Skip to content

API for Amazon Augmented AI Runtime

ABAP Interface /AWS1/IF_SGA

The "TLA" is a Three Letter Abbreviation that appears in ABAP class names, data dictionary objects and other ABAP objects throughout the AWS SDK for SAP ABAP. The TLA for Amazon Augmented AI Runtime is SGA. This TLA helps squeeze ABAP objects into the 30-character length limit of the ABAP data dictionary.


To install the AWS SDK for SAP ABAP, import the Core transport, along with the transport for the SageMaker A2I Runtime module and other API modules you are interested in. A few modules are included in the Core transport itself. For more information, see the Developer Guide guide.

About The Service

Amazon Augmented AI (Amazon A2I) adds the benefit of human judgment to any machine learning application. When an AI application can't evaluate data with a high degree of confidence, human reviewers can take over. This human review is called a human review workflow. To create and start a human review workflow, you need three resources: a worker task template, a flow definition, and a human loop.

For information about these resources and prerequisites for using Amazon A2I, see Get Started with Amazon Augmented AI in the Amazon SageMaker Developer Guide.

This API reference includes information about API actions and data types that you can use to interact with Amazon A2I programmatically. Use this guide to:

  • Start a human loop with the StartHumanLoop operation when using Amazon A2I with a custom task type. To learn more about the difference between custom and built-in task types, see Use Task Types . To learn how to start a human loop using this API, see Create and Start a Human Loop for a Custom Task Type in the Amazon SageMaker Developer Guide.

  • Manage your human loops. You can list all human loops that you have created, describe individual human loops, and stop and delete human loops. To learn more, see Monitor and Manage Your Human Loop in the Amazon SageMaker Developer Guide.

Amazon A2I integrates APIs from various AWS services to create and start human review workflows for those services. To learn how Amazon A2I uses these APIs, see Use APIs in Amazon A2I in the Amazon SageMaker Developer Guide.

Using the SDK

In your code, create a client using the SDK module for Amazon Augmented AI Runtime, which is created with factory method /AWS1/CL_SGA_FACTORY=>create(). In this example we will assume you have configured an SDK profile in transaction /AWS1/IMG called ZFINANCE.

DATA(go_session)   = /aws1/cl_rt_session_aws=>create( 'ZFINANCE' ).
DATA(go_sga)       = /aws1/cl_sga_factory=>create( go_session ).

Your variable go_sga is an instance of /AWS1/IF_SGA, and all of the operations in the Amazon Augmented AI Runtime service are accessed by calling methods in /AWS1/IF_SGA.

API Operations

For an overview of ABAP method calls corresponding to API operations in Amazon Augmented AI Runtime, see the Operation List.

Factory Method

/AWS1/CL_SGA_FACTORY=>create( )

Creates an object of type /AWS1/IF_SGA.


Optional arguments:







/AWS1/IF_SGA represents the ABAP client for the SageMaker A2I Runtime service, representing each operation as a method call. For more information see the API Page page.

Configuring Programmatically

DATA(lo_config) = DATA(go_sga)->get_config( ).

lo_config is a variable of type /AWS1/CL_SGA_CONFIG. See the documentation for /AWS1/CL_SGA_CONFIG for details on the settings that can be configured.


Paginators for Amazon Augmented AI Runtime can be created via get_paginator() which returns a paginator object of type /AWS1/IF_SGA_PAGINATOR. The operation method that is being paginated is called using the paginator object, which accepts any necessary parameters to provide to the underlying API operation. This returns an iterator object which can be used to iterate over paginated results using has_next() and get_next() methods.

Details about the paginator methods available for service Amazon Augmented AI Runtime can be found in interface /AWS1/IF_SGA_PAGINATOR.