aws_sdk_sagemakerruntime/operation/invoke_endpoint_with_response_stream/

builders.rs

// Code generated by software.amazon.smithy.rust.codegen.smithy-rs. DO NOT EDIT.
pub use crate::operation::invoke_endpoint_with_response_stream::_invoke_endpoint_with_response_stream_output::InvokeEndpointWithResponseStreamOutputBuilder;

pub use crate::operation::invoke_endpoint_with_response_stream::_invoke_endpoint_with_response_stream_input::InvokeEndpointWithResponseStreamInputBuilder;

impl crate::operation::invoke_endpoint_with_response_stream::builders::InvokeEndpointWithResponseStreamInputBuilder {
    /// Sends a request with this input using the given client.
    pub async fn send_with(
        self,
        client: &crate::Client,
    ) -> ::std::result::Result<
        crate::operation::invoke_endpoint_with_response_stream::InvokeEndpointWithResponseStreamOutput,
        ::aws_smithy_runtime_api::client::result::SdkError<
            crate::operation::invoke_endpoint_with_response_stream::InvokeEndpointWithResponseStreamError,
            ::aws_smithy_runtime_api::client::orchestrator::HttpResponse,
        >,
    > {
        let mut fluent_builder = client.invoke_endpoint_with_response_stream();
        fluent_builder.inner = self;
        fluent_builder.send().await
    }
}
/// Fluent builder constructing a request to `InvokeEndpointWithResponseStream`.
///
/// <p>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 AI hosting services, and the container for that model must support inference streaming.</p>
/// <p>For more information that can help you use this API, see the following sections in the <i>Amazon SageMaker AI Developer Guide</i>:</p>
/// <ul>
/// <li>
/// <p>For information about how to add streaming support to a model, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-inference-code.html#your-algorithms-inference-code-how-containe-serves-requests">How Containers Serve Requests</a>.</p></li>
/// <li>
/// <p>For information about how to process the streaming response, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/realtime-endpoints-test-endpoints.html">Invoke real-time endpoints</a>.</p></li>
/// </ul>
/// <p>Before you can use this operation, your IAM permissions must allow the <code>sagemaker:InvokeEndpoint</code> action. For more information about Amazon SageMaker AI actions for IAM policies, see <a href="https://docs.aws.amazon.com/service-authorization/latest/reference/list_amazonsagemaker.html">Actions, resources, and condition keys for Amazon SageMaker AI</a> in the <i>IAM Service Authorization Reference</i>.</p>
/// <p>Amazon SageMaker AI strips all POST headers except those supported by the API. Amazon SageMaker AI might add additional headers. You should not rely on the behavior of headers outside those enumerated in the request syntax.</p>
/// <p>Calls to <code>InvokeEndpointWithResponseStream</code> are authenticated by using Amazon Web Services Signature Version 4. For information, see <a href="https://docs.aws.amazon.com/AmazonS3/latest/API/sig-v4-authenticating-requests.html">Authenticating Requests (Amazon Web Services Signature Version 4)</a> in the <i>Amazon S3 API Reference</i>.</p>
#[derive(::std::clone::Clone, ::std::fmt::Debug)]
pub struct InvokeEndpointWithResponseStreamFluentBuilder {
    handle: ::std::sync::Arc<crate::client::Handle>,
    inner: crate::operation::invoke_endpoint_with_response_stream::builders::InvokeEndpointWithResponseStreamInputBuilder,
    config_override: ::std::option::Option<crate::config::Builder>,
}
impl
    crate::client::customize::internal::CustomizableSend<
        crate::operation::invoke_endpoint_with_response_stream::InvokeEndpointWithResponseStreamOutput,
        crate::operation::invoke_endpoint_with_response_stream::InvokeEndpointWithResponseStreamError,
    > for InvokeEndpointWithResponseStreamFluentBuilder
{
    fn send(
        self,
        config_override: crate::config::Builder,
    ) -> crate::client::customize::internal::BoxFuture<
        crate::client::customize::internal::SendResult<
            crate::operation::invoke_endpoint_with_response_stream::InvokeEndpointWithResponseStreamOutput,
            crate::operation::invoke_endpoint_with_response_stream::InvokeEndpointWithResponseStreamError,
        >,
    > {
        ::std::boxed::Box::pin(async move { self.config_override(config_override).send().await })
    }
}
impl InvokeEndpointWithResponseStreamFluentBuilder {
    /// Creates a new `InvokeEndpointWithResponseStreamFluentBuilder`.
    pub(crate) fn new(handle: ::std::sync::Arc<crate::client::Handle>) -> Self {
        Self {
            handle,
            inner: ::std::default::Default::default(),
            config_override: ::std::option::Option::None,
        }
    }
    /// Access the InvokeEndpointWithResponseStream as a reference.
    pub fn as_input(&self) -> &crate::operation::invoke_endpoint_with_response_stream::builders::InvokeEndpointWithResponseStreamInputBuilder {
        &self.inner
    }
    /// Sends the request and returns the response.
    ///
    /// If an error occurs, an `SdkError` will be returned with additional details that
    /// can be matched against.
    ///
    /// By default, any retryable failures will be retried twice. Retry behavior
    /// is configurable with the [RetryConfig](aws_smithy_types::retry::RetryConfig), which can be
    /// set when configuring the client.
    pub async fn send(
        self,
    ) -> ::std::result::Result<
        crate::operation::invoke_endpoint_with_response_stream::InvokeEndpointWithResponseStreamOutput,
        ::aws_smithy_runtime_api::client::result::SdkError<
            crate::operation::invoke_endpoint_with_response_stream::InvokeEndpointWithResponseStreamError,
            ::aws_smithy_runtime_api::client::orchestrator::HttpResponse,
        >,
    > {
        let input = self
            .inner
            .build()
            .map_err(::aws_smithy_runtime_api::client::result::SdkError::construction_failure)?;
        let runtime_plugins = crate::operation::invoke_endpoint_with_response_stream::InvokeEndpointWithResponseStream::operation_runtime_plugins(
            self.handle.runtime_plugins.clone(),
            &self.handle.conf,
            self.config_override,
        );
        let mut output =
            crate::operation::invoke_endpoint_with_response_stream::InvokeEndpointWithResponseStream::orchestrate(&runtime_plugins, input).await?;

