      end
+
+      def on_internal_stream_failure_event(&block)
+        @event_emitter.on(:internal_stream_failure, block) if block_given?
+      end
+
+      def on_error_event(&block)
+        @event_emitter.on(:error, block) if block_given?
+      end
+
+      def on_initial_response_event(&block)
+        @event_emitter.on(:initial_response, block) if block_given?
+      end
+
+      def on_unknown_event(&block)
+        @event_emitter.on(:unknown_event, block) if block_given?
+      end
+
+      def on_event(&block)
+        on_payload_part_event(&block)
+        on_model_stream_error_event(&block)
+        on_internal_stream_failure_event(&block)
+        on_error_event(&block)
+        on_initial_response_event(&block)
+        on_unknown_event(&block)
+      end
+
+      # @api private
+      # @return Aws::EventEmitter
+      attr_reader :event_emitter
+
+    end
+
+  end
+end
+

data/lib/aws-sdk-sagemakerruntime/plugins/endpoints.rb

@@ -60,6 +60,8 @@ module Aws::SageMakerRuntime
             Aws::SageMakerRuntime::Endpoints::InvokeEndpoint.build(context)
           when :invoke_endpoint_async
             Aws::SageMakerRuntime::Endpoints::InvokeEndpointAsync.build(context)
+          when :invoke_endpoint_with_response_stream
+            Aws::SageMakerRuntime::Endpoints::InvokeEndpointWithResponseStream.build(context)
           end
         end
       end

data/lib/aws-sdk-sagemakerruntime/types.rb

@@ -37,13 +37,27 @@ module Aws::SageMakerRuntime
       include Aws::Structure
     end
 
+    # The stream processing failed because of an unknown error, exception or
+    # failure. Try your request again.
+    #
+    # @!attribute [rw] message
+    #   @return [String]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/runtime.sagemaker-2017-05-13/InternalStreamFailure AWS API Documentation
+    #
+    class InternalStreamFailure < Struct.new(
+      :message)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
     # @!attribute [rw] endpoint_name
     #   The name of the endpoint that you specified when you created the
-    #   endpoint using the [ `CreateEndpoint` ][1] API.
+    #   endpoint using the [CreateEndpoint][1] API.
     #
     #
     #
-    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/API_CreateEndpoint.html
     #   @return [String]
     #
     # @!attribute [rw] content_type
@@ -51,7 +65,8 @@ module Aws::SageMakerRuntime
     #   @return [String]
     #
     # @!attribute [rw] accept
-    #   The desired MIME type of the inference in the response.
+    #   The desired MIME type of the inference response from the model
+    #   container.
     #   @return [String]
     #
     # @!attribute [rw] custom_attributes
@@ -69,7 +84,7 @@ module Aws::SageMakerRuntime
     #   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.
+    #   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.
@@ -165,7 +180,8 @@ module Aws::SageMakerRuntime
     #   @return [String]
     #
     # @!attribute [rw] accept
-    #   The desired MIME type of the inference in the response.
+    #   The desired MIME type of the inference response from the model
+    #   container.
     #   @return [String]
     #
     # @!attribute [rw] custom_attributes
@@ -190,7 +206,7 @@ module Aws::SageMakerRuntime
     #
     #
     #
-    #   [1]: https://tools.ietf.org/html/rfc7230#section-3.2.6
+    #   [1]: https://datatracker.ietf.org/doc/html/rfc7230#section-3.2.6
     #   @return [String]
     #
     # @!attribute [rw] target_model
@@ -274,7 +290,7 @@ module Aws::SageMakerRuntime
     #   @return [String]
     #
     # @!attribute [rw] content_type
-    #   The MIME type of the inference returned in the response body.
+    #   The MIME type of the inference returned from the model container.
     #   @return [String]
     #
     # @!attribute [rw] invoked_production_variant
@@ -319,6 +335,153 @@ module Aws::SageMakerRuntime
       include Aws::Structure
     end
 
