Struct aws_sdk_sagemakerruntime::input::invoke_endpoint_input::Builder

pub struct Builder { /* private fields */ }

A builder for InvokeEndpointInput.

Implementations

impl Builder

pub fn endpoint_name(self, input: impl Into<String>) -> Self

The name of the endpoint that you specified when you created the endpoint using the CreateEndpoint API.

Examples found in repository

src/client.rs (line 211)

        pub fn endpoint_name(mut self, input: impl Into<std::string::String>) -> Self {
            self.inner = self.inner.endpoint_name(input.into());
            self
        }

pub fn set_endpoint_name(self, input: Option<String>) -> Self

The name of the endpoint that you specified when you created the endpoint using the CreateEndpoint API.

Examples found in repository

src/client.rs (line 219)

        pub fn set_endpoint_name(
            mut self,
            input: std::option::Option<std::string::String>,
        ) -> Self {
            self.inner = self.inner.set_endpoint_name(input);
            self
        }

pub fn body(self, input: Blob) -> Self

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.

Examples found in repository

src/client.rs (line 225)

        pub fn body(mut self, input: aws_smithy_types::Blob) -> Self {
            self.inner = self.inner.body(input);
            self
        }

pub fn set_body(self, input: Option<Blob>) -> Self

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.

Examples found in repository

src/client.rs (line 231)

        pub fn set_body(mut self, input: std::option::Option<aws_smithy_types::Blob>) -> Self {
            self.inner = self.inner.set_body(input);
            self
        }

pub fn content_type(self, input: impl Into<String>) -> Self

The MIME type of the input data in the request body.

Examples found in repository

src/client.rs (line 236)

        pub fn content_type(mut self, input: impl Into<std::string::String>) -> Self {
            self.inner = self.inner.content_type(input.into());
            self
        }

pub fn set_content_type(self, input: Option<String>) -> Self

The MIME type of the input data in the request body.

Examples found in repository

src/client.rs (line 241)

        pub fn set_content_type(mut self, input: std::option::Option<std::string::String>) -> Self {
            self.inner = self.inner.set_content_type(input);
            self
        }

pub fn accept(self, input: impl Into<String>) -> Self

The desired MIME type of the inference in the response.

Examples found in repository

src/client.rs (line 246)

        pub fn accept(mut self, input: impl Into<std::string::String>) -> Self {
            self.inner = self.inner.accept(input.into());
            self
        }

pub fn set_accept(self, input: Option<String>) -> Self

The desired MIME type of the inference in the response.

Examples found in repository

src/client.rs (line 251)

        pub fn set_accept(mut self, input: std::option::Option<std::string::String>) -> Self {
            self.inner = self.inner.set_accept(input);
            self
        }

pub fn custom_attributes(self, input: impl Into<String>) -> Self

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.

Examples found in repository

src/client.rs (line 258)

        pub fn custom_attributes(mut self, input: impl Into<std::string::String>) -> Self {
            self.inner = self.inner.custom_attributes(input.into());
            self
        }

pub fn set_custom_attributes(self, input: Option<String>) -> Self

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.

Examples found in repository

src/client.rs (line 268)

        pub fn set_custom_attributes(
            mut self,
            input: std::option::Option<std::string::String>,
        ) -> Self {
            self.inner = self.inner.set_custom_attributes(input);
            self
        }

pub fn target_model(self, input: impl Into<String>) -> Self

The model to request for inference when invoking a multi-model endpoint.

Examples found in repository

src/client.rs (line 273)

        pub fn target_model(mut self, input: impl Into<std::string::String>) -> Self {
            self.inner = self.inner.target_model(input.into());
            self
        }

pub fn set_target_model(self, input: Option<String>) -> Self

The model to request for inference when invoking a multi-model endpoint.