        // Converts any error encountered beyond this point into an `SdkError` response error
        // with an `HttpResponse`. However, since we have already exited the `orchestrate`
        // function, the original `HttpResponse` is no longer available and cannot be restored.
        // This means that header information from the original response has been lost.
        //
        // Note that the response body would have been consumed by the deserializer
        // regardless, even if the initial message was hypothetically processed during
        // the orchestrator's deserialization phase but later resulted in an error.
        fn response_error(
            err: impl ::std::convert::Into<::aws_smithy_runtime_api::box_error::BoxError>,
        ) -> ::aws_smithy_runtime_api::client::result::SdkError<
            crate::operation::invoke_endpoint_with_response_stream::InvokeEndpointWithResponseStreamError,
            ::aws_smithy_runtime_api::client::orchestrator::HttpResponse,
        > {
            ::aws_smithy_runtime_api::client::result::SdkError::response_error(
                err,
                ::aws_smithy_runtime_api::client::orchestrator::HttpResponse::new(
                    ::aws_smithy_runtime_api::http::StatusCode::try_from(200).expect("valid successful code"),
                    ::aws_smithy_types::body::SdkBody::empty(),
                ),
            )
        }

        let message = output.body.try_recv_initial_response().await.map_err(response_error)?;

        match message {
            ::std::option::Option::Some(_message) => ::std::result::Result::Ok(output),
            ::std::option::Option::None => ::std::result::Result::Ok(output),
        }
    }

