Integration of AI Functionalities

Use the features of the Artificial Intelligence Platform to offer object type predictions during object creation processes in your client application.

Introduction

The Artificial Intelligence Platform is a set of APIs and tools that enable customers to set up and use AI functionalities by themselves, with low costs and high performance. Customers can export their own documents, train models using different algorithms provided by OPTIMAL SYSTEMS GmbH, evaluate trained models, and deploy them to make predictions. Every part of the AI Platform can be deployed on-premises or in the cloud.
>> Platform Overview

The following information is intended to support administrators to configure the system for the AI functionalities to be integrated in client applications based on our developer libraries.

Classification in Object Type Definitions

The object types to be considered for analysis and predictions via the AI services have to be classified with the classification attribute:

<classification>prediction:classify</classification>

Set this attribute for all desired object types in their schema definition.
>> Schema - Defining Object Types | Defining Object Types for a Library-based Client

Inference Schema

The inference schema is a JSON configuration file defining the object types that will be available for the classification as well as the properties for which the metadata extraction should be done.
>> Inference Schema

In order to use the Artificial Intelligence Platform with a client application based on our client libraries (e.g., yuuvis® client as reference implementation), objectTypeId has to be defined as a concatenation of app name and SOTs separated by pipes as can be seen in the following example:

Example inference schema
{
    "tenant" : "os__papi",
    "appName" : "AIInvoiceClient",
    "classification" : {
        "enabled" : true,
        "timeout" : 10,
        "aiClassifierId" : "DOCUMENT_CLASSIFICATION",
		"objectTypes": [ 
			{ 
				"objectTypeId" : "appImpulse:hrdocsot|appImpulse:hrDocumentType|Bescheinigung",
				"aiObjectTypeId" : "appImpulse:contractsot"
			},
			{ 
				"objectTypeId" : "appImpulse:receiptsot",
				"aiObjectTypeId" : "appImpulse:hrdocsot"
			},
			{ 
				"objectTypeId" : "appImpulse:contractsot|appImpulse:contractType|Arbeitsvertrag",
				"aiObjectTypeId" : "appImpulse:receiptsot"
			},
			{ 
				"objectTypeId" : "appImpulse:hrdocsot|appImpulse:hrDocumentType|Arbeitsvertrag",
				"aiObjectTypeId" : "appImpulse:basedocumentsot"
			}
		]
    }
}

The inference schema is managed via a the Kairos CLI App.
>> KAIROS-API Service