@@ -40,9 +40,9 @@ If your organization is using [Azure Policy](/azure/governance/policy/overview),
     
     :::image type="content" source="~/reusable-content/ce-skilling/azure/media/ai-studio/resource-create-basics.png" alt-text="Screenshot of the option to set hub basic information." lightbox="~/reusable-content/ce-skilling/azure/media/ai-studio/resource-create-basics.png":::
 
-1. Select the **Storage** tab to specify storage account settings.
+1. Select the **Storage** tab to specify storage account settings. For storing credentials, either provide your Azure Key Vault or use the [Microsoft-managed credential store (preview)](#choose-how-credentials-are-stored).
 
-    :::image type="content" source="~/reusable-content/ce-skilling/azure/media/ai-studio/resource-create-resources.png" alt-text="Screenshot of the Create a hub with the option to set storage resource information." lightbox="~/reusable-content/ce-skilling/azure/media/ai-studio/resource-create-resources.png"::: 
+    :::image type="content" source="../media/how-to/hubs/resource-create-resources.png" alt-text="Screenshot of the Create a hub with the option to set storage resource information." lightbox="../media/how-to/hubs/resource-create-resources.png"::: 
 
 1. Select the **Networking** tab to set up Network isolation. Read more on [network isolation](configure-managed-network.md). For a walkthrough of creating a secure hub, see [Create a secure hub](create-secure-ai-hub.md).
 
@@ -90,7 +90,7 @@ Hub networking settings can be set during resource creation or changed in the **
 
 At hub creation, select between the networking isolation modes: **Public**, **Private with Internet Outbound**, and **Private with Approved Outbound**. To secure your resource, select either **Private with Internet Outbound** or **Private with Approved Outbound** for your networking needs. For the private isolation modes, a private endpoint should be created for inbound access. For more information on network isolation, see [Managed virtual network isolation](configure-managed-network.md). To create a secure hub, see [Create a secure hub](create-secure-ai-hub.md). 
 
-At hub creation in the Azure portal, creation of associated Azure AI services, Storage account, Key vault, Application insights, and Container registry is given. These resources are found on the Resources tab during creation. 
+At hub creation in the Azure portal, creation of associated Azure AI services, Storage account, Key vault (optional), Application insights (optional), and Container registry (optional) is given. These resources are found on the Resources tab during creation. 
 
 To connect to Azure AI services (Azure OpenAI, Azure AI Search, and Azure AI Content Safety) or storage accounts in Azure AI Studio, create a private endpoint in your virtual network. Ensure the public network access (PNA) flag is disabled when creating the private endpoint connection. For more about Azure AI services connections, follow documentation [here](../../ai-services/cognitive-services-virtual-networks.md). You can optionally bring your own (BYO) search, but this requires a private endpoint connection from your virtual network.
 
@@ -143,20 +143,28 @@ az ml workspace update -n "myexamplehub" -g "{MY_RESOURCE_GROUP}" -a "APPLICATIO
 ```
 ---
 
-## Delete an Azure AI Studio hub
+### Choose how credentials are stored
+
+Select scenarios in AI Studio store credentials on your behalf. For example when you create a connection in AI Studio to access an Azure Storage account with stored account key, access Azure Container Registry with admin password, or when you create a compute instance with enabled SSH keys. No credentials are stored with connections when you choose EntraID identity-based authentication.
 
-To delete a hub, use the [Azure portal](https://portal.azure.com). To quickly get to the Azure portal from the Azure AI Studio, go to the **Hub overview** for your hub and then select **Manage in Azure portal**.
+You can choose where credentials are stored:
 
-:::image type="content" source="../media/how-to/hubs/manage-hub-azure-portal.png" alt-text="Screenshot of the manage in Azure portal link in Azure AI Studio.":::
+1. **Your Azure Key Vault**: This requires you to manage your own Azure Key Vault instance and configure it per hub. It gives you additional control over secret lifecycle e.g. to set expiry policies. You can also share stored secrets with other applications in Azure.
+   
+1. **Microsoft-managed credential store (preview)**: In this variant Microsoft manages an Azure Key Vault instance on your behalf per hub. No resource management is needed on your side and the vault does not show in your Azure subscription. Secret data lifecycle follows the resource lifecycle of your hubs and projects. For example, when a project's storage connection is deleted, its stored secret is deleted as well.
 
-From the portal page for your hub, select **Overview** along the left side of the page and then select **Delete** from the top of the page.
+After your hub is created, it is not possible to switch between Your Azure Key Vault and using a Microsoft-managed credential store.
+
+## Delete an Azure AI Studio hub
 
-:::image type="content" source="../media/how-to/hubs/delete-hub-button.png" alt-text="Screenshot of the delete button for the Azure AI Studio hub in the Azure portal.":::
+To delete a hub from Azure AI Studio, select the hub and then select **Delete hub** from the **Hub properties** section of the page.
 
-You can also find your hub in the Azure portal by entering the hub name in the search field at the top of the Azure portal. Select the hub from the **Resources** list to navigate to the **Overview** page for the hub.
+:::image type="content" source="../media/how-to/hubs/studio-delete-hub.png" alt-text="Screenshot of the delete hub link in hub properties." lightbox="../media/how-to/hubs/studio-delete-hub.png":::
 
-:::image type="content" source="../media/how-to/hubs/search-in-portal.png" alt-text="Screenshot of using the search field in the Azure portal to find a hub.":::
+> [!NOTE]
+> You can also delete the hub from the Azure portal.
 
+Deleting a hub deletes all associated projects. When a project is deleted, all nested endpoints for the project are also deleted. You can optionally delete connected resources; however, make sure that no other applications are using this connection. For example, another Azure AI Studio deployment might be using it.
 
 
 ## Related content

@@ -432,8 +432,8 @@ result = evaluate(
     },
     # column mapping
     evaluator_config={
-        "column_mapping": {
-            "relevance": {
+        "relevance": {
+            "column_mapping": {
                 "query": "${data.queries}"
                 "ground_truth": "${data.ground_truth}"
                 "response": "${outputs.response}"
@@ -560,8 +560,8 @@ result = evaluate(
         "relevance": relevance_eval
     },
     evaluator_config={
-        "column_mapping": {
-            "default": {
+        "default": {
+            "column_mapping": {
                 "query": "${data.queries}"
                 "context": "${outputs.context}"
                 "response": "${outputs.response}"

@@ -45,7 +45,10 @@ To run this tutorial, you need:
     ```bash
     pip install -U llama-index-llms-azure-inference
     pip install -U llama-index-embeddings-azure-inference
-    ``` 
+    ```
+
+    > [!IMPORTANT]
+    > Using the [Azure AI model inference service](https://aka.ms/aiservices/inference) requires version `0.2.4` for `llama-index-llms-azure-inference` or `llama-index-embeddings-azure-inference`.
 
 ## Configure the environment
 
@@ -67,7 +70,7 @@ export AZURE_INFERENCE_ENDPOINT="<your-model-endpoint-goes-here>"
 export AZURE_INFERENCE_CREDENTIAL="<your-key-goes-here>"
 ```
 
