sagemakerruntime

package module
v1.19.0 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Apr 4, 2023 License: Apache-2.0 Imports: 29 Imported by: 13

Documentation

Overview

Package sagemakerruntime provides the API client, operations, and parameter types for Amazon SageMaker Runtime.

The Amazon SageMaker runtime API.

Index

Constants

View Source 
const ServiceAPIVersion = "2017-05-13"
View Source 
const ServiceID = "SageMaker Runtime"

Variables

This section is empty.

Functions

func NewDefaultEndpointResolver 

func NewDefaultEndpointResolver() *internalendpoints.Resolver

NewDefaultEndpointResolver constructs a new service endpoint resolver

func WithAPIOptions added in v1.0.0 

func WithAPIOptions(optFns ...func(*middleware.Stack) error) func(*Options)

WithAPIOptions returns a functional option for setting the Client's APIOptions option.

func WithEndpointResolver 

func WithEndpointResolver(v EndpointResolver) func(*Options)

WithEndpointResolver returns a functional option for setting the Client's EndpointResolver option.

Types

type Client 

type Client struct {
	// contains filtered or unexported fields
}

Client provides the API client to make operations call for Amazon SageMaker Runtime.

func New 

func New(options Options, optFns ...func(*Options)) *Client

New returns an initialized Client based on the functional options. Provide additional functional options to further configure the behavior of the client, such as changing the client's endpoint or adding custom middleware behavior.

func NewFromConfig 

func NewFromConfig(cfg aws.Config, optFns ...func(*Options)) *Client

NewFromConfig returns a new client from the provided config.

func (*Client) InvokeEndpoint 

func (c *Client) InvokeEndpoint(ctx context.Context, params *InvokeEndpointInput, optFns ...func(*Options)) (*InvokeEndpointOutput, error)

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 (https://docs.aws.amazon.com/sagemaker/latest/dg/how-it-works.html). 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) (https://docs.aws.amazon.com/AmazonS3/latest/API/sig-v4-authenticating-requests.html) 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.

func (*Client) InvokeEndpointAsync added in v1.5.0 

func (c *Client) InvokeEndpointAsync(ctx context.Context, params *InvokeEndpointAsyncInput, optFns ...func(*Options)) (*InvokeEndpointAsyncOutput, error)

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 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) (https://docs.aws.amazon.com/AmazonS3/latest/API/sig-v4-authenticating-requests.html) in the Amazon S3 API Reference.

type EndpointResolver 

type EndpointResolver interface {
	ResolveEndpoint(region string, options EndpointResolverOptions) (aws.Endpoint, error)
}

EndpointResolver interface for resolving service endpoints.

func EndpointResolverFromURL added in v1.1.0 

func EndpointResolverFromURL(url string, optFns ...func(*aws.Endpoint)) EndpointResolver

EndpointResolverFromURL returns an EndpointResolver configured using the provided endpoint url. By default, the resolved endpoint resolver uses the client region as signing region, and the endpoint source is set to EndpointSourceCustom.You can provide functional options to configure endpoint values for the resolved endpoint.

type EndpointResolverFunc 

type EndpointResolverFunc func(region string, options EndpointResolverOptions) (aws.Endpoint, error)

EndpointResolverFunc is a helper utility that wraps a function so it satisfies the EndpointResolver interface. This is useful when you want to add additional endpoint resolving logic, or stub out specific endpoints with custom values.

func (EndpointResolverFunc) ResolveEndpoint 

func (fn EndpointResolverFunc) ResolveEndpoint(region string, options EndpointResolverOptions) (endpoint aws.Endpoint, err error)

type EndpointResolverOptions added in v0.29.0 

type EndpointResolverOptions = internalendpoints.Options

EndpointResolverOptions is the service endpoint resolver options

type HTTPClient 

type HTTPClient interface {
	Do(*http.Request) (*http.Response, error)
}

type HTTPSignerV4 

type HTTPSignerV4 interface {
	SignHTTP(ctx context.Context, credentials aws.Credentials, r *http.Request, payloadHash string, service string, region string, signingTime time.Time, optFns ...func(*v4.SignerOptions)) error
}

type InvokeEndpointAsyncInput added in v1.5.0 

type InvokeEndpointAsyncInput struct {

	// The name of the endpoint that you specified when you created the endpoint using
	// the CreateEndpoint
	// (https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html)
	// API.
	//
	// This member is required.
	EndpointName *string

