class Aws::SageMakerRuntime::Client

An API client for SageMakerRuntime. To construct a client, you need to configure a `:region` and `:credentials`.

client = Aws::SageMakerRuntime::Client.new(
  region: region_name,
  credentials: credentials,
  # ...
)

For details on configuring region and credentials see the [developer guide](/sdk-for-ruby/v3/developer-guide/setup-config.html).

See {#initialize} for a full list of supported configuration options.

Attributes

identifier[R]

@api private

Public Class Methods

errors_module() click to toggle source

@api private

# File lib/aws-sdk-sagemakerruntime/client.rb, line 612
def errors_module
  Errors
end
new(*args) click to toggle source

@overload initialize(options)

@param [Hash] options
@option options [required, Aws::CredentialProvider] :credentials
  Your AWS credentials. This can be an instance of any one of the
  following classes:

  * `Aws::Credentials` - Used for configuring static, non-refreshing
    credentials.

  * `Aws::SharedCredentials` - Used for loading static credentials from a
    shared file, such as `~/.aws/config`.

  * `Aws::AssumeRoleCredentials` - Used when you need to assume a role.

  * `Aws::AssumeRoleWebIdentityCredentials` - Used when you need to
    assume a role after providing credentials via the web.

  * `Aws::SSOCredentials` - Used for loading credentials from AWS SSO using an
    access token generated from `aws login`.

  * `Aws::ProcessCredentials` - Used for loading credentials from a
    process that outputs to stdout.

  * `Aws::InstanceProfileCredentials` - Used for loading credentials
    from an EC2 IMDS on an EC2 instance.

  * `Aws::ECSCredentials` - Used for loading credentials from
    instances running in ECS.

  * `Aws::CognitoIdentityCredentials` - Used for loading credentials
    from the Cognito Identity service.

  When `:credentials` are not configured directly, the following
  locations will be searched for credentials:

  * `Aws.config[:credentials]`
  * The `:access_key_id`, `:secret_access_key`, and `:session_token` options.
  * ENV['AWS_ACCESS_KEY_ID'], ENV['AWS_SECRET_ACCESS_KEY']
  * `~/.aws/credentials`
  * `~/.aws/config`
  * EC2/ECS IMDS instance profile - When used by default, the timeouts
    are very aggressive. Construct and pass an instance of
    `Aws::InstanceProfileCredentails` or `Aws::ECSCredentials` to
    enable retries and extended timeouts.

@option options [required, String] :region
  The AWS region to connect to.  The configured `:region` is
  used to determine the service `:endpoint`. When not passed,
  a default `:region` is searched for in the following locations:

  * `Aws.config[:region]`
  * `ENV['AWS_REGION']`
  * `ENV['AMAZON_REGION']`
  * `ENV['AWS_DEFAULT_REGION']`
  * `~/.aws/credentials`
  * `~/.aws/config`

@option options [String] :access_key_id

@option options [Boolean] :active_endpoint_cache (false)
  When set to `true`, a thread polling for endpoints will be running in
  the background every 60 secs (default). Defaults to `false`.

@option options [Boolean] :adaptive_retry_wait_to_fill (true)
  Used only in `adaptive` retry mode.  When true, the request will sleep
  until there is sufficent client side capacity to retry the request.
  When false, the request will raise a `RetryCapacityNotAvailableError` and will
  not retry instead of sleeping.

@option options [Boolean] :client_side_monitoring (false)
  When `true`, client-side metrics will be collected for all API requests from
  this client.

@option options [String] :client_side_monitoring_client_id ("")
  Allows you to provide an identifier for this client which will be attached to
  all generated client side metrics. Defaults to an empty string.

@option options [String] :client_side_monitoring_host ("127.0.0.1")
  Allows you to specify the DNS hostname or IPv4 or IPv6 address that the client
  side monitoring agent is running on, where client metrics will be published via UDP.

@option options [Integer] :client_side_monitoring_port (31000)
  Required for publishing client metrics. The port that the client side monitoring
  agent is running on, where client metrics will be published via UDP.

@option options [Aws::ClientSideMonitoring::Publisher] :client_side_monitoring_publisher (Aws::ClientSideMonitoring::Publisher)
  Allows you to provide a custom client-side monitoring publisher class. By default,
  will use the Client Side Monitoring Agent Publisher.

@option options [Boolean] :convert_params (true)
  When `true`, an attempt is made to coerce request parameters into
  the required types.