-Once configured, create a client to connect to the endpoint. The parameter `model_name` in the constructor is not required for endpoints serving a single model, like serverless endpoints.
+Once configured, create a client to connect to the endpoint.
 
 ```python
 import os
@@ -80,7 +83,20 @@ llm = AzureAICompletionsModel(
 ```
 
 > [!TIP]
-> If your model is an OpenAI model deployed to Azure OpenAI service or AI services resource, configure the client as indicated at [Azure OpenAI models](#azure-openai-models).
+> If your model is an OpenAI model deployed to Azure OpenAI service or AI services resource, configure the client as indicated at [Azure OpenAI models and Azure AI model inference service](#azure-openai-models-and-azure-ai-model-infernece-service).
+
+If your endpoint is serving more than one model, like with the [Azure AI model inference service](../../ai-services/model-inference.md) or [GitHub Models](https://github.com/marketplace/models), you have to indicate `model_name` parameter:
+
+```python
+import os
+from llama_index.llms.azure_inference import AzureAICompletionsModel
+
+llm = AzureAICompletionsModel(
+    endpoint=os.environ["AZURE_INFERENCE_ENDPOINT"],
+    credential=os.environ["AZURE_INFERENCE_CREDENTIAL"],
+    model_name="mistral-large-2407",
+)
+```
 
 Alternatively, if your endpoint support Microsoft Entra ID, you can use the following code to create the client:
 
@@ -112,22 +128,23 @@ llm = AzureAICompletionsModel(
 )
 ```
 
-### Azure OpenAI models
+### Azure OpenAI models and Azure AI model infernece service
 
-If you are using Azure OpenAI models with key-based authentication, you need to pass the authentication key in the header `api-key`, which is the one expected in the Azure OpenAI service and in Azure AI Services. This configuration is not required if you are using Microsoft Entra ID (formerly known as Azure AD). The following example shows how to configure the client:
+If you are using Azure OpenAI models or [Azure AI model inference service](../../ai-services/model-inference.md), ensure you have at least version `0.2.4` of the LlamaIndex integration. Use `api_version` parameter in case you need to select a specific `api_version`. For the [Azure AI model inference service](../../ai-services/model-inference.md), you need to pass `model_name` parameter:
 
 ```python
-import os
 from llama_index.llms.azure_inference import AzureAICompletionsModel
 
 llm = AzureAICompletionsModel(
     endpoint=os.environ["AZURE_INFERENCE_ENDPOINT"],
-    credential="",
-    client_kwargs={"headers" : { "api-key": os.environ["AZURE_INFERENCE_CREDENTIAL"] } }
+    credential=os.environ["AZURE_INFERENCE_CREDENTIAL"],
+    model_name="gpt-4o",
+    api_version="2024-05-01-preview",
 )
 ```
 
-Notice that `credentials` is still being passed with an empty value since it's a required parameter.
+> [!TIP]
+> Using a wrong `api_version` or one not supported by the model results in a `ResourceNotFound` exception.
 
 ### Inference parameters
 

@@ -38,4 +38,9 @@ You can follow instructions [How to install the Azure CLI](/cli/azure/install-az
 After you install the Azure CLI, sign in using the ``az login`` command and sign-in using the browser:
 ```
 az login
+
+```
+Alternatively, you can log in manually via the browser with a device code.
+```
+az login --use-device-code
 ```
\ No newline at end of file