Atlas AI - Azure Step 3: Manual creation of Azure OpenAI in your subscription (Atlas 6.0+)

NOTE: Before creating any Azure OpenAI service in your Azure subscription, you must request Microsoft to enable the service first, and you will have to wait for some time for Microsoft to approve your request. If you have never done this, we recommend you follow the related article to do so, which you can find at the bottom of this article. 

*See all Atlas AI & IKS articles here*

Atlas comes with a set of AI features that make use of the OpenAI service provided by Microsoft in Azure.

This article outlines the steps required for both creating the Azure OpenAI resource and configuring it to work with Atlas.

In the next sections of this article, you will learn:

• How to create Azure OpenAI with the configuration required for Atlas
• How to create the models used by Azure OpenAI to make it compatible with the use of Atlas

Once you complete both steps to create Azure OpenAI and configure the models, you must take note of the name of the Azure OpenAI resource, which is the only thing we will request from you when deploying Atlas to make it compatible with the AI features.

NOTE: If you already have an Azure OpenAI resource created in your Azure subscription that you would like to make compatible with Atlas, you can still follow the next steps to manage some configuration, like the networking settings of the resource as well as the creation or configuration of the required OpenAI models.

Create and configure Azure OpenAI in your Azure subscription

First, you must create the resource in your Azure subscription for later configuration. Follow the next steps to create the resource and configure it (if you just want to configure the networking, you can set in your existing resource the same configuration that you will see in these steps):

1. Open your browser and go to https://portal.azure.com
2. In the top search box in the portal, search for "Azure OpenAI" and click on the first result (see screenshot below):
   
3. The next window is a general view of the Azure OpenAI resources you may have created with your subscription. To create a new one, click on the "+ Create" button:
   
4. The next window is the form to create Azure OpenAI. Fill in each value in the form in the following way:

• •  Basics

Subscription: Select the subscription where you will create the resource

IMPORTANT: The subscription must be the same where the rest of your Atlas' resources are located

Resource group: Select the resource group where the resource will be created (the resource group can be in another region)

IMPORTANT: The resource group must be the same one where you will be deploying Atlas

Region: Select the region where Azure OpenAI will be created

IMPORTANT: The region must be compatible with the use of Atlas in terms of what models can be created. For this version of Atlas, we require the use of GPT-4o (version 2024-08-06) and GPT-4o-mini (version 2024-07-18), so please make sure to check the compatible regions for these models here: Azure OpenAI Service models - Model summary table and region availability
We also offer a separate article that adds a bit more of context and information related to the compatible regions. You can find it at the bottom of this article.

Name: Type the name of your choice for your Azure OpenAI resource

Pricing tier: Select "Standard S0" (currently the only option available)

The "Basics" tab in the form should look like the example below:

• • Network
    
    Type: "All networks, including the internet, can access this resource"
    
    The "Network" tab in the form should look like the example below:
    
    
    NOTE: If you already have an Azure OpenAI resource created and only want to make it compatible with Atlas, go to your resource in Azure and on the left side of the configuration options, under "Resource Management" -> "Networking", select the "All networks" option under "Firewalls and virtual networks", and click on "Save" if you are modifying the configuration (see example below):
    
    
    
  • Tags: This is optional, and there are no requirements to meet
    
    
  • Review + submit: Confirm your selections and create the resource by clicking on the "Create" button at the bottom of the form. See the example below:
    

1.  

1.  

Create and configure Azure OpenAI models

In this section, you will see the models that you must create to make the Azure OpenAI service compatible with the AI features that come along with Atlas. Three models will be created in this section:

• text-embedding-3-large
• gpt-4o
• gpt-4o-mini

Creating a model in your Azure OpenAI service is also known as "creating a new deployment", which is really like creating an instance of a given model from the ones available in your Azure OpenAI service. This means that you may have, for example, two deployments (or instances) of the model "gpt-4o" or "gpt-4o-mini" that may coexist because you may be working with different products that leverage your Azure OpenAI service created in your Azure subscription.

The next steps will provide the guidelines to create these deployments and configure them to make them compatible with the use of Atlas AI. You will end up with up to three new deployments of the models that will be compatible with our Atlas AI features, and these will be the ones used by Atlas when configuring it during a deployment to work with your Azure OpenAI service:

1. Open your browser and go to Azure AI Foundry
2. Click on the "Sign In" button at the top-right corner, if you are not already signed in, with your work account
   
   
   
3. Once in the Home dashboard of the "Azure AI Foundry | Azure OpenAI Service" portal, make sure to select the Azure OpenAI Service resource you want to work with using the select dropdown at the top as shown in the screenshot
   
   
   
4. Now, under "Shared resources", click on "Deployments" in the left menu, and then click on the "+ Deploy model" button:
   
   
   
5. A new window will appear showing up all the available models for your Azure OpenAI to create a new deployment. So, first, we need to select the model we want and then click on Confirm:
   
   
   
6. A new form will appear to create the deployment with the configuration you want. Because you must create up to three deployments (repeat this process as needed), one per each of the models required, follow the next tables and screenshots to fill in the information required for each field, and click on "Create" each time to save your deployment.
   
   IMPORTANT: you should use the same values for the "Deployment name" and "Model version" from the tables below for your deployment; otherwise, Atlas AI may not work when using your Azure OpenAI resource. However, for the rest of the fields, the values that we suggest are just recommendations to get a good performance.
   
   Please, pay special attention to the "Deployment type" field because this option cannot be edited after creating the deployment. If you need a different deployment type because your data is geo-sensitive or if you need more information before continuing, please check the documentation here: Azure OpenAI deployment types
   
   WARNING: A bug has recently been detected in the User Interface of this form. When changing the model version, the "Model Name" field reset to default without any notice, so please leave the "Model Name" field for the end just before applying to avoid misconfigurations.
   
   
   • Model gpt-4o:
     
     

     Deployment name	atlas-gpt-4o
     Deployment Type	Global Standard
     Deployment Details
     Model version	2024-08-06
     Tokens per Minute Rate Limit (thousands)	150K
     Content Filter	DefaultV2

     
     
     
     
     
   • Model gpt-4o-mini:
     
     

     Deployment name	atlas-gpt-4o-mini
     Deployment Type	Global Standard
     Deployment Details
     Model version	2024-07-18 (Default)
     Tokens per Minute Rate Limit (thousands)	300K
     Content Filter	DefaultV2

     
     
     
     
     
   • Model text-embedding-3-large
     
     

     Deployment name	atlas-embeddings
     Deployment Type	Standard
     Deployment Details
     Model version	1 (Default)
     Tokens per Minute Rate Limit (thousands)	250K
     Content Filter	DefaultV2
     Enable Dynamic Quota	Enabled

     
     
     
     
7. Once you create the deployments, your "Deployments" summary should look like the screenshot below (notice you might have other deployments in your Azure OpenAI resource):
   
   
   

Now that you have completed all the steps, remember to take note of the name of your Azure OpenAI resource to make use of it when deploying Atlas to your Azure subscription. Additionally, if you need to modify the technical configuration of the OpenAI models for any reason at any moment, please check the related article referred to this matter down below.

Related articles:

• Atlas AI: Review access to Azure OpenAI in your Azure subscription (and request access to Microsoft)
• Atlas AI - Atlas 6.0: Compatible regions for the Azure OpenAI service
• Atlas AI - Atlas 6.0: Changing the configuration of the Open AI models for Atlas