NAME
Paws::SageMakerA2IRuntime - Perl Interface to AWS Amazon Augmented AI Runtime
SYNOPSIS
use Paws;
my $obj = Paws->service('SageMakerA2IRuntime');
my $res = $obj->Method(
Arg1 => $val1,
Arg2 => [ 'V1', 'V2' ],
# if Arg3 is an object, the HashRef will be used as arguments to the constructor
# of the arguments type
Arg3 => { Att1 => 'Val1' },
# if Arg4 is an array of objects, the HashRefs will be passed as arguments to
# the constructor of the arguments type
Arg4 => [ { Att1 => 'Val1' }, { Att1 => 'Val2' } ],
);
DESCRIPTION
Amazon Augmented AI (Augmented AI) (Preview) is a service that adds human judgment to any machine learning application. Human reviewers can take over when an AI application can't evaluate data with a high degree of confidence.
From fraudulent bank transaction identification to document processing to image analysis, machine learning models can be trained to make decisions as well as or better than a human. Nevertheless, some decisions require contextual interpretation, such as when you need to decide whether an image is appropriate for a given audience. Content moderation guidelines are nuanced and highly dependent on context, and they vary between countries. When trying to apply AI in these situations, you can be forced to choose between "ML only" systems with unacceptably high error rates or "human only" systems that are expensive and difficult to scale, and that slow down decision making.
This API reference includes information about API actions and data types you can use to interact with Augmented AI programmatically.
You can create a flow definition against the Augmented AI API. Provide the Amazon Resource Name (ARN) of a flow definition to integrate AI service APIs, such as Textract.AnalyzeDocument and Rekognition.DetectModerationLabels. These AI services, in turn, invoke the StartHumanLoop API, which evaluates conditions under which humans will be invoked. If humans are required, Augmented AI creates a human loop. Results of human work are available asynchronously in Amazon Simple Storage Service (Amazon S3). You can use Amazon CloudWatch Events to detect human work results.
You can find additional Augmented AI API documentation in the following reference guides: Amazon Rekognition (https://aws.amazon.com/rekognition/latest/dg/API_Reference.html), Amazon SageMaker (https://aws.amazon.com/sagemaker/latest/dg/API_Reference.html), and Amazon Textract (https://aws.amazon.com/textract/latest/dg/API_Reference.html).
For the AWS API documentation, see https://docs.aws.amazon.com/goto/WebAPI/a2i-runtime.sagemaker-2019-11-07
METHODS
DeleteHumanLoop
Each argument is described in detail in: Paws::SageMakerA2IRuntime::DeleteHumanLoop
Returns: a Paws::SageMakerA2IRuntime::DeleteHumanLoopResponse instance
Deletes the specified human loop for a flow definition.
DescribeHumanLoop
Each argument is described in detail in: Paws::SageMakerA2IRuntime::DescribeHumanLoop
Returns: a Paws::SageMakerA2IRuntime::DescribeHumanLoopResponse instance
Returns information about the specified human loop.
ListHumanLoops
- [CreationTimeAfter => Str]
- [CreationTimeBefore => Str]
- [MaxResults => Int]
- [NextToken => Str]
- [SortOrder => Str]
Each argument is described in detail in: Paws::SageMakerA2IRuntime::ListHumanLoops
Returns: a Paws::SageMakerA2IRuntime::ListHumanLoopsResponse instance
Returns information about human loops, given the specified parameters.
StartHumanLoop
- FlowDefinitionArn => Str
- HumanLoopInput => Paws::SageMakerA2IRuntime::HumanLoopInputContent
- HumanLoopName => Str
- [DataAttributes => Paws::SageMakerA2IRuntime::HumanReviewDataAttributes]
Each argument is described in detail in: Paws::SageMakerA2IRuntime::StartHumanLoop
Returns: a Paws::SageMakerA2IRuntime::StartHumanLoopResponse instance
Starts a human loop, provided that at least one activation condition is met.
StopHumanLoop
Each argument is described in detail in: Paws::SageMakerA2IRuntime::StopHumanLoop
Returns: a Paws::SageMakerA2IRuntime::StopHumanLoopResponse instance
Stops the specified human loop.
PAGINATORS
Paginator methods are helpers that repetively call methods that return partial results
ListAllHumanLoops(sub { },[CreationTimeAfter => Str, CreationTimeBefore => Str, MaxResults => Int, NextToken => Str, SortOrder => Str])
ListAllHumanLoops([CreationTimeAfter => Str, CreationTimeBefore => Str, MaxResults => Int, NextToken => Str, SortOrder => Str])
If passed a sub as first parameter, it will call the sub for each element found in :
- HumanLoopSummaries, passing the object as the first parameter, and the string 'HumanLoopSummaries' as the second parameter
If not, it will return a a Paws::SageMakerA2IRuntime::ListHumanLoopsResponse instance with all the params; from all the responses. Please take into account that this mode can potentially consume vasts ammounts of memory.
SEE ALSO
This service class forms part of Paws
BUGS and CONTRIBUTIONS
The source code is located here: https://github.com/pplu/aws-sdk-perl
Please report bugs to: https://github.com/pplu/aws-sdk-perl/issues