    /// Consumes this builder, creating a customizable operation that can be modified before being sent.
    pub fn customize(
        self,
    ) -> crate::client::customize::CustomizableOperation<
        crate::operation::invoke_endpoint_with_response_stream::InvokeEndpointWithResponseStreamOutput,
        crate::operation::invoke_endpoint_with_response_stream::InvokeEndpointWithResponseStreamError,
        Self,
    > {
        crate::client::customize::CustomizableOperation::new(self)
    }
    pub(crate) fn config_override(mut self, config_override: impl ::std::convert::Into<crate::config::Builder>) -> Self {
        self.set_config_override(::std::option::Option::Some(config_override.into()));
        self
    }

    pub(crate) fn set_config_override(&mut self, config_override: ::std::option::Option<crate::config::Builder>) -> &mut Self {
        self.config_override = config_override;
        self
    }
    /// <p>The name of the endpoint that you specified when you created the endpoint using the <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/API_CreateEndpoint.html">CreateEndpoint</a> API.</p>
    pub fn endpoint_name(mut self, input: impl ::std::convert::Into<::std::string::String>) -> Self {
        self.inner = self.inner.endpoint_name(input.into());
        self
    }
    /// <p>The name of the endpoint that you specified when you created the endpoint using the <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/API_CreateEndpoint.html">CreateEndpoint</a> API.</p>
    pub fn set_endpoint_name(mut self, input: ::std::option::Option<::std::string::String>) -> Self {
        self.inner = self.inner.set_endpoint_name(input);
        self
    }
    /// <p>The name of the endpoint that you specified when you created the endpoint using the <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/API_CreateEndpoint.html">CreateEndpoint</a> API.</p>
    pub fn get_endpoint_name(&self) -> &::std::option::Option<::std::string::String> {
        self.inner.get_endpoint_name()
    }
    /// <p>Provides input data, in the format specified in the <code>ContentType</code> request header. Amazon SageMaker AI passes all of the data in the body to the model.</p>
    /// <p>For information about the format of the request body, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html">Common Data Formats-Inference</a>.</p>
    pub fn body(mut self, input: ::aws_smithy_types::Blob) -> Self {
        self.inner = self.inner.body(input);
        self
    }
    /// <p>Provides input data, in the format specified in the <code>ContentType</code> request header. Amazon SageMaker AI passes all of the data in the body to the model.</p>
    /// <p>For information about the format of the request body, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html">Common Data Formats-Inference</a>.</p>
    pub fn set_body(mut self, input: ::std::option::Option<::aws_smithy_types::Blob>) -> Self {
        self.inner = self.inner.set_body(input);
        self
    }
    /// <p>Provides input data, in the format specified in the <code>ContentType</code> request header. Amazon SageMaker AI passes all of the data in the body to the model.</p>
    /// <p>For information about the format of the request body, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html">Common Data Formats-Inference</a>.</p>
    pub fn get_body(&self) -> &::std::option::Option<::aws_smithy_types::Blob> {
        self.inner.get_body()
    }
    /// <p>The MIME type of the input data in the request body.</p>
    pub fn content_type(mut self, input: impl ::std::convert::Into<::std::string::String>) -> Self {
        self.inner = self.inner.content_type(input.into());
        self
    }
    /// <p>The MIME type of the input data in the request body.</p>
    pub fn set_content_type(mut self, input: ::std::option::Option<::std::string::String>) -> Self {
        self.inner = self.inner.set_content_type(input);
        self
    }
    /// <p>The MIME type of the input data in the request body.</p>
    pub fn get_content_type(&self) -> &::std::option::Option<::std::string::String> {
        self.inner.get_content_type()
    }
    /// <p>The desired MIME type of the inference response from the model container.</p>
    pub fn accept(mut self, input: impl ::std::convert::Into<::std::string::String>) -> Self {
        self.inner = self.inner.accept(input.into());
        self
    }
    /// <p>The desired MIME type of the inference response from the model container.</p>
    pub fn set_accept(mut self, input: ::std::option::Option<::std::string::String>) -> Self {
        self.inner = self.inner.set_accept(input);
        self
    }
    /// <p>The desired MIME type of the inference response from the model container.</p>
    pub fn get_accept(&self) -> &::std::option::Option<::std::string::String> {