Examples found in repository

src/client.rs (line 278)

        pub fn set_target_model(mut self, input: std::option::Option<std::string::String>) -> Self {
            self.inner = self.inner.set_target_model(input);
            self
        }

pub fn target_variant(self, input: impl Into<String>) -> Self

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

Examples found in repository

src/client.rs (line 284)

        pub fn target_variant(mut self, input: impl Into<std::string::String>) -> Self {
            self.inner = self.inner.target_variant(input.into());
            self
        }

pub fn set_target_variant(self, input: Option<String>) -> Self

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

Examples found in repository

src/client.rs (line 293)

        pub fn set_target_variant(
            mut self,
            input: std::option::Option<std::string::String>,
        ) -> Self {
            self.inner = self.inner.set_target_variant(input);
            self
        }

pub fn target_container_hostname(self, input: impl Into<String>) -> Self

If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.

Examples found in repository

src/client.rs (line 298)

        pub fn target_container_hostname(mut self, input: impl Into<std::string::String>) -> Self {
            self.inner = self.inner.target_container_hostname(input.into());
            self
        }

pub fn set_target_container_hostname(self, input: Option<String>) -> Self

If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.

Examples found in repository

src/client.rs (line 306)

        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
        }

pub fn inference_id(self, input: impl Into<String>) -> Self

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.

Examples found in repository

src/client.rs (line 311)

        pub fn inference_id(mut self, input: impl Into<std::string::String>) -> Self {
            self.inner = self.inner.inference_id(input.into());
            self
        }

pub fn set_inference_id(self, input: Option<String>) -> Self

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.

Examples found in repository

src/client.rs (line 316)

        pub fn set_inference_id(mut self, input: std::option::Option<std::string::String>) -> Self {
            self.inner = self.inner.set_inference_id(input);
            self
        }

pub fn enable_explanations(self, input: impl Into<String>) -> Self

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.

Examples found in repository

src/client.rs (line 321)

        pub fn enable_explanations(mut self, input: impl Into<std::string::String>) -> Self {
            self.inner = self.inner.enable_explanations(input.into());
            self
        }

pub fn set_enable_explanations(self, input: Option<String>) -> Self

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.

Examples found in repository

src/client.rs (line 329)

        pub fn set_enable_explanations(
            mut self,
            input: std::option::Option<std::string::String>,
        ) -> Self {
            self.inner = self.inner.set_enable_explanations(input);
            self
        }

pub fn build(self) -> Result<InvokeEndpointInput, BuildError>

Consumes the builder and constructs a InvokeEndpointInput.

Examples found in repository

src/client.rs (line 178)

        pub async fn customize(
            self,
        ) -> std::result::Result<
            crate::operation::customize::CustomizableOperation<
                crate::operation::InvokeEndpoint,
                aws_http::retry::AwsResponseRetryClassifier,
            >,
            aws_smithy_http::result::SdkError<crate::error::InvokeEndpointError>,
        > {
            let handle = self.handle.clone();
            let operation = self
                .inner
                .build()
                .map_err(aws_smithy_http::result::SdkError::construction_failure)?
                .make_operation(&handle.conf)
                .await
                .map_err(aws_smithy_http::result::SdkError::construction_failure)?;
            Ok(crate::operation::customize::CustomizableOperation { handle, operation })
        }

        /// 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::output::InvokeEndpointOutput,
            aws_smithy_http::result::SdkError<crate::error::InvokeEndpointError>,
        > {
            let op = self
                .inner
                .build()
                .map_err(aws_smithy_http::result::SdkError::construction_failure)?
                .make_operation(&self.handle.conf)
                .await
                .map_err(aws_smithy_http::result::SdkError::construction_failure)?;
            self.handle.client.call(op).await
        }

Trait Implementations

impl Clone for Builder

fn clone(&self) -> Builder

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Builder

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for Builder

fn default() -> Builder

Returns the “default value” for a type.

impl PartialEq<Builder> for Builder

fn eq(&self, other: &Builder) -> bool

This method tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

This method tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for Builder