-- Hoogle documentation, generated by Haddock -- See Hoogle, http://www.haskell.org/hoogle/ -- | Amazon SageMaker Runtime SDK. -- -- Derived from API version 2017-05-13 of the AWS service -- descriptions, licensed under Apache 2.0. -- -- The types from this library are intended to be used with -- amazonka, which provides mechanisms for specifying AuthN/AuthZ -- information, sending requests, and receiving responses. -- -- It is recommended to use generic lenses or optics from packages such -- as generic-lens or optics to modify optional fields and -- deconstruct responses. -- -- Generated lenses can be found in Amazonka.SageMakerRuntime.Lens -- and are suitable for use with a lens package such as lens or -- lens-family-core. -- -- See Amazonka.SageMakerRuntime and the AWS documentation -- to get started. @package amazonka-sagemaker-runtime @version 2.0 module Amazonka.SageMakerRuntime.Types -- | API version 2017-05-13 of the Amazon SageMaker Runtime SDK -- configuration. defaultService :: Service -- | Your request caused an exception with an internal dependency. Contact -- customer support. _InternalDependencyException :: AsError a => Fold a ServiceError -- | An internal failure occurred. _InternalFailure :: AsError a => Fold a ServiceError -- | Model (owned by the customer in the container) returned 4xx or 5xx -- error code. _ModelError :: AsError a => Fold a ServiceError -- | Either a serverless endpoint variant's resources are still being -- provisioned, or a multi-model endpoint is still downloading or loading -- the target model. Wait and try your request again. _ModelNotReadyException :: AsError a => Fold a ServiceError -- | The service is unavailable. Try your call again. _ServiceUnavailable :: AsError a => Fold a ServiceError -- | Inspect your request and try again. _ValidationError :: AsError a => Fold a ServiceError -- | 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. -- -- 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. -- -- 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 InvokeEndpointAsync are authenticated by using -- Amazon Web Services Signature Version 4. For information, see -- Authenticating Requests (Amazon Web Services Signature Version -- 4) in the Amazon S3 API Reference. module Amazonka.SageMakerRuntime.InvokeEndpointAsync -- | See: newInvokeEndpointAsync smart constructor. data InvokeEndpointAsync InvokeEndpointAsync' :: Maybe Text -> Maybe Text -> Maybe (Sensitive Text) -> Maybe Text -> Maybe Natural -> Text -> Text -> InvokeEndpointAsync -- | The desired MIME type of the inference in the response. [$sel:accept:InvokeEndpointAsync'] :: InvokeEndpointAsync -> Maybe Text -- | The MIME type of the input data in the request body. [$sel:contentType:InvokeEndpointAsync'] :: InvokeEndpointAsync -> Maybe Text -- | 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. [$sel:customAttributes:InvokeEndpointAsync'] :: InvokeEndpointAsync -> Maybe (Sensitive Text) -- | The identifier for the inference request. Amazon SageMaker will -- generate an identifier for you if none is specified. [$sel:inferenceId:InvokeEndpointAsync'] :: InvokeEndpointAsync -> Maybe Text -- | Maximum age in seconds a request can be in the queue before it is -- marked as expired. [$sel:requestTTLSeconds:InvokeEndpointAsync'] :: InvokeEndpointAsync -> Maybe Natural -- | The name of the endpoint that you specified when you created the -- endpoint using the CreateEndpoint API. [$sel:endpointName:InvokeEndpointAsync'] :: InvokeEndpointAsync -> Text -- | The Amazon S3 URI where the inference request payload is stored. [$sel:inputLocation:InvokeEndpointAsync'] :: InvokeEndpointAsync -> Text -- | Create a value of InvokeEndpointAsync with all optional fields -- omitted. -- -- Use generic-lens or optics to modify other optional -- fields. -- -- The following record fields are available, with the corresponding -- lenses provided for backwards compatibility: -- -- $sel:accept:InvokeEndpointAsync', -- invokeEndpointAsync_accept - The desired MIME type of the -- inference in the response. -- -- $sel:contentType:InvokeEndpointAsync', -- invokeEndpointAsync_contentType - The MIME type of the input -- data in the request body. -- -- $sel:customAttributes:InvokeEndpointAsync', -- invokeEndpointAsync_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. -- -- InvokeEndpointAsync, invokeEndpointAsync_inferenceId - -- The identifier for the inference request. Amazon SageMaker will -- generate an identifier for you if none is specified. -- -- $sel:requestTTLSeconds:InvokeEndpointAsync', -- invokeEndpointAsync_requestTTLSeconds - Maximum age in seconds -- a request can be in the queue before it is marked as expired. -- -- $sel:endpointName:InvokeEndpointAsync', -- invokeEndpointAsync_endpointName - The name of the endpoint -- that you specified when you created the endpoint using the -- CreateEndpoint API. -- -- $sel:inputLocation:InvokeEndpointAsync', -- invokeEndpointAsync_inputLocation - The Amazon S3 URI where the -- inference request payload is stored. newInvokeEndpointAsync :: Text -> Text -> InvokeEndpointAsync -- | The desired MIME type of the inference in the response. invokeEndpointAsync_accept :: Lens' InvokeEndpointAsync (Maybe Text) -- | The MIME type of the input data in the request body. invokeEndpointAsync_contentType :: Lens' InvokeEndpointAsync (Maybe Text) -- | 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. invokeEndpointAsync_customAttributes :: Lens' InvokeEndpointAsync (Maybe Text) -- | The identifier for the inference request. Amazon SageMaker will -- generate an identifier for you if none is specified. invokeEndpointAsync_inferenceId :: Lens' InvokeEndpointAsync (Maybe Text) -- | Maximum age in seconds a request can be in the queue before it is -- marked as expired. invokeEndpointAsync_requestTTLSeconds :: Lens' InvokeEndpointAsync (Maybe Natural) -- | The name of the endpoint that you specified when you created the -- endpoint using the CreateEndpoint API. invokeEndpointAsync_endpointName :: Lens' InvokeEndpointAsync Text -- | The Amazon S3 URI where the inference request payload is stored. invokeEndpointAsync_inputLocation :: Lens' InvokeEndpointAsync Text -- | See: newInvokeEndpointAsyncResponse smart constructor. data InvokeEndpointAsyncResponse InvokeEndpointAsyncResponse' :: Maybe Text -> Maybe Text -> Int -> InvokeEndpointAsyncResponse -- | Identifier for an inference request. This will be the same as the -- InferenceId specified in the input. Amazon SageMaker will -- generate an identifier for you if you do not specify one. [$sel:inferenceId:InvokeEndpointAsyncResponse'] :: InvokeEndpointAsyncResponse -> Maybe Text -- | The Amazon S3 URI where the inference response payload is stored. [$sel:outputLocation:InvokeEndpointAsyncResponse'] :: InvokeEndpointAsyncResponse -> Maybe Text -- | The response's http status code. [$sel:httpStatus:InvokeEndpointAsyncResponse'] :: InvokeEndpointAsyncResponse -> Int -- | Create a value of InvokeEndpointAsyncResponse with all optional -- fields omitted. -- -- Use generic-lens or optics to modify other optional -- fields. -- -- The following record fields are available, with the corresponding -- lenses provided for backwards compatibility: -- -- InvokeEndpointAsync, -- invokeEndpointAsyncResponse_inferenceId - Identifier for an -- inference request. This will be the same as the InferenceId -- specified in the input. Amazon SageMaker will generate an identifier -- for you if you do not specify one. -- -- $sel:outputLocation:InvokeEndpointAsyncResponse', -- invokeEndpointAsyncResponse_outputLocation - The Amazon S3 URI -- where the inference response payload is stored. -- -- $sel:httpStatus:InvokeEndpointAsyncResponse', -- invokeEndpointAsyncResponse_httpStatus - The response's http -- status code. newInvokeEndpointAsyncResponse :: Int -> InvokeEndpointAsyncResponse -- | Identifier for an inference request. This will be the same as the -- InferenceId specified in the input. Amazon SageMaker will -- generate an identifier for you if you do not specify one. invokeEndpointAsyncResponse_inferenceId :: Lens' InvokeEndpointAsyncResponse (Maybe Text) -- | The Amazon S3 URI where the inference response payload is stored. invokeEndpointAsyncResponse_outputLocation :: Lens' InvokeEndpointAsyncResponse (Maybe Text) -- | The response's http status code. invokeEndpointAsyncResponse_httpStatus :: Lens' InvokeEndpointAsyncResponse Int instance GHC.Generics.Generic Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsync instance GHC.Show.Show Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsync instance GHC.Classes.Eq Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsync instance GHC.Generics.Generic Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsyncResponse instance GHC.Show.Show Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsyncResponse instance GHC.Read.Read Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsyncResponse instance GHC.Classes.Eq Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsyncResponse instance Amazonka.Types.AWSRequest Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsync instance Control.DeepSeq.NFData Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsyncResponse instance Data.Hashable.Class.Hashable Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsync instance Control.DeepSeq.NFData Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsync instance Amazonka.Data.Headers.ToHeaders Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsync instance Data.Aeson.Types.ToJSON.ToJSON Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsync instance Amazonka.Data.Path.ToPath Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsync instance Amazonka.Data.Query.ToQuery Amazonka.SageMakerRuntime.InvokeEndpointAsync.InvokeEndpointAsync -- | 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. -- -- For an overview of Amazon SageMaker, see How It Works. -- -- 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 InvokeEndpoint are authenticated by using Amazon Web -- Services Signature Version 4. For information, see Authenticating -- Requests (Amazon Web Services Signature Version 4) in the -- Amazon S3 API Reference. -- -- 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. -- -- 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. module Amazonka.SageMakerRuntime.InvokeEndpoint -- | See: newInvokeEndpoint smart constructor. data InvokeEndpoint InvokeEndpoint' :: Maybe Text -> Maybe Text -> Maybe (Sensitive Text) -> Maybe Text -> Maybe Text -> Maybe Text -> Maybe Text -> Maybe Text -> Text -> Text -> InvokeEndpoint -- | The desired MIME type of the inference in the response. [$sel:accept:InvokeEndpoint'] :: InvokeEndpoint -> Maybe Text -- | The MIME type of the input data in the request body. [$sel:contentType:InvokeEndpoint'] :: InvokeEndpoint -> Maybe Text -- | Provides additional information about a request for an inference -- submitted to a model hosted at an Amazon SageMaker endpoint. The -- information is an opaque value that is forwarded verbatim. You could -- use this value, for example, to provide an ID that you can use to -- track a request or to provide other metadata that a service endpoint -- was programmed to process. The value must consist of no more than 1024 -- visible US-ASCII characters as specified in Section 3.3.6. Field -- Value Components of the Hypertext Transfer Protocol (HTTP/1.1). -- -- The code in your model is responsible for setting or updating any -- custom attributes in the response. If your code does not set this -- value in the response, an empty value is returned. For example, if a -- custom attribute represents the trace ID, your model can prepend the -- custom attribute with Trace ID: in your post-processing -- function. -- -- This feature is currently supported in the Amazon Web Services SDKs -- but not in the Amazon SageMaker Python SDK. [$sel:customAttributes:InvokeEndpoint'] :: InvokeEndpoint -> Maybe (Sensitive Text) -- | An optional JMESPath expression used to override the -- EnableExplanations parameter of the -- ClarifyExplainerConfig API. See the EnableExplanations -- section in the developer guide for more information. [$sel:enableExplanations:InvokeEndpoint'] :: InvokeEndpoint -> Maybe Text -- | If you provide a value, it is added to the captured data when you -- enable data capture on the endpoint. For information about data -- capture, see Capture