Merge pull request #4114 from MicrosoftDocs/main

4/14/2025 PM Publish

Author: Taojunshen

articles/ai-foundry/.openpublishing.redirection.ai-studio.json

@@ -704,8 +704,8 @@
         },
         {
             "source_path_from_root": "/articles/ai-studio/ai-services/how-to/connect-ai-services.md",
-            "redirect_url": "/azure/ai-foundry/ai-services/how-to/connect-ai-services",
-            "redirect_document_id": true
+            "redirect_url": "/azure/ai-services/connect-services-ai-foundry-portal",
+            "redirect_document_id": false
         },
         {
             "source_path_from_root": "/articles/ai-studio/ai-services/how-to/connect-azure-openai.md",
@@ -880,7 +880,7 @@
         },
         {
             "source_path_from_root": "/articles/ai-studio/how-to/models-foundation-azure-ai.md",
-            "redirect_url": "/azure/ai-studio/ai-services/how-to/connect-ai-services",
+            "redirect_url": "/azure/ai-services/connect-services-ai-foundry-portal",
             "redirect_document_id": true
         },
         {
@@ -960,17 +960,17 @@
         },
         {
             "source_path_from_root": "/articles/ai-studio/ai-services/get-started.md",
-            "redirect_url": "/azure/ai-studio/ai-services/how-to/connect-ai-services",
+            "redirect_url": "/azure/ai-services/connect-services-ai-foundry-portal",
             "redirect_document_id": false
         },
         {
             "source_path_from_root": "/articles/ai-studio/ai-services/where-to-use-ai-services.md",
-            "redirect_url": "/azure/ai-studio/ai-services/how-to/connect-ai-services",
+            "redirect_url": "/azure/ai-services/connect-services-ai-foundry-portal",
             "redirect_document_id": false
         },
         {
             "source_path_from_root": "/articles/ai-studio/ai-services/connect-ai-services.md",
-            "redirect_url": "/azure/ai-studio/ai-services/how-to/connect-ai-services",
+            "redirect_url": "/azure/ai-services/connect-services-ai-foundry-portal",
             "redirect_document_id": false
         },
         {
@@ -1132,6 +1132,11 @@
             "source_path_from_root": "/articles/ai-foundry/how-to/prompt-flow.md",
             "redirect_url": "/azure/ai-foundry/concepts/prompt-flow",
             "redirect_document_id": true
+        },
+        {
+          "source_path_from_root": "/articles/ai-foundry/ai-services/how-to/connect-ai-services.md",
+          "redirect_url": "/azure/ai-services/connect-services-ai-foundry-portal",
+          "redirect_document_id": false
         }
     ]
 }

articles/ai-foundry/how-to/develop/connections-add-sdk.md

@@ -73,7 +73,7 @@ ml_client.connections.create_or_update(wps_connection)
 