@option options [Boolean] :correct_clock_skew (true)
  Used only in `standard` and adaptive retry modes. Specifies whether to apply
  a clock skew correction and retry requests with skewed client clocks.

@option options [Boolean] :disable_host_prefix_injection (false)
  Set to true to disable SDK automatically adding host prefix
  to default service endpoint when available.

@option options [String] :endpoint
  The client endpoint is normally constructed from the `:region`
  option. You should only configure an `:endpoint` when connecting
  to test or custom endpoints. This should be a valid HTTP(S) URI.

@option options [Integer] :endpoint_cache_max_entries (1000)
  Used for the maximum size limit of the LRU cache storing endpoints data
  for endpoint discovery enabled operations. Defaults to 1000.

@option options [Integer] :endpoint_cache_max_threads (10)
  Used for the maximum threads in use for polling endpoints to be cached, defaults to 10.

@option options [Integer] :endpoint_cache_poll_interval (60)
  When :endpoint_discovery and :active_endpoint_cache is enabled,
  Use this option to config the time interval in seconds for making
  requests fetching endpoints information. Defaults to 60 sec.

@option options [Boolean] :endpoint_discovery (false)
  When set to `true`, endpoint discovery will be enabled for operations when available.

@option options [Aws::Log::Formatter] :log_formatter (Aws::Log::Formatter.default)
  The log formatter.

@option options [Symbol] :log_level (:info)
  The log level to send messages to the `:logger` at.

@option options [Logger] :logger
  The Logger instance to send log messages to.  If this option
  is not set, logging will be disabled.

@option options [Integer] :max_attempts (3)
  An integer representing the maximum number attempts that will be made for
  a single request, including the initial attempt.  For example,
  setting this value to 5 will result in a request being retried up to
  4 times. Used in `standard` and `adaptive` retry modes.

@option options [String] :profile ("default")
  Used when loading credentials from the shared credentials file
  at HOME/.aws/credentials.  When not specified, 'default' is used.

@option options [Proc] :retry_backoff
  A proc or lambda used for backoff. Defaults to 2**retries * retry_base_delay.
  This option is only used in the `legacy` retry mode.

@option options [Float] :retry_base_delay (0.3)
  The base delay in seconds used by the default backoff function. This option
  is only used in the `legacy` retry mode.

@option options [Symbol] :retry_jitter (:none)
  A delay randomiser function used by the default backoff function.
  Some predefined functions can be referenced by name - :none, :equal, :full,
  otherwise a Proc that takes and returns a number. This option is only used
  in the `legacy` retry mode.

  @see https://www.awsarchitectureblog.com/2015/03/backoff.html

@option options [Integer] :retry_limit (3)
  The maximum number of times to retry failed requests.  Only
  ~ 500 level server errors and certain ~ 400 level client errors
  are retried.  Generally, these are throttling errors, data
  checksum errors, networking errors, timeout errors, auth errors,
  endpoint discovery, and errors from expired credentials.
  This option is only used in the `legacy` retry mode.

@option options [Integer] :retry_max_delay (0)
  The maximum number of seconds to delay between retries (0 for no limit)
  used by the default backoff function. This option is only used in the
  `legacy` retry mode.

@option options [String] :retry_mode ("legacy")
  Specifies which retry algorithm to use. Values are:

  * `legacy` - The pre-existing retry behavior.  This is default value if
    no retry mode is provided.

  * `standard` - A standardized set of retry rules across the AWS SDKs.
    This includes support for retry quotas, which limit the number of
    unsuccessful retries a client can make.

  * `adaptive` - An experimental retry mode that includes all the
    functionality of `standard` mode along with automatic client side
    throttling.  This is a provisional mode that may change behavior
    in the future.

@option options [String] :secret_access_key

@option options [String] :session_token

@option options [Boolean] :stub_responses (false)
  Causes the client to return stubbed responses. By default
  fake responses are generated and returned. You can specify
  the response data to return or errors to raise by calling
  {ClientStubs#stub_responses}. See {ClientStubs} for more information.

  ** Please note ** When response stubbing is enabled, no HTTP
  requests are made, and retries are disabled.

@option options [Boolean] :validate_params (true)
  When `true`, request parameters are validated before
  sending the request.

@option options [URI::HTTP,String] :http_proxy A proxy to send
  requests through.  Formatted like 'http://proxy.com:123'.

@option options [Float] :http_open_timeout (15) The number of
  seconds to wait when opening a HTTP session before raising a
  `Timeout::Error`.

@option options [Integer] :http_read_timeout (60) The default
  number of seconds to wait for response data.  This value can
  safely be set per-request on the session.