Data. [$sel:inferenceId:InvokeEndpoint'] :: InvokeEndpoint -> Maybe Text -- | If the endpoint hosts multiple containers and is configured to use -- direct invocation, this parameter specifies the host name of the -- container to invoke. [$sel:targetContainerHostname:InvokeEndpoint'] :: InvokeEndpoint -> Maybe Text -- | The model to request for inference when invoking a multi-model -- endpoint. [$sel:targetModel:InvokeEndpoint'] :: InvokeEndpoint -> Maybe Text -- | 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 [$sel:targetVariant:InvokeEndpoint'] :: InvokeEndpoint -> Maybe Text -- | The name of the endpoint that you specified when you created the -- endpoint using the CreateEndpoint API. [$sel:endpointName:InvokeEndpoint'] :: InvokeEndpoint -> Text -- | 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. [$sel:body:InvokeEndpoint'] :: InvokeEndpoint -> Text -- | Create a value of InvokeEndpoint with all optional fields -- omitted. -- -- Use generic-lens or optics to modify other optional -- fields. -- -- The following record fields are available, with the corresponding -- lenses provided for backwards compatibility: -- -- $sel:accept:InvokeEndpoint', invokeEndpoint_accept - The -- desired MIME type of the inference in the response. -- -- InvokeEndpoint, invokeEndpoint_contentType - The MIME -- type of the input data in the request body. -- -- InvokeEndpoint, invokeEndpoint_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. -- -- $sel:enableExplanations:InvokeEndpoint', -- invokeEndpoint_enableExplanations - An optional JMESPath -- expression used to override the EnableExplanations parameter -- of the ClarifyExplainerConfig API. See the -- EnableExplanations section in the developer guide for more -- information. -- -- $sel:inferenceId:InvokeEndpoint', -- invokeEndpoint_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. -- -- $sel:targetContainerHostname:InvokeEndpoint', -- invokeEndpoint_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. -- -- $sel:targetModel:InvokeEndpoint', -- invokeEndpoint_targetModel - The model to request for inference -- when invoking a multi-model endpoint. -- -- $sel:targetVariant:InvokeEndpoint', -- invokeEndpoint_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 -- -- $sel:endpointName:InvokeEndpoint', -- invokeEndpoint_endpointName - The name of the endpoint that you -- specified when you created the endpoint using the -- CreateEndpoint API. -- -- InvokeEndpoint, invokeEndpoint_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. newInvokeEndpoint :: Text -> Text -> InvokeEndpoint -- | The desired MIME type of the inference in the response. invokeEndpoint_accept :: Lens' InvokeEndpoint (Maybe Text) -- | The MIME type of the input data in the request body. invokeEndpoint_contentType :: Lens' InvokeEndpoint (Maybe Text) -- | 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. invokeEndpoint_customAttributes :: Lens' InvokeEndpoint (Maybe Text) -- | An optional JMESPath expression used to override the -- EnableExplanations parameter of the -- ClarifyExplainerConfig API. See the EnableExplanations -- section in the developer guide for more information. invokeEndpoint_enableExplanations :: Lens' InvokeEndpoint (Maybe Text) -- | 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. invokeEndpoint_inferenceId :: Lens' InvokeEndpoint (Maybe Text) -- | If the endpoint hosts multiple containers and is configured to use -- direct invocation, this parameter specifies the host name of the -- container to invoke. invokeEndpoint_targetContainerHostname :: Lens' InvokeEndpoint (Maybe Text) -- | The model to request for inference when invoking a multi-model -- endpoint. invokeEndpoint_targetModel :: Lens' InvokeEndpoint (Maybe Text) -- | 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 invokeEndpoint_targetVariant :: Lens' InvokeEndpoint (Maybe Text) -- | The name of the endpoint that you specified when you created the -- endpoint using the CreateEndpoint API. invokeEndpoint_endpointName :: Lens' InvokeEndpoint Text -- | 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. invokeEndpoint_body :: Lens' InvokeEndpoint