 ## Azure AI services
 
-The following example creates an Azure AI services connection. This example creates one connection for the AI services documented in the [Connect to Azure AI services](../../ai-services/how-to/connect-ai-services.md) article. The same connection also supports the Azure OpenAI service.
+The following example creates an Azure AI services connection. This example creates one connection for the AI services documented in the [Connect to Azure AI services](../../../ai-services/connect-services-ai-foundry-portal.md) article. The same connection also supports the Azure OpenAI service.
 
 ```python
 from azure.ai.ml.entities import AzureAIServicesConnection, ApiKeyConfiguration

articles/ai-foundry/how-to/model-catalog-overview.md

@@ -190,5 +190,5 @@ To set the public network access flag for the Azure AI Foundry hub:
 
 ## Related content
 
-* [Explore foundation models in Azure AI Foundry portal](../ai-services/how-to/connect-ai-services.md)
+* [Explore foundation models in Azure AI Foundry portal](../../ai-services/connect-services-ai-foundry-portal.md)
 * [Model deprecation and retirement in Azure AI model catalog](../concepts/model-lifecycle-retirement.md)

articles/ai-foundry/toc.yml

@@ -135,8 +135,8 @@ items:
   - name: Use Azure OpenAI Service in Azure AI Foundry portal
     href: ai-services/how-to/connect-azure-openai.md
   - name: Use Azure AI services in Azure AI Foundry portal
-    href: ai-services/how-to/connect-ai-services.md
-    displayName: cognitive,task
+    href: ../ai-services/connect-services-ai-foundry-portal.md?context=/azure/ai-foundry/context/context
+    displayName: cognitive,task,speech,vision,language,translator,document,intelligence,content,understanding,safety
   - name: What are Azure AI services?
     href: /azure/ai-services/what-are-ai-services
   - name: Azure OpenAI

articles/ai-services/agents/how-to/use-your-own-resources.md

@@ -24,11 +24,11 @@ Use this article if you want to use the Azure Agent Service with resources you a
 
 To use your own resources, you can edit the parameters in the provided deployment templates. To start, determine if you want to edit the [basic agent setup template](https://github.com/Azure-Samples/azureai-samples/tree/main/scenarios/Agents/setup/basic-agent-identity), or the [standard agent setup template](https://github.com/Azure-Samples/azureai-samples/tree/main/scenarios/Agents/setup/standard-agent).
 
-**Basic Setup**:  Agents use multitenant search and storage resources fully managed by Microsoft. You don't have visibility or control over these underlying Azure resources. You can only use your own AI services account with this option.
+**Basic Setup**:  Agents created in a basic project use multitenant search and storage resources fully managed by Microsoft. You don't have visibility or control over these underlying Azure resources. You can only use your own AI services account with this option.
 
-**Standard Setup**: Agents use customer-owned, single-tenant search and storage resources. With this setup, you have full control and visibility over these resources, but you incur costs based on your usage. You can use your own AI services account, storage account, and/or Azure AI Search resource with this option. 
+**Standard Setup**: Agents created in a standard project use customer-owned, single-tenant search and storage resources. With this setup, you have full control and visibility over these resources, but you incur costs based on your usage. You can use your own AI services account, Azure Storage account, Cosmos DB for NoSQL account and/or Azure AI Search resource with this option. 
 
-## Basic agent setup: use an existing AI Services/Azure OpenAI resource 
+## Basic agent setup: Use an existing AI Services/Azure OpenAI resource 
 
 Replace the parameter value for `aiServiceAccountResourceId` with the full arm resource ID of the AI Services or Azure OpenAI resource you want to use.
 
@@ -52,11 +52,12 @@ Replace the parameter value for `aiServiceAccountResourceId` with the full arm r
     If you want to use an existing Azure OpenAI resource, you will need to update the `aiServiceAccountResourceId` and the `aiServiceKind` parameters in the parameter file. The aiServiceKind parameter should be set to AzureOpenAI.
 
 
-## Standard agent setup: use an existing AI Services/Azure OpenAI, storage, and/or Azure AI Search resource 
+## Standard agent setup: Use an existing AI Services/Azure OpenAI, Azure Storage account, Azure Cosmos DB for NoSQL account, and/or Azure AI Search resource 
 
-Use an existing AI Search, storage account, and/or Azure AI Search resource by providing the full arm resource ID in the standard agent template file.
+Use an existing AI Services / Azure OpenAI, Azure Storage account, Azure Cosmos DB for NoSQL account and/or Azure AI Search resource by providing the full ARM resource ID in the standard agent template file.
+
+### Use an existing AI Services or Azure OpenAI resource
 
-Use an existing AI Services or Azure OpenAI resource:
 1. Follow the steps in basic agent setup to get the AI Services account resource ID.
 2. In the standard agent template file, replace the following placeholders:
     
@@ -66,7 +67,7 @@ Use an existing AI Services or Azure OpenAI resource:
     [Azure OpenAI Only] aiServiceKind: AzureOpenAI
     ```
 
-### Use an existing storage account
+### Use an existing Azure Storage account for file storage
 
 1. To get your storage account resource ID, sign in to the Azure CLI and select the subscription with your storage account: 
     
@@ -82,6 +83,25 @@ Use an existing AI Services or Azure OpenAI resource:
     aiStorageAccountResourceId:/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.Storage/storageAccounts/{storageAccountName}
     ```
 
+### Use an existing Azure Cosmos DB for NoSQL account for thread storage
+
+1. To get your Azure Cosmos DB account resource ID, sign in to the Azure CLI and select the subscription with your account: 
+    
+    ```console
+    az login
+    ``` 
+    
+2. Then run the command:
+
+    ```console