+    # @!attribute [rw] endpoint_name
+    #   The name of the endpoint that you specified when you created the
+    #   endpoint using the [CreateEndpoint][1] API.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/API_CreateEndpoint.html
+    #   @return [String]
+    #
+    # @!attribute [rw] 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][1].
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html
+    #   @return [String]
+    #
+    # @!attribute [rw] content_type
+    #   The MIME type of the input data in the request body.
+    #   @return [String]
+    #
+    # @!attribute [rw] accept
+    #   The desired MIME type of the inference response from the model
+    #   container.
+    #   @return [String]
+    #
+    # @!attribute [rw] custom_attributes
+    #   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][1] 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.
+    #
+    #
+    #
+    #   [1]: https://datatracker.ietf.org/doc/html/rfc7230#section-3.2.6
+    #   @return [String]
+    #
+    # @!attribute [rw] target_variant
+    #   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]
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/model-ab-testing.html
+    #   @return [String]
+    #
+    # @!attribute [rw] target_container_hostname
+    #   If the endpoint hosts multiple containers and is configured to use
+    #   direct invocation, this parameter specifies the host name of the
+    #   container to invoke.
+    #   @return [String]
+    #
+    # @!attribute [rw] inference_id
+    #   An identifier that you assign to your request.
+    #   @return [String]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/runtime.sagemaker-2017-05-13/InvokeEndpointWithResponseStreamInput AWS API Documentation
+    #
+    class InvokeEndpointWithResponseStreamInput < Struct.new(
+      :endpoint_name,
+      :body,
+      :content_type,
+      :accept,
+      :custom_attributes,
+      :target_variant,
+      :target_container_hostname,
+      :inference_id)
+      SENSITIVE = [:body, :custom_attributes]
+      include Aws::Structure
+    end
+
+    # @!attribute [rw] body
+    #   A stream of payload parts. Each part contains a portion of the
+    #   response for a streaming inference request.
+    #   @return [Types::ResponseStream]
+    #
+    # @!attribute [rw] content_type
+    #   The MIME type of the inference returned from the model container.
+    #   @return [String]
+    #
+    # @!attribute [rw] invoked_production_variant
+    #   Identifies the production variant that was invoked.
+    #   @return [String]
+    #
+    # @!attribute [rw] custom_attributes
+    #   Provides additional information in the response about the inference
+    #   returned by 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 return an ID received in the
+    #   `CustomAttributes` header of a request or other metadata that a
+    #   service endpoint was programmed to produce. The value must consist
+    #   of no more than 1024 visible US-ASCII characters as specified in
+    #   [Section 3.3.6. Field Value Components][1] of the Hypertext Transfer
+    #   Protocol (HTTP/1.1). If the customer wants the custom attribute
+    #   returned, the model must set the custom attribute to be included on
+    #   the way back.
+    #
+    #   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.
+    #
+    #
+    #
+    #   [1]: https://tools.ietf.org/html/rfc7230#section-3.2.6
+    #   @return [String]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/runtime.sagemaker-2017-05-13/InvokeEndpointWithResponseStreamOutput AWS API Documentation
+    #
+    class InvokeEndpointWithResponseStreamOutput < Struct.new(
+      :body,
+      :content_type,
+      :invoked_production_variant,
+      :custom_attributes)
+      SENSITIVE = [:custom_attributes]
+      include Aws::Structure
+    end
+
     # Model (owned by the customer in the container) returned 4xx or 5xx
     # error code.
     #
@@ -363,6 +526,63 @@ module Aws::SageMakerRuntime
       include Aws::Structure
     end
 