Text -- | See: newInvokeEndpointResponse smart constructor. data InvokeEndpointResponse InvokeEndpointResponse' :: Maybe Text -> Maybe (Sensitive Text) -> Maybe Text -> Int -> Text -> InvokeEndpointResponse -- | The MIME type of the inference returned in the response body. [$sel:contentType:InvokeEndpointResponse'] :: InvokeEndpointResponse -> Maybe Text -- | 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 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. [$sel:customAttributes:InvokeEndpointResponse'] :: InvokeEndpointResponse -> Maybe (Sensitive Text) -- | Identifies the production variant that was invoked. [$sel:invokedProductionVariant:InvokeEndpointResponse'] :: InvokeEndpointResponse -> Maybe Text -- | The response's http status code. [$sel:httpStatus:InvokeEndpointResponse'] :: InvokeEndpointResponse -> Int -- | Includes the inference provided by the model. -- -- For information about the format of the response body, see Common -- Data Formats-Inference. -- -- If the explainer is activated, the body includes the explanations -- provided by the model. For more information, see the __Response -- section__ under Invoke the Endpoint in the Developer Guide. [$sel:body:InvokeEndpointResponse'] :: InvokeEndpointResponse -> Text -- | Create a value of InvokeEndpointResponse with all optional -- fields omitted. -- -- Use generic-lens or optics to modify other optional -- fields. -- -- The following record fields are available, with the corresponding -- lenses provided for backwards compatibility: -- -- InvokeEndpoint, invokeEndpointResponse_contentType - The -- MIME type of the inference returned in the response body. -- -- InvokeEndpoint, invokeEndpointResponse_customAttributes -- - 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 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. -- -- $sel:invokedProductionVariant:InvokeEndpointResponse', -- invokeEndpointResponse_invokedProductionVariant - Identifies -- the production variant that was invoked. -- -- $sel:httpStatus:InvokeEndpointResponse', -- invokeEndpointResponse_httpStatus - The response's http status -- code. -- -- InvokeEndpoint, invokeEndpointResponse_body - Includes -- the inference provided by the model. -- -- For information about the format of the response body, see Common -- Data Formats-Inference. -- -- If the explainer is activated, the body includes the explanations -- provided by the model. For more information, see the __Response -- section__ under Invoke the Endpoint in the Developer Guide. newInvokeEndpointResponse :: Int -> Text -> InvokeEndpointResponse -- | The MIME type of the inference returned in the response body. invokeEndpointResponse_contentType :: Lens' InvokeEndpointResponse (Maybe Text) -- | 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 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. invokeEndpointResponse_customAttributes :: Lens' InvokeEndpointResponse (Maybe Text) -- | Identifies the production variant that was invoked. invokeEndpointResponse_invokedProductionVariant :: Lens' InvokeEndpointResponse (Maybe Text) -- | The response's http status code. invokeEndpointResponse_httpStatus :: Lens' InvokeEndpointResponse Int -- | Includes the inference provided by the model. -- -- For information about the format of the response body, see Common -- Data Formats-Inference. -- -- If the explainer is activated, the body includes the explanations -- provided by the model. For more information, see the __Response -- section__ under Invoke the Endpoint in the Developer Guide. invokeEndpointResponse_body :: Lens' InvokeEndpointResponse Text instance GHC.Generics.Generic Amazonka.SageMakerRuntime.InvokeEndpoint.InvokeEndpoint instance GHC.Show.Show Amazonka.SageMakerRuntime.InvokeEndpoint.InvokeEndpoint instance GHC.Classes.Eq Amazonka.SageMakerRuntime.InvokeEndpoint.InvokeEndpoint instance GHC.Generics.Generic Amazonka.SageMakerRuntime.InvokeEndpoint.InvokeEndpointResponse instance GHC.Show.Show Amazonka.SageMakerRuntime.InvokeEndpoint.InvokeEndpointResponse instance GHC.Classes.Eq Amazonka.SageMakerRuntime.InvokeEndpoint.InvokeEndpointResponse instance