@option options [Float] :http_idle_timeout (5) The number of
  seconds a connection is allowed to sit idle before it is
  considered stale.  Stale connections are closed and removed
  from the pool before making a request.

@option options [Float] :http_continue_timeout (1) The number of
  seconds to wait for a 100-continue response before sending the
  request body.  This option has no effect unless the request has
  "Expect" header set to "100-continue".  Defaults to `nil` which
  disables this behaviour.  This value can safely be set per
  request on the session.

@option options [Boolean] :http_wire_trace (false) When `true`,
  HTTP debug output will be sent to the `:logger`.

@option options [Boolean] :ssl_verify_peer (true) When `true`,
  SSL peer certificates are verified when establishing a
  connection.

@option options [String] :ssl_ca_bundle Full path to the SSL
  certificate authority bundle file that should be used when
  verifying peer certificates.  If you do not pass
  `:ssl_ca_bundle` or `:ssl_ca_directory` the the system default
  will be used if available.

@option options [String] :ssl_ca_directory Full path of the
  directory that contains the unbundled SSL certificate
  authority files for verifying peer certificates.  If you do
  not pass `:ssl_ca_bundle` or `:ssl_ca_directory` the the
  system default will be used if available.
Calls superclass method
# File lib/aws-sdk-sagemakerruntime/client.rb, line 324
def initialize(*args)
  super
end

Public Instance Methods

build_request(operation_name, params = {}) click to toggle source

@param params ({}) @api private

# File lib/aws-sdk-sagemakerruntime/client.rb, line 587
def build_request(operation_name, params = {})
  handlers = @handlers.for(operation_name)
  context = Seahorse::Client::RequestContext.new(
    operation_name: operation_name,
    operation: config.api.operation(operation_name),
    client: self,
    params: params,
    config: config)
  context[:gem_name] = 'aws-sdk-sagemakerruntime'
  context[:gem_version] = '1.35.0'
  Seahorse::Client::Request.new(handlers, context)
end
invoke_endpoint(params = {}, options = {}) click to toggle source

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 AWS Signature Version 4. For information, see [Authenticating Requests (AWS 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.

<note markdown=“1”> 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.

</note>

[1]: docs.aws.amazon.com/sagemaker/latest/dg/how-it-works.html [2]: docs.aws.amazon.com/AmazonS3/latest/API/sig-v4-authenticating-requests.html

@option params [required, String] :endpoint_name

The name of the endpoint that you specified when you created the
endpoint using the [CreateEndpoint][1] API.

[1]: https://docs.aws.amazon.com/sagemaker/latest/dg/API_CreateEndpoint.html

@option params [required, String, StringIO, File] :body

Provides input data, in the format specified in the `ContentType`
request header. Amazon SageMaker passes all of the data in the body to
the model.

For information about the format of the request body, see [Common Data
Formats-Inference][1].

[1]: https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html

@option params [String] :content_type

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

@option params [String] :accept

The desired MIME type of the inference in the response.

@option params [String] :custom_attributes

Provides additional information about a request for an inference
submitted to a model hosted at an Amazon SageMaker endpoint. The
information is an opaque value that is forwarded verbatim. You could
use this value, for example, to provide an ID that you can use to
track a request or to provide other metadata that a service endpoint
was programmed to process. The value must consist of no more than 1024
visible US-ASCII characters as specified in [Section 3.3.6. Field
Value Components][1] of the Hypertext Transfer Protocol (HTTP/1.1).

The code in your model is responsible for setting or updating any
custom attributes in the response. If your code does not set this
value in the response, an empty value is returned. For example, if a
custom attribute represents the trace ID, your model can prepend the
custom attribute with `Trace ID:` in your post-processing function.

This feature is currently supported in the AWS SDKs but not in the
Amazon SageMaker Python SDK.

[1]: https://tools.ietf.org/html/rfc7230#section-3.2.6

@option params [String] :target_model

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

@option params [String] :target_variant

Specify the production variant to send the inference request to when
invoking an endpoint that is running two or more variants. Note that
this parameter overrides the default behavior for the endpoint, which
is to distribute the invocation traffic based on the variant weights.

For information about how to use variant targeting to perform a/b
testing, see [Test models in production][1]

[1]: https://docs.aws.amazon.com/sagemaker/latest/dg/model-ab-testing.html

@option params [String] :target_container_hostname

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

@option params [String] :inference_id

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][1].