+    az cosmosdb show --resource-group  <your-resource-group> --name <your-comosdb-account>  --query "id" --output tsv
+    ```
+    
+     The output is the `cosmosDBResourceId` you need to use in the template.
+3. In the standard agent template file, replace the following placeholders:
+    
+    `cosmosDBResourceId:/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.DocumentDB/databaseAccounts/{cosmosDbAccountName}`
+    
 ### Use an existing Azure AI Search resource
 
 1. To get your Azure AI Search resource ID, sign into Azure CLI and select the subscription with your search resource: 

articles/ai-services/agents/includes/bicep-setup.md

@@ -40,7 +40,7 @@ https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.github
 | Description and Autodeploy  |  Diagram (click to zoom in) |
 | -----------------------------------------------| -----------------------|
 | Deploy a basic agent setup that uses Managed Identity for authentication. Resources for the AI hub, AI project, storage account, and AI Services are created for you. <br><br> The AI Services account is connected to your project and hub, and a gpt-4o-mini model is deployed in the eastus region. A Microsoft-managed key vault is used by default. <br><br> [![Deploy To Azure](https://aka.ms/deploytoazurebutton)](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2FAzure-Samples%2Fazureai-samples%2Fmain%2Fscenarios%2FAgents%2Fsetup%2Fbasic-agent-identity%2Fazuredeploy.json) |  :::image type="content" source="../media/quickstart/basic-agent-setup-resources.png" alt-text="An architecture diagram for basic agent setup." lightbox="../media/quickstart/basic-agent-setup-resources.png"::: | 
-| Deploy a standard agent setup that uses Managed Identity for authentication. <br><br> Resources for the AI hub, AI project, key vault, storage account, AI Services, and AI Search are created for you. <br><br>The AI Services, AI Search, key vault, and storage account are connected to your project and hub. A gpt-4o-mini model is deployed in eastus region. <br><br> [![Deploy To Azure](https://aka.ms/deploytoazurebutton)](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2FAzure-Samples%2Fazureai-samples%2Fmain%2Fscenarios%2FAgents%2Fsetup%2Fstandard-agent%2Fazuredeploy.json) | :::image type="content" source="../media/quickstart/standard-agent-setup-resources.png" alt-text="An architecture diagram for standard agent setup." lightbox="../media/quickstart/standard-agent-setup-resources.png"::: |
+| Deploy a standard agent setup that uses Managed Identity for authentication. <br><br> Resources for the AI hub, AI project, key vault, storage account, AI Services, and AI Search are created for you. <br><br>The AI Services, AI Search, key vault, and storage account are connected to your project and hub. A gpt-4o-mini model is deployed in eastus region. <br><br> [![Deploy To Azure](https://aka.ms/deploytoazurebutton)](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2FAzure-Samples%2Fazureai-samples%2Fmain%2Fscenarios%2FAgents%2Fsetup%2Fstandard-agent-with-threadstorage%2Fazuredeploy.json) | :::image type="content" source="../media/quickstart/standard-agent-setup-resources.png" alt-text="An architecture diagram for standard agent setup." lightbox="../media/quickstart/standard-agent-setup-resources.png"::: |
 
 
 ### [Optional] Model selection in autodeploy template
@@ -50,9 +50,9 @@ By default, the deployment template is configured with the following values:
 
 | Model Parameter  | Default Value  |
 |------------------|----------------|
-| modelName        | gpt-4o-mini    |
+| modelName        | gpt-4o         |
 | modelFormat      | OpenAI (for Azure OpenAI) |
-| modelVersion     | 2024-07-18     |
+| modelVersion     | 2024-11-20     |
 | modelSkuName     | GlobalStandard |
 | modelLocation    | eastus         |
 
@@ -88,4 +88,4 @@ Resources for the AI hub, AI project, and AI Services are created for you. A sto
 :::image type="content" source="../media/quickstart/standard-agent-setup-resources.png" alt-text="An architecture diagram for standard agent setup." lightbox="../media/quickstart/standard-agent-setup-resources.png":::
 
 Resources for the AI hub, AI project, key vault, storage account, AI Services, and AI Search are created for you. The AI Services, AI Search, key vault, and storage account are connected to your project and hub. A gpt-4o-mini model is deployed in eastus region using the Azure OpenAI endpoint for your resource.
--->
+-->

articles/ai-services/agents/includes/portal-agent-limitation.md

@@ -4,8 +4,9 @@ author: aahill
 ms.author: aahi
 ms.service: azure-ai-agent-service
 ms.topic: include
-ms.date: 02/05/2025
+ms.date: 04/13/2025
 ---
 
 > [!NOTE]
-> You can use the following automated bicep templates to perform either a standard or basic agent. You can also create a basic agent using the [Azure AI Foundry portal](../quickstart.md?pivots=ai-foundry). Azure AI Foundry currently doesn't support the standard agent setup.
+> The Standard Agent Setup now supports **Bring your own (BYO) Thread Storage using an Azure Cosmos DB for NoSQL account**. This feature lets you store all messages and conversation history in your own Azure Cosmos DB for NoSQL account.
+> You can use the following automated bicep templates to deploy either a Standard or Basic agent project. You can also create a basic project using the [Azure AI Foundry portal](../quickstart.md?pivots=ai-foundry). The Azure AI Foundry portal currently doesn't support creating a Standard project.

articles/ai-services/agents/whats-new.md

@@ -15,6 +15,10 @@ ms.custom: azure-ai-agents
 
 This article provides a summary of the latest releases and major documentation updates for Azure AI Agent Service.
 
+## April 2025
+### BYO thread storage
+The Standard Agent Setup now supports **Bring Your Own (BYO) thread storage using an Azure Cosmos DB for NoSQL account**. This feature ensures all thread messages and conversation history are stored in your own resources. See the [Quickstart](./quickstart.md) for more information on how to deploy a Standard agent project.
+
 ## March 2025
 
 ### Microsoft Fabric tool