Amazonka.Types.AWSRequest Amazonka.SageMakerRuntime.InvokeEndpoint.InvokeEndpoint instance Control.DeepSeq.NFData Amazonka.SageMakerRuntime.InvokeEndpoint.InvokeEndpointResponse instance Data.Hashable.Class.Hashable Amazonka.SageMakerRuntime.InvokeEndpoint.InvokeEndpoint instance Control.DeepSeq.NFData Amazonka.SageMakerRuntime.InvokeEndpoint.InvokeEndpoint instance Amazonka.Data.Headers.ToHeaders Amazonka.SageMakerRuntime.InvokeEndpoint.InvokeEndpoint instance Data.Aeson.Types.ToJSON.ToJSON Amazonka.SageMakerRuntime.InvokeEndpoint.InvokeEndpoint instance Amazonka.Data.Path.ToPath Amazonka.SageMakerRuntime.InvokeEndpoint.InvokeEndpoint instance Amazonka.Data.Query.ToQuery Amazonka.SageMakerRuntime.InvokeEndpoint.InvokeEndpoint module Amazonka.SageMakerRuntime.Lens -- | The desired MIME type of the inference in the response. invokeEndpoint_accept :: Lens' InvokeEndpoint (Maybe Text) -- | The MIME type of the input data in the request body. invokeEndpoint_contentType :: Lens' InvokeEndpoint (Maybe Text) -- | 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. invokeEndpoint_customAttributes :: Lens' InvokeEndpoint (Maybe Text) -- | An optional JMESPath expression used to override the -- EnableExplanations parameter of the -- ClarifyExplainerConfig API. See the EnableExplanations -- section in the developer guide for more information. invokeEndpoint_enableExplanations :: Lens' InvokeEndpoint (Maybe Text) -- | 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. invokeEndpoint_inferenceId :: Lens' InvokeEndpoint (Maybe Text) -- | If the endpoint hosts multiple containers and is configured to use -- direct invocation, this parameter specifies the host name of the -- container to invoke. invokeEndpoint_targetContainerHostname :: Lens' InvokeEndpoint (Maybe Text) -- | The model to request for inference when invoking a multi-model -- endpoint. invokeEndpoint_targetModel :: Lens' InvokeEndpoint (Maybe Text) -- | 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 invokeEndpoint_targetVariant :: Lens' InvokeEndpoint (Maybe Text) -- | The name of the endpoint that you specified when you created the -- endpoint using the CreateEndpoint API. invokeEndpoint_endpointName :: Lens' InvokeEndpoint Text -- | 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. invokeEndpoint_body :: Lens' InvokeEndpoint Text -- | The MIME type of the inference returned in the response body. invokeEndpointResponse_contentType :: Lens' InvokeEndpointResponse (Maybe Text) -- | 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 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. invokeEndpointResponse_customAttributes :: Lens' InvokeEndpointResponse (Maybe Text) -- | Identifies the production variant that was invoked. invokeEndpointResponse_invokedProductionVariant :: Lens' InvokeEndpointResponse (Maybe Text) -- | The response's http status code. invokeEndpointResponse_httpStatus :: Lens' InvokeEndpointResponse Int -- | Includes the inference provided by the model. -- -- For information about the format of the response body, see Common -- Data Formats-Inference. -- -- If the explainer is activated, the body includes the explanations -- provided by the model. For more information, see the __Response -- section__ under Invoke the Endpoint in the Developer Guide. invokeEndpointResponse_body :: Lens' InvokeEndpointResponse Text -- | The desired MIME type of the inference in the response. invokeEndpointAsync_accept :: Lens' InvokeEndpointAsync (Maybe Text) -- | The MIME type of the input data in the request body. invokeEndpointAsync_contentType :: Lens' InvokeEndpointAsync (Maybe Text) -- | 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. invokeEndpointAsync_customAttributes :: Lens' InvokeEndpointAsync (Maybe Text) -- | The identifier for the inference request. Amazon SageMaker will -- generate an identifier for you if none is specified. invokeEndpointAsync_inferenceId :: Lens' InvokeEndpointAsync (Maybe Text) -- | Maximum age in seconds a request can be in the queue before it is -- marked as expired. invokeEndpointAsync_requestTTLSeconds :: Lens' InvokeEndpointAsync (Maybe Natural) -- | The name