[1]: https://docs.aws.amazon.com/sagemaker/latest/dg/model-monitor-data-capture.html

@return [Types::InvokeEndpointOutput] Returns a {Seahorse::Client::Response response} object which responds to the following methods:

* {Types::InvokeEndpointOutput#body #body} => String
* {Types::InvokeEndpointOutput#content_type #content_type} => String
* {Types::InvokeEndpointOutput#invoked_production_variant #invoked_production_variant} => String
* {Types::InvokeEndpointOutput#custom_attributes #custom_attributes} => String

@example Request syntax with placeholder values

resp = client.invoke_endpoint({
  endpoint_name: "EndpointName", # required
  body: "data", # required
  content_type: "Header",
  accept: "Header",
  custom_attributes: "CustomAttributesHeader",
  target_model: "TargetModelHeader",
  target_variant: "TargetVariantHeader",
  target_container_hostname: "TargetContainerHostnameHeader",
  inference_id: "InferenceId",
})

@example Response structure

resp.body #=> String
resp.content_type #=> String
resp.invoked_production_variant #=> String
resp.custom_attributes #=> String

@see docs.aws.amazon.com/goto/WebAPI/runtime.sagemaker-2017-05-13/InvokeEndpoint AWS API Documentation

@overload invoke_endpoint(params = {}) @param [Hash] params ({})

# File lib/aws-sdk-sagemakerruntime/client.rb, line 475
def invoke_endpoint(params = {}, options = {})
  req = build_request(:invoke_endpoint, params)
  req.send_request(options)
end
invoke_endpoint_async(params = {}, options = {}) click to toggle source

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 AWS Signature Version 4. For information, see [Authenticating Requests (AWS Signature Version 4)] in the *Amazon S3 API Reference*.

[1]: docs.aws.amazon.com/AmazonS3/latest/API/sig-v4-authenticating-requests.html

@option params [required, String] :endpoint_name

The name of the endpoint that you specified when you created the
endpoint using the [ `CreateEndpoint` ][1] API.

[1]: https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html

@option params [String] :content_type

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

@option params [String] :accept

The desired MIME type of the inference in the response.

@option params [String] :custom_attributes

Provides additional information about a request for an inference
submitted to a model hosted at an Amazon SageMaker endpoint. The
information is an opaque value that is forwarded verbatim. You could
use this value, for example, to provide an ID that you can use to
track a request or to provide other metadata that a service endpoint
was programmed to process. The value must consist of no more than 1024
visible US-ASCII characters as specified in [Section 3.3.6. Field
Value Components][1] of the Hypertext Transfer Protocol (HTTP/1.1).

The code in your model is responsible for setting or updating any
custom attributes in the response. If your code does not set this
value in the response, an empty value is returned. For example, if a
custom attribute represents the trace ID, your model can prepend the
custom attribute with `Trace ID`\: in your post-processing function.

This feature is currently supported in the AWS SDKs but not in the
Amazon SageMaker Python SDK.

[1]: https://datatracker.ietf.org/doc/html/rfc7230#section-3.2.6

@option params [String] :inference_id

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

@option params [required, String] :input_location

The Amazon S3 URI where the inference request payload is stored.

@option params [Integer] :request_ttl_seconds

Maximum age in seconds a request can be in the queue before it is
marked as expired.

@return [Types::InvokeEndpointAsyncOutput] Returns a {Seahorse::Client::Response response} object which responds to the following methods:

* {Types::InvokeEndpointAsyncOutput#inference_id #inference_id} => String
* {Types::InvokeEndpointAsyncOutput#output_location #output_location} => String

@example Request syntax with placeholder values

resp = client.invoke_endpoint_async({
  endpoint_name: "EndpointName", # required
  content_type: "Header",
  accept: "Header",
  custom_attributes: "CustomAttributesHeader",
  inference_id: "InferenceId",
  input_location: "InputLocationHeader", # required
  request_ttl_seconds: 1,
})

@example Response structure

resp.inference_id #=> String
resp.output_location #=> String

@see docs.aws.amazon.com/goto/WebAPI/runtime.sagemaker-2017-05-13/InvokeEndpointAsync AWS API Documentation

@overload invoke_endpoint_async(params = {}) @param [Hash] params ({})

# File lib/aws-sdk-sagemakerruntime/client.rb, line 578
def invoke_endpoint_async(params = {}, options = {})
  req = build_request(:invoke_endpoint_async, params)
  req.send_request(options)
end
waiter_names() click to toggle source

@api private @deprecated

# File lib/aws-sdk-sagemakerruntime/client.rb, line 602
def waiter_names
  []
end