	// The Amazon S3 URI where the inference request payload is stored.
	//
	// This member is required.
	InputLocation *string

	// The desired MIME type of the inference in the response.
	Accept *string

	// The MIME type of the input data in the request body.
	ContentType *string

	// Provides additional information about a request for an inference submitted to a
	// model hosted at an Amazon SageMaker endpoint. The information is an opaque value
	// that is forwarded verbatim. You could use this value, for example, to provide an
	// ID that you can use to track a request or to provide other metadata that a
	// service endpoint was programmed to process. The value must consist of no more
	// than 1024 visible US-ASCII characters as specified in Section 3.3.6. Field Value
	// Components (https://datatracker.ietf.org/doc/html/rfc7230#section-3.2.6) 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.
	CustomAttributes *string

	// The identifier for the inference request. Amazon SageMaker will generate an
	// identifier for you if none is specified.
	InferenceId *string

	// Maximum amount of time in seconds a request can be processed before it is marked
	// as expired. The default is 15 minutes, or 900 seconds.
	InvocationTimeoutSeconds *int32

	// Maximum age in seconds a request can be in the queue before it is marked as
	// expired. The default is 6 hours, or 21,600 seconds.
	RequestTTLSeconds *int32
	// contains filtered or unexported fields
}

type InvokeEndpointAsyncOutput added in v1.5.0 

type InvokeEndpointAsyncOutput struct {

	// The Amazon S3 URI where the inference failure response payload is stored.
	FailureLocation *string

	// 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.
	InferenceId *string

	// The Amazon S3 URI where the inference response payload is stored.
	OutputLocation *string

	// Metadata pertaining to the operation's result.
	ResultMetadata middleware.Metadata
	// contains filtered or unexported fields
}

type InvokeEndpointInput 

type InvokeEndpointInput struct {

	// 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
	// (https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html).
	//
	// This member is required.
	Body []byte

	// The name of the endpoint that you specified when you created the endpoint using
	// the CreateEndpoint
	// (https://docs.aws.amazon.com/sagemaker/latest/dg/API_CreateEndpoint.html) API.
	//
	// This member is required.
	EndpointName *string

	// The desired MIME type of the inference in the response.
	Accept *string

	// The MIME type of the input data in the request body.
	ContentType *string

	// Provides additional information about a request for an inference submitted to a
	// model hosted at an Amazon SageMaker endpoint. The information is an opaque value
	// that is forwarded verbatim. You could use this value, for example, to provide an
	// ID that you can use to track a request or to provide other metadata that a
	// service endpoint was programmed to process. The value must consist of no more
	// than 1024 visible US-ASCII characters as specified in Section 3.3.6. Field Value
	// Components (https://tools.ietf.org/html/rfc7230#section-3.2.6) 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.
	CustomAttributes *string

	// An optional JMESPath expression used to override the EnableExplanations
	// parameter of the ClarifyExplainerConfig API. See the EnableExplanations
	// (https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-online-explainability-create-endpoint.html#clarify-online-explainability-create-endpoint-enable)
	// section in the developer guide for more information.
	EnableExplanations *string

	// 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
	// (https://docs.aws.amazon.com/sagemaker/latest/dg/model-monitor-data-capture.html).
	InferenceId *string

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

	// The model to request for inference when invoking a multi-model endpoint.
	TargetModel *string

	// Specify the production variant to send the inference request to when invoking an
	// endpoint that is running two or more variants. Note that this parameter
	// overrides the default behavior for the endpoint, which is to distribute the
	// invocation traffic based on the variant weights. For information about how to
	// use variant targeting to perform a/b testing, see Test models in production
	// (https://docs.aws.amazon.com/sagemaker/latest/dg/model-ab-testing.html)
	TargetVariant *string
	// contains filtered or unexported fields
}

type InvokeEndpointOutput 

type InvokeEndpointOutput struct {

	// Includes the inference provided by the model. For information about the format
	// of the response body, see Common Data Formats-Inference
	// (https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html). 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
	// (https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-online-explainability-invoke-endpoint.html#clarify-online-explainability-response)
	// in the Developer Guide.
	//
	// This member is required.
	Body []byte