of the endpoint that you specified when you created the -- endpoint using the CreateEndpoint API. invokeEndpointAsync_endpointName :: Lens' InvokeEndpointAsync Text -- | The Amazon S3 URI where the inference request payload is stored. invokeEndpointAsync_inputLocation :: Lens' InvokeEndpointAsync Text -- | Identifier for an inference request. This will be the same as the -- InferenceId specified in the input. Amazon SageMaker will -- generate an identifier for you if you do not specify one. invokeEndpointAsyncResponse_inferenceId :: Lens' InvokeEndpointAsyncResponse (Maybe Text) -- | The Amazon S3 URI where the inference response payload is stored. invokeEndpointAsyncResponse_outputLocation :: Lens' InvokeEndpointAsyncResponse (Maybe Text) -- | The response's http status code. invokeEndpointAsyncResponse_httpStatus :: Lens' InvokeEndpointAsyncResponse Int module Amazonka.SageMakerRuntime.Waiters -- | Derived from API version 2017-05-13 of the AWS service -- descriptions, licensed under Apache 2.0. -- -- The Amazon SageMaker runtime API. module Amazonka.SageMakerRuntime -- | API version 2017-05-13 of the Amazon SageMaker Runtime SDK -- configuration. defaultService :: Service -- | Your request caused an exception with an internal dependency. Contact -- customer support. _InternalDependencyException :: AsError a => Fold a ServiceError -- | An internal failure occurred. _InternalFailure :: AsError a => Fold a ServiceError -- | Model (owned by the customer in the container) returned 4xx or 5xx -- error code. _ModelError :: AsError a => Fold a ServiceError -- | Either a serverless endpoint variant's resources are still being -- provisioned, or a multi-model endpoint is still downloading or loading -- the target model. Wait and try your request again. _ModelNotReadyException :: AsError a => Fold a ServiceError -- | The service is unavailable. Try your call again. _ServiceUnavailable :: AsError a => Fold a ServiceError -- | Inspect your request and try again. _ValidationError :: AsError a => Fold a ServiceError -- | See: newInvokeEndpoint smart constructor. data InvokeEndpoint InvokeEndpoint' :: Maybe Text -> Maybe Text -> Maybe (Sensitive Text) -> Maybe Text -> Maybe Text -> Maybe Text -> Maybe Text -> Maybe Text -> Text -> Text -> InvokeEndpoint -- | Create a value of InvokeEndpoint with all optional fields -- omitted. -- -- Use generic-lens or optics to modify other optional -- fields. -- -- The following record fields are available, with the corresponding -- lenses provided for backwards compatibility: -- -- $sel:accept:InvokeEndpoint', invokeEndpoint_accept - The -- desired MIME type of the inference in the response. -- -- InvokeEndpoint, invokeEndpoint_contentType - The MIME -- type of the input data in the request body. -- -- InvokeEndpoint, invokeEndpoint_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. -- -- $sel:enableExplanations:InvokeEndpoint', -- invokeEndpoint_enableExplanations - An optional JMESPath -- expression used to override the EnableExplanations parameter -- of the ClarifyExplainerConfig API. See the -- EnableExplanations section in the developer guide for more -- information. -- -- $sel:inferenceId:InvokeEndpoint', -- invokeEndpoint_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. -- -- $sel:targetContainerHostname:InvokeEndpoint', -- invokeEndpoint_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. -- -- $sel:targetModel:InvokeEndpoint', -- invokeEndpoint_targetModel - The model to request for inference -- when invoking a multi-model endpoint. -- -- $sel:targetVariant:InvokeEndpoint', -- invokeEndpoint_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 -- -- $sel:endpointName:InvokeEndpoint', -- invokeEndpoint_endpointName - The name of the endpoint that you -- specified when you created the endpoint using the -- CreateEndpoint API. -- -- InvokeEndpoint, invokeEndpoint_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. newInvokeEndpoint :: Text -> Text -> InvokeEndpoint -- | See: newInvokeEndpointResponse smart constructor. data InvokeEndpointResponse InvokeEndpointResponse' :: Maybe Text -> Maybe (Sensitive Text) -> Maybe