        self.inner.get_accept()
    }
    /// <p>Provides additional information about a request for an inference submitted to a model hosted at an Amazon SageMaker AI endpoint. The information is an opaque value that is forwarded verbatim. You could use this value, for example, to provide an ID that you can use to track a request or to provide other metadata that a service endpoint was programmed to process. The value must consist of no more than 1024 visible US-ASCII characters as specified in <a href="https://datatracker.ietf.org/doc/html/rfc7230#section-3.2.6">Section 3.3.6. Field Value Components</a> of the Hypertext Transfer Protocol (HTTP/1.1).</p>
    /// <p>The code in your model is responsible for setting or updating any custom attributes in the response. If your code does not set this value in the response, an empty value is returned. For example, if a custom attribute represents the trace ID, your model can prepend the custom attribute with <code>Trace ID:</code> in your post-processing function.</p>
    /// <p>This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker AI Python SDK.</p>
    pub fn custom_attributes(mut self, input: impl ::std::convert::Into<::std::string::String>) -> Self {
        self.inner = self.inner.custom_attributes(input.into());
        self
    }
    /// <p>Provides additional information about a request for an inference submitted to a model hosted at an Amazon SageMaker AI endpoint. The information is an opaque value that is forwarded verbatim. You could use this value, for example, to provide an ID that you can use to track a request or to provide other metadata that a service endpoint was programmed to process. The value must consist of no more than 1024 visible US-ASCII characters as specified in <a href="https://datatracker.ietf.org/doc/html/rfc7230#section-3.2.6">Section 3.3.6. Field Value Components</a> of the Hypertext Transfer Protocol (HTTP/1.1).</p>
    /// <p>The code in your model is responsible for setting or updating any custom attributes in the response. If your code does not set this value in the response, an empty value is returned. For example, if a custom attribute represents the trace ID, your model can prepend the custom attribute with <code>Trace ID:</code> in your post-processing function.</p>
    /// <p>This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker AI Python SDK.</p>
    pub fn set_custom_attributes(mut self, input: ::std::option::Option<::std::string::String>) -> Self {
        self.inner = self.inner.set_custom_attributes(input);
        self
    }
    /// <p>Provides additional information about a request for an inference submitted to a model hosted at an Amazon SageMaker AI endpoint. The information is an opaque value that is forwarded verbatim. You could use this value, for example, to provide an ID that you can use to track a request or to provide other metadata that a service endpoint was programmed to process. The value must consist of no more than 1024 visible US-ASCII characters as specified in <a href="https://datatracker.ietf.org/doc/html/rfc7230#section-3.2.6">Section 3.3.6. Field Value Components</a> of the Hypertext Transfer Protocol (HTTP/1.1).</p>
    /// <p>The code in your model is responsible for setting or updating any custom attributes in the response. If your code does not set this value in the response, an empty value is returned. For example, if a custom attribute represents the trace ID, your model can prepend the custom attribute with <code>Trace ID:</code> in your post-processing function.</p>
    /// <p>This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker AI Python SDK.</p>
    pub fn get_custom_attributes(&self) -> &::std::option::Option<::std::string::String> {
        self.inner.get_custom_attributes()
    }
    /// <p>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.</p>
    /// <p>For information about how to use variant targeting to perform a/b testing, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/model-ab-testing.html">Test models in production</a></p>
    pub fn target_variant(mut self, input: impl ::std::convert::Into<::std::string::String>) -> Self {
        self.inner = self.inner.target_variant(input.into());
        self
    }
    /// <p>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.</p>
    /// <p>For information about how to use variant targeting to perform a/b testing, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/model-ab-testing.html">Test models in production</a></p>
    pub fn set_target_variant(mut self, input: ::std::option::Option<::std::string::String>) -> Self {
        self.inner = self.inner.set_target_variant(input);
        self
    }
    /// <p>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.</p>