+    # An error occurred while streaming the response body. This error can
+    # have the following error codes:
+    #
+    # ModelInvocationTimeExceeded
+    #
+    # : The model failed to finish sending the response within the timeout
+    #   period allowed by Amazon SageMaker.
+    #
+    # StreamBroken
+    #
+    # : The Transmission Control Protocol (TCP) connection between the
+    #   client and the model was reset or closed.
+    #
+    # @!attribute [rw] message
+    #   @return [String]
+    #
+    # @!attribute [rw] error_code
+    #   This error can have the following error codes:
+    #
+    #   ModelInvocationTimeExceeded
+    #
+    #   : The model failed to finish sending the response within the timeout
+    #     period allowed by Amazon SageMaker.
+    #
+    #   StreamBroken
+    #
+    #   : The Transmission Control Protocol (TCP) connection between the
+    #     client and the model was reset or closed.
+    #   @return [String]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/runtime.sagemaker-2017-05-13/ModelStreamError AWS API Documentation
+    #
+    class ModelStreamError < Struct.new(
+      :message,
+      :error_code)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
+    # A wrapper for pieces of the payload that's returned in response to a
+    # streaming inference request. A streaming inference response consists
+    # of one or more payload parts.
+    #
+    # @!attribute [rw] bytes
+    #   A blob that contains part of the response for your streaming
+    #   inference request.
+    #   @return [String]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/runtime.sagemaker-2017-05-13/PayloadPart AWS API Documentation
+    #
+    class PayloadPart < Struct.new(
+      :bytes,
+      :event_type)
+      SENSITIVE = [:bytes]
+      include Aws::Structure
+    end
+
     # The service is unavailable. Try your call again.
     #
     # @!attribute [rw] message
@@ -389,5 +609,25 @@ module Aws::SageMakerRuntime
       include Aws::Structure
     end
 
+    # A stream of payload parts. Each part contains a portion of the
+    # response for a streaming inference request.
+    #
+    # EventStream is an Enumerator of Events.
+    #  #event_types #=> Array, returns all modeled event types in the stream
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/runtime.sagemaker-2017-05-13/ResponseStream AWS API Documentation
+    #
+    class ResponseStream < Enumerator
+
+      def event_types
+        [
+          :payload_part,
+          :model_stream_error,
+          :internal_stream_failure
+        ]
+      end
+
+    end
+
   end
 end

data/lib/aws-sdk-sagemakerruntime.rb

@@ -21,6 +21,7 @@ require_relative 'aws-sdk-sagemakerruntime/endpoint_parameters'
 require_relative 'aws-sdk-sagemakerruntime/endpoint_provider'
 require_relative 'aws-sdk-sagemakerruntime/endpoints'
 require_relative 'aws-sdk-sagemakerruntime/customizations'
+require_relative 'aws-sdk-sagemakerruntime/event_streams'
 
 # This module provides support for Amazon SageMaker Runtime. This module is available in the
 # `aws-sdk-sagemakerruntime` gem.
@@ -52,6 +53,6 @@ require_relative 'aws-sdk-sagemakerruntime/customizations'
 # @!group service
 module Aws::SageMakerRuntime
 
-  GEM_VERSION = '1.54.0'
+  GEM_VERSION = '1.56.0'
 
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: aws-sdk-sagemakerruntime
 version: !ruby/object:Gem::Version
-  version: 1.54.0
+  version: 1.56.0
 platform: ruby
 authors:
 - Amazon Web Services
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-07-11 00:00:00.000000000 Z
+date: 2023-09-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: aws-sdk-core
@@ -19,7 +19,7 @@ dependencies:
         version: '3'
     - - ">="
       - !ruby/object:Gem::Version
-        version: 3.177.0
+        version: 3.184.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -29,7 +29,7 @@ dependencies:
         version: '3'
     - - ">="
       - !ruby/object:Gem::Version
-        version: 3.177.0
+        version: 3.184.0
 - !ruby/object:Gem::Dependency
   name: aws-sigv4
   requirement: !ruby/object:Gem::Requirement
@@ -63,6 +63,7 @@ files:
 - lib/aws-sdk-sagemakerruntime/endpoint_provider.rb
 - lib/aws-sdk-sagemakerruntime/endpoints.rb
 - lib/aws-sdk-sagemakerruntime/errors.rb
+- lib/aws-sdk-sagemakerruntime/event_streams.rb
 - lib/aws-sdk-sagemakerruntime/plugins/endpoints.rb
 - lib/aws-sdk-sagemakerruntime/resource.rb
 - lib/aws-sdk-sagemakerruntime/types.rb