> For the complete documentation index, see [llms.txt](https://docs.inogic.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.inogic.com/next-best-action/installation/installation-of-nba-ai-ml-engine.md).
# Installation of NBA AI/ML Engine
To install NBA AI/ML Engine, follow the steps below:
**Download the NBA AI/ML Engine (Azure Managed Application)**\
* Once you click on Install it will navigate you to the NBA AI/ML Engine page, click Get it now to begin the deployment process.
* A confirmation prompt appears. Click '**Get it now**' again to confirm.
**Select Subscription and Create**
* Select your active Azure subscription from the subscription dropdown. (You must have an active subscription to proceed.)
* Click **Create** to continue to the deployment configuration UI.
**Basics Tab - Resource Group & Names**
* Create a new Resource Group OR select an existing Resource Group.
* Important: If you select an existing resource group, it must be empty. If it contains resources, create a new resource group instead.
* Enter the Container App name and Managed Application name.
{% hint style="info" %}
**Note**: The Container App name will appear in the URL of the created container app. Choose it carefully.
{% endhint %}
* Enter the Object ID of the deploying user.
* To get the Object ID, go to the Azure portal, search for Microsoft Entra ID.
* Click **Manage → Users**.
* Click **All users → Search for your username and select it.**
* Copy the **Object ID**.
* Paste your Object ID and click **Next**.
#### **OpenAI Service Configuration Tab**
Move to the Open AI service configuration tab. You will be prompted to choose an option (Yes / No).
### **If you select No:**
* The NBA AI/ML Engine will create an Azure AI service for you and deploy the model into that service automatically.
* From the dropdown, select the model you want to deploy and select/set the token for that model.
* Set the token value based on your requirements and the tokens available in your Azure subscription. (Ensure you have sufficient tokens/quota for the chosen model.)
* Click **Next** to proceed.
#### **Finalize Deployment**
* Review all configuration selections (subscription, resource group, container app name, OpenAI configuration, model and token, environment, owner).
* Complete the deployment (click **Create / Deploy** as applicable in the Azure UI).
* This will create a managed application in the selected Azure subscription. After successful deployment user must open the managed application.
### **If you select Yes:**
* In the Azure OpenAI Service dropdown, all existing Azure OpenAI services will be listed. Select the service you want to use.
**Note:** The Azure service must have at least one deployed chat completion model
* Select the **Model Deployment Name** and **Azure OpenAI API Version**, then click **Next**.
* Go to:
\
**Home → ChatCompletionService → Access Control (IAM) → Add Role Assignment**
* Under **Roles**, select **Cognitive Services OpenAI User**.
* Under **Members**, choose **Assign access to Managed Identity**.
* To get the managed identity name:
\
Go to the **Azure** Portal and search for **Managed Applications**.
* Open it and search for the deployed NBA AI/ML engine (**NBAEngine**).
* Open the **Managed resource group** from that application.
* Look for the **Managed Identity** under resources and copy its name.
* Paste the name into **Managed Identity**, then:
* Click **Select**.
* Click **Review+assign**.
* After assigning:
Open the Managed Resource Group again.
Locate and open the **Azure Machine Learning Workspace**.
* Under the **Manage** section, open the **Studio Web URL**.
* Go to **Manage** -> **Compute**
* Scroll down and find System Assigned Identity
* Copy the Principal ID
* Now go back and:
Click **Members** → Assign access to **User, Group, or Service Principal**
* Paste the **Principal ID**.
* Click **Select**.
* Click **Review + Assign**.
* Click Here to configure the NBA AI/ML Engine.