    /// <p>For information about how to use variant targeting to perform a/b testing, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/model-ab-testing.html">Test models in production</a></p>
    pub fn get_target_variant(&self) -> &::std::option::Option<::std::string::String> {
        self.inner.get_target_variant()
    }
    /// <p>If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.</p>
    pub fn target_container_hostname(mut self, input: impl ::std::convert::Into<::std::string::String>) -> Self {
        self.inner = self.inner.target_container_hostname(input.into());
        self
    }
    /// <p>If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.</p>
    pub fn set_target_container_hostname(mut self, input: ::std::option::Option<::std::string::String>) -> Self {
        self.inner = self.inner.set_target_container_hostname(input);
        self
    }
    /// <p>If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.</p>
    pub fn get_target_container_hostname(&self) -> &::std::option::Option<::std::string::String> {
        self.inner.get_target_container_hostname()
    }
    /// <p>An identifier that you assign to your request.</p>
    pub fn inference_id(mut self, input: impl ::std::convert::Into<::std::string::String>) -> Self {
        self.inner = self.inner.inference_id(input.into());
        self
    }
    /// <p>An identifier that you assign to your request.</p>
    pub fn set_inference_id(mut self, input: ::std::option::Option<::std::string::String>) -> Self {
        self.inner = self.inner.set_inference_id(input);
        self
    }
    /// <p>An identifier that you assign to your request.</p>
    pub fn get_inference_id(&self) -> &::std::option::Option<::std::string::String> {
        self.inner.get_inference_id()
    }
    /// <p>If the endpoint hosts one or more inference components, this parameter specifies the name of inference component to invoke for a streaming response.</p>
    pub fn inference_component_name(mut self, input: impl ::std::convert::Into<::std::string::String>) -> Self {
        self.inner = self.inner.inference_component_name(input.into());
        self
    }
    /// <p>If the endpoint hosts one or more inference components, this parameter specifies the name of inference component to invoke for a streaming response.</p>
    pub fn set_inference_component_name(mut self, input: ::std::option::Option<::std::string::String>) -> Self {
        self.inner = self.inner.set_inference_component_name(input);
        self
    }
    /// <p>If the endpoint hosts one or more inference components, this parameter specifies the name of inference component to invoke for a streaming response.</p>
    pub fn get_inference_component_name(&self) -> &::std::option::Option<::std::string::String> {
        self.inner.get_inference_component_name()
    }
    /// <p>The ID of a stateful session to handle your request.</p>
    /// <p>You can't create a stateful session by using the <code>InvokeEndpointWithResponseStream</code> action. Instead, you can create one by using the <code> <code>InvokeEndpoint</code> </code> action. In your request, you specify <code>NEW_SESSION</code> for the <code>SessionId</code> request parameter. The response to that request provides the session ID for the <code>NewSessionId</code> response parameter.</p>
    pub fn session_id(mut self, input: impl ::std::convert::Into<::std::string::String>) -> Self {
        self.inner = self.inner.session_id(input.into());
        self
    }
    /// <p>The ID of a stateful session to handle your request.</p>
    /// <p>You can't create a stateful session by using the <code>InvokeEndpointWithResponseStream</code> action. Instead, you can create one by using the <code> <code>InvokeEndpoint</code> </code> action. In your request, you specify <code>NEW_SESSION</code> for the <code>SessionId</code> request parameter. The response to that request provides the session ID for the <code>NewSessionId</code> response parameter.</p>
    pub fn set_session_id(mut self, input: ::std::option::Option<::std::string::String>) -> Self {
        self.inner = self.inner.set_session_id(input);
        self
    }
    /// <p>The ID of a stateful session to handle your request.</p>
    /// <p>You can't create a stateful session by using the <code>InvokeEndpointWithResponseStream</code> action. Instead, you can create one by using the <code> <code>InvokeEndpoint</code> </code> action. In your request, you specify <code>NEW_SESSION</code> for the <code>SessionId</code> request parameter. The response to that request provides the session ID for the <code>NewSessionId</code> response parameter.</p>
    pub fn get_session_id(&self) -> &::std::option::Option<::std::string::String> {
        self.inner.get_session_id()
    }
}