Skip to content

AI Services

To simplify the use of various AI services, we have created a central location where you can store your AI service resources. These resources can then be reused in our modules. This significantly simplifies the setup and avoids inconsistencies from different configuration sources.

All AI services are centrally managed in the “Core – AI Service List". There, you can create as many services as you like and use them in the modules of your choice.

Setting Up an AI Service

Setting up an AI service is straightforward. Please follow these steps:

  1. Open the search in Business Central and enter “Core – AI Service List".
  2. Open the “Core – AI Service List" page.
  3. You are now in the overview of all available AI services. Click on “Create" to create a new service.

A wizard will then open to guide you through the creation of the AI service. Please note:

  • Each AI service requires a unique name.
  • The description serves for internal documentation of your configuration.
  • In the AI Service Type field, select the desired service type.
  • Depending on the selected service, you will need to provide different configuration data (see below).

Important

To use the services, you need an active Azure Subscription. If you do not have an Azure account yet, you can create a free account here or contact your partner.

Supported AI Services

AI Service Description Setup Guide
Azure OpenAI Use of OpenAI models via Azure (e.g., GPT-4, Chat, Embeddings). Create Azure OpenAI Service
Document Intelligence Extraction and classification of content from documents. —
AI Content Understanding (Preview) Advanced, semantic document analysis with context-based understanding and schema extraction. This service is currently in preview. Create Content Understanding Service

Retrieve Resource Details

  1. Open the Azure Portal.
  2. Create a new Azure OpenAI Service if it does not already exist.
  3. After creation: Navigate to Resource Management → Keys and Endpoint to obtain your API key and Endpoint.
  4. In the overview, open the link to the AI Foundry Portal.
  5. In the AI Foundry Portal: Go to Deployments to deploy a model (e.g., gpt-4o).
  6. Enter these values during setup in the AI Service Configuration Wizard.
  1. Open the Azure Portal for Document Intelligence.
  2. Create a new Document Intelligence Service.
  3. Go to Resource Management → Keys and Endpoint.
  4. Enter these values during setup in the AI Service Configuration Wizard.
  1. Open the AI Foundry Portal for Content Understanding.
  2. Create a new Content Understanding Project using the wizard.
  3. After setup: Open the created project and scroll down in the left menu to the Management Center.
  4. Then navigate to the “Overview" tab. There, under “Project properties" on the right side, you will find the link “Get API endpoints and keys".
  5. Enter these values during setup in the AI Service Configuration Wizard.

If this guide is not sufficient, we refer you to the Microsoft Documentation for creating the service.

Information

The service connection is validated once during the creation of the AI service in Business Central. If the service is not configured correctly, an appropriate error message will appear.

Once you have selected the desired AI service type and entered all necessary configuration data, you can complete the wizard. The service will then be available system-wide in our modules.

Microsoft Foundry Service

AI-based functions are subject to so-called quotas. Quotas determine how many AI requests and how much data processing is possible within a certain period. If the available quota is reached, AI functions may be temporarily restricted or delayed. Depending on the use case, a quota increase can be requested from Microsoft to enable higher or more stable usage. For more information and the possibility to request, see Microsoft Foundry Service: Request for Quota Increase