Text -> Int -> Text -> InvokeEndpointResponse -- | Create a value of InvokeEndpointResponse with all optional -- fields omitted. -- -- Use generic-lens or optics to modify other optional -- fields. -- -- The following record fields are available, with the corresponding -- lenses provided for backwards compatibility: -- -- InvokeEndpoint, invokeEndpointResponse_contentType - The -- MIME type of the inference returned in the response body. -- -- InvokeEndpoint, invokeEndpointResponse_customAttributes -- - 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 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. -- -- $sel:invokedProductionVariant:InvokeEndpointResponse', -- invokeEndpointResponse_invokedProductionVariant - Identifies -- the production variant that was invoked. -- -- $sel:httpStatus:InvokeEndpointResponse', -- invokeEndpointResponse_httpStatus - The response's http status -- code. -- -- InvokeEndpoint, invokeEndpointResponse_body - Includes -- the inference provided by the model. -- -- For information about the format of the response body, see Common -- Data Formats-Inference. -- -- If the explainer is activated, the body includes the explanations -- provided by the model. For more information, see the __Response -- section__ under Invoke the Endpoint in the Developer Guide. newInvokeEndpointResponse :: Int -> Text -> InvokeEndpointResponse -- | See: newInvokeEndpointAsync smart constructor. data InvokeEndpointAsync InvokeEndpointAsync' :: Maybe Text -> Maybe Text -> Maybe (Sensitive Text) -> Maybe Text -> Maybe Natural -> Text -> Text -> InvokeEndpointAsync -- | Create a value of InvokeEndpointAsync with all optional fields -- omitted. -- -- Use generic-lens or optics to modify other optional -- fields. -- -- The following record fields are available, with the corresponding -- lenses provided for backwards compatibility: -- -- $sel:accept:InvokeEndpointAsync', -- invokeEndpointAsync_accept - The desired MIME type of the -- inference in the response. -- -- $sel:contentType:InvokeEndpointAsync', -- invokeEndpointAsync_contentType - The MIME type of the input -- data in the request body. -- -- $sel:customAttributes:InvokeEndpointAsync', -- invokeEndpointAsync_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. -- -- InvokeEndpointAsync, invokeEndpointAsync_inferenceId - -- The identifier for the inference request. Amazon SageMaker will -- generate an identifier for you if none is specified. -- -- $sel:requestTTLSeconds:InvokeEndpointAsync', -- invokeEndpointAsync_requestTTLSeconds - Maximum age in seconds -- a request can be in the queue before it is marked as expired. -- -- $sel:endpointName:InvokeEndpointAsync', -- invokeEndpointAsync_endpointName - The name of the endpoint -- that you specified when you created the endpoint using the -- CreateEndpoint API. -- -- $sel:inputLocation:InvokeEndpointAsync', -- invokeEndpointAsync_inputLocation - The Amazon S3 URI where the -- inference request payload is stored. newInvokeEndpointAsync :: Text -> Text -> InvokeEndpointAsync -- | See: newInvokeEndpointAsyncResponse smart constructor. data InvokeEndpointAsyncResponse InvokeEndpointAsyncResponse' :: Maybe Text -> Maybe Text -> Int -> InvokeEndpointAsyncResponse -- | Create a value of InvokeEndpointAsyncResponse with all optional -- fields omitted. -- -- Use generic-lens or optics to modify other optional -- fields. -- -- The following record fields are available, with the corresponding -- lenses provided for backwards compatibility: -- -- InvokeEndpointAsync, -- invokeEndpointAsyncResponse_inferenceId - Identifier for an -- inference request. This will be the same as the InferenceId -- specified in the input. Amazon SageMaker will generate an identifier -- for you if you do not specify one. -- -- $sel:outputLocation:InvokeEndpointAsyncResponse', -- invokeEndpointAsyncResponse_outputLocation - The Amazon S3 URI -- where the inference response payload is stored. -- -- $sel:httpStatus:InvokeEndpointAsyncResponse', -- invokeEndpointAsyncResponse_httpStatus - The response's http -- status code. newInvokeEndpointAsyncResponse :: Int -> InvokeEndpointAsyncResponse