Atlas AI: (Optional) Manual creation of Azure Open AI in your subscription (In preference to Steps 1-3)

**This is not a public document and should be shared carefully to protect ClearPeople IP**

**AI technology and supporting information is rapidly changing**

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.

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

During the deployment of Atlas, you can also choose to create, at the same time, the Azure OpenAI service in your Azure subscription within the same resource group that is used to deploy the rest of Atlas' resources that will be used by Atlas for its AI features.

You will be able to select in each deployment of Atlas if you want us to create or update the Azure OpenAI resource (preferred option) like we do with the rest of Atlas' Azure resources; however, you might prefer to create and manage the Azure OpenAI service on your own due to any reasons related to your company's management. Because of this, 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):
   1. 
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:
   1. 
4. The next window is the form to create Azure OpenAI. Fill in each value in the form in the following way:
   1. Basics
      1. Subscription: Select the subscription where you will create the resource
         1. IMPORTANT: If you want Azure OpenAI to be managed by the deployments of Atlas, the subscription must be the same where the rest of your Atlas' resources are located
      2. Resource group: Select the resource group where the resource will be created (the resource group can be in another region)
         1. IMPORTANT: If you want Azure OpenAI to be managed by the deployments of Atlas, the resource group must be the same where you will be deploying Atlas
      3. Region: Select the region where Azure OpenAI will be created
         1. IMPORTANT: The region must be compatible with the use of Atlas in terms of what models can be created. If you haven't reviewed the available regions yet, you can see the related article on compatible regions at the bottom of this article
      4. Name: Type the name of your choice for your Azure OpenAI resource
         1. IMPORTANT: If you want Azure OpenAI to be managed by the deployments of Atlas, the name of the resource must follow this pattern: cog-atlas-oai-{0}-{1}
            1. {0}: This is what is known in Atlas as the client acronym
               1. The maximum number of characters allowed is six. Example: "msft"
            2. {1}: This is what is known in Atlas as the Atlas environment name
               1. The maximum number of characters allowed is four. Example: "prod"
            3. If you have never deployed Atlas yet, you will be asked to fill in this information in the form that you will be provided by ClearPeople (contact your CSA) before deploying Atlas. You can also get these values from the .csv file that you will be provided to run the Atlas deployment
            4. If you are already a customer using Atlas, you can also get this information from the resources that are deployed in your resource group in Azure, where your Atlas' resources are deployed. See the screenshot below for an example
               1. 
      5. Pricing tier: Select "Standard S0" (currently the only option available)
      6. The "Basics" tab in the form should look like the example below:
         1. 
5. Network
   1. Type: "All networks, including the internet, can access this resource"
   2. The "Network" tab in the form should look like the example below:
      1. 
   3. 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 in 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):
      1. 
6. Tags: This is optional, and there are no requirements to meet
7. 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. 

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. Two models will be created in this section:

• gpt-4-32k
• text-embedding-ada-002

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-4-32k" 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 two 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 https://portal.azure.com
2. Search for your Azure OpenAI resource and click on it
   1. You can do this either by searching for the name of the resource on the top search bar in the Azure Portal:
      1. 
   2. Or you can search in the top bar for Azure OpenAI and select the resource you want to work with:
      1. 
      2. 
3. On the left menu, under "Resource Management", click on "Model deployments" and click on the "Manage Deployments" button that will show up. This will open in the browser the "Azure OpenAI Studio", where you can manage the deployments of your available models:
   1. 
4. In Azure OpenAI Studio, under "Management", click on "Deployments" in the left menu, and click on the "+ Create new deployment" button:
   1. 
5. A new form will appear to create the deployment with the configuration you want. Because you must create two deployments (repeat this process twice), 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 from the tables for your deployment; otherwise, Atlas AI may not work when using your Azure OpenAI resource; e.g., using a different "model, "version" or "deployment name"):
   

   1. Select a model	gpt-4-32k
      Model version	0613
      Deployment name	atlas-gpt
      Advanced options
      Content Filter	Default
      Deployment type	Standard
      Tokens per Minute Rate Limit (thousands)	30K
      Enable Dynamic Quota	Disabled

   2. 

   3. Select a model	text-embedding-ada-002
      Model version	2 (Default)
      Deployment name	atlas-embeddings
      Advanced options
      Content Filter	Default
      Tokens per Minute Rate Limit (thousands)	120K
      Enable Dynamic Quota	Disabled

   4. 
6. Once you create both deployments, your "Deployments" summary should look like the screenshot below (notice you might have other deployments in your Azure OpenAI resource):
   1. 

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.

Related articles:

• Atlas AI: Review access to Azure OpenAI in your Azure subscription (and request access to Microsoft)
• Atlas AI: Compatible regions for the Azure Open AI service