Introduction

This documentation describes how to go about deploying and configuring Azure OpenAI models.

Prerequisites

The following prerequisites must be fullfilled before starting on configuring the PA models:

• An Azure subscription - An active Azure Plan or Pay-as-you-go subscription is required. If one does not have one, one can sign up for one at https://portal.azure.com.

• A Sufficient large Azure OpenAI quota - Using one of the methods described in Azure Open AI Quotas Verification, ensure that the quota is sufficiently large. If needed, request more using this form. See Azure OpenAI Service quotas and limits - Azure AI services for details.

• The Personal Assistant Administrator Role - Consult the Managing Users and Roles section of the Ayfie Locator Installation Guide for how to be made a Personal Assistant Admin.

Configuration

The Personal Assistant offers two configuration variants:

• Auto Configuration: Applies to Marketsplace offers where the Personal Assistant is automatically configured.

• On-Demand Configuration: Used in on-premises deployments and is described below.

In the following we will describe the manual steps of the on-demand configuration.

First-time Deployment

1. Obtain the Azure ARM Template: Acquire the template from the application.
   
   

   Open

   

2. Deploy models: Use the Deploy from Custom Template feature to deploy the Azure OpenAI models. It provides the preferred configuration parameters, such as the OpenAI model quota and the model deployment type. It is recommended to use Sweden Central as the deployment region due to the model's capacity and availability.
   
   

To deploy ARM template follow these steps

• Select Build your own template in the editor

Open

• Replace the selected text with ARM template definition and press Save

• Fill in the form

3. Obtain the API Token and the API URL
   Once the deployment is completed, navigate to the selected resource group and the newly created Azure OpenAI resource.
   Under Resource Management / Keys and Endpoint one will find the API token and the API URL

4. Insert system models
   Provide the API token and the API URL and press Save. The application is now configured with recommended models and can be tested.
   
   

Update Existing Deployment

1. Detection of new system model configuration

Once the system detects there is a new version of the recommended system model configuration, the Update system models option becomes available.

2. Redeploying models

The system will detect if the new recommended configuration requires a redeployjment of the Azure OpenAI models. In that case, the red circled message seen below will be shown:

• Navigate to Azure AI services | Azure Open AI and identify the Azure Open AI resource.

• Delete the resource - that will only result in a soft delete.

• Select Managed deleted resources and purge the deleted resource.
  

Follow these instructions to deploy new models

3. Obtain API token, API URL and update the configuration

Follow these instructions to finalize the model configuration.

Models restoration

The application also provides the option to restore the default system model configuration. To do so, click the Restore system model option and provide the API token and the API URL in the pop up window before clicking Save.