	// The MIME type of the inference returned in the response body.
	ContentType *string

	// 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
	// (https://tools.ietf.org/html/rfc7230#section-3.2.6) 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.
	CustomAttributes *string

	// Identifies the production variant that was invoked.
	InvokedProductionVariant *string

	// Metadata pertaining to the operation's result.
	ResultMetadata middleware.Metadata
	// contains filtered or unexported fields
}

type Options 

type Options struct {
	// Set of options to modify how an operation is invoked. These apply to all
	// operations invoked for this client. Use functional options on operation call to
	// modify this list for per operation behavior.
	APIOptions []func(*middleware.Stack) error

	// Configures the events that will be sent to the configured logger.
	ClientLogMode aws.ClientLogMode

	// The credentials object to use when signing requests.
	Credentials aws.CredentialsProvider

	// The configuration DefaultsMode that the SDK should use when constructing the
	// clients initial default settings.
	DefaultsMode aws.DefaultsMode

	// The endpoint options to be used when attempting to resolve an endpoint.
	EndpointOptions EndpointResolverOptions

	// The service endpoint resolver.
	EndpointResolver EndpointResolver

	// Signature Version 4 (SigV4) Signer
	HTTPSignerV4 HTTPSignerV4

	// The logger writer interface to write logging messages to.
	Logger logging.Logger

	// The region to send requests to. (Required)
	Region string

	// RetryMaxAttempts specifies the maximum number attempts an API client will call
	// an operation that fails with a retryable error. A value of 0 is ignored, and
	// will not be used to configure the API client created default retryer, or modify
	// per operation call's retry max attempts. When creating a new API Clients this
	// member will only be used if the Retryer Options member is nil. This value will
	// be ignored if Retryer is not nil. If specified in an operation call's functional
	// options with a value that is different than the constructed client's Options,
	// the Client's Retryer will be wrapped to use the operation's specific
	// RetryMaxAttempts value.
	RetryMaxAttempts int

	// RetryMode specifies the retry mode the API client will be created with, if
	// Retryer option is not also specified. When creating a new API Clients this
	// member will only be used if the Retryer Options member is nil. This value will
	// be ignored if Retryer is not nil. Currently does not support per operation call
	// overrides, may in the future.
	RetryMode aws.RetryMode

	// Retryer guides how HTTP requests should be retried in case of recoverable
	// failures. When nil the API client will use a default retryer. The kind of
	// default retry created by the API client can be changed with the RetryMode
	// option.
	Retryer aws.Retryer

	// The RuntimeEnvironment configuration, only populated if the DefaultsMode is set
	// to DefaultsModeAuto and is initialized using config.LoadDefaultConfig. You
	// should not populate this structure programmatically, or rely on the values here
	// within your applications.
	RuntimeEnvironment aws.RuntimeEnvironment

	// The HTTP client to invoke API calls with. Defaults to client's default HTTP
	// implementation if nil.
	HTTPClient HTTPClient
	// contains filtered or unexported fields
}

func (Options) Copy 

func (o Options) Copy() Options

Copy creates a clone where the APIOptions list is deep copied.

type ResolveEndpoint 

type ResolveEndpoint struct {
	Resolver EndpointResolver
	Options  EndpointResolverOptions
}

func (*ResolveEndpoint) HandleSerialize 

func (m *ResolveEndpoint) HandleSerialize(ctx context.Context, in middleware.SerializeInput, next middleware.SerializeHandler) (
	out middleware.SerializeOutput, metadata middleware.Metadata, err error,
)

func (*ResolveEndpoint) ID 

func (*ResolveEndpoint) ID() string

Source Files

View all Source files

Directories

Path Synopsis
internal
endpoints

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.