Merge pull request #5092 from MicrosoftDocs/main

5/20/2025 PM Publish

Author: Taojunshen

.openpublishing.redirection.json

@@ -120,6 +120,11 @@
       "redirect_url": "/azure/ai-services/agents/overview",
       "redirect_document_id": false
     },
+    {
+      "source_path_from_root": "/articles/ai-services/openai/assistants-quickstart.md",
+      "redirect_url": "/azure/ai-services/agents/quickstart",
+      "redirect_document_id": true
+    },
     {
       "source_path_from_root": "/articles/ai-services/openai/how-to/use-your-data-securely.md",
       "redirect_url": "/azure/ai-services/openai/how-to/on-your-data-configuration",
@@ -284,6 +289,11 @@
       "source_path": "articles/ai-services/index.yml",
       "redirect_url": "/azure/ai-foundry",
       "redirect_document_id": false
+    },
+    {
+      "source_path_from_root": "/articles/ai-services/speech-service/text-to-speech-avatar/custom-avatar-endpoint.md",
+      "redirect_url": "/azure/ai-services/speech-service/custom-avatar-create",
+      "redirect_document_id": false
     }
   ]
 }

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

@@ -59,7 +59,7 @@ Here's a table of some of the available connection types in Azure AI Foundry por
 | API key                       |         |                                        | API Key connections handle authentication to your specified target on an individual basis. |
 | Custom                        |         |                                        | Custom connections allow you to securely store and access keys while storing related properties, such as targets and versions. Custom connections are useful when you have many targets or cases where you wouldn't need a credential to access. LangChain scenarios are a good example where you would use custom service connections. Custom connections don't manage authentication, so you have to manage authentication on your own. |
 | Serverless Model              |    ✓    |                                        | Serverless Model connections allow you to serverless API deployment.                                                                                                                     |
-| Azure Databricks              |    ✓    |                                        | Azure Databricks connector allows you to connect your Azure AI Foundry Agents to Azure Databricks to access workflows and Genie Spaces during runtime. It supports three connection types - __Jobs__, __Genie__, and __Other__. You can pick the Job or Genie space you want associated with this connection while setting up the connection in the Foundry UI. You can also use the Other connection type and allow your agent to access workspace operations in Azure Databricks. Authentication is handled through Microsoft Entra ID for users or service principals. |
+| Azure Databricks              |    ✓    |                                        | Azure Databricks connector allows you to connect your Azure AI Foundry Agents to Azure Databricks to access workflows and Genie Spaces during runtime. It supports three connection types - __Jobs__, __Genie__, and __Other__. You can pick the Job or Genie space you want associated with this connection while setting up the connection in the Foundry UI. You can also use the Other connection type and allow your agent to access workspace operations in Azure Databricks. Authentication is handled through Microsoft Entra ID for users or service principals. For examples of using this connector, see [Jobs](https://github.com/Azure-Samples/AI-Foundry-Connections/blob/main/src/samples/python/sample_agent_adb_job.py) and [Genie](https://github.com/Azure-Samples/AI-Foundry-Connections/blob/main/src/samples/python/sample_agent_adb_genie.py). |
 
 ## Agent knowledge tool connections
 

articles/ai-foundry/how-to/develop/get-started-projects-vs-code.md

@@ -1,18 +1,18 @@
 ---
 title: Work with the Azure AI Foundry for Visual Studio Code extension
 titleSuffix: Azure AI Foundry
-description: Use this article to learn how to deploy Large Language Models using Azure AI Foundry capabilities directly in VS Code.
+description: Use this article to learn how to create projects and deploy Large Language Models using Azure AI Foundry capabilities directly in VS Code.
 manager: mcleans
 ms.service: azure-ai-foundry
 content_well_notification: 
   - AI-contribution
 ai-usage: ai-assisted
 ms.topic: how-to
-ms.date: 05/07/2025
+ms.date: 05/20/2025
 ms.reviewer: erichen
 ms.author: johalexander
 author: ms-johnalex
-# customer intent: As an AI app developer, I want to learn how to use the Azure AI Foundry for Visual Studio Code extension so that I can deploy Large Language Models using Azure AI Foundry capabilities directly in VS Code.
+# customer intent: As an AI app developer, I want to learn how to use the Azure AI Foundry for Visual Studio Code extension so that I can create projects and deploy Large Language Models using Azure AI Foundry capabilities directly in VS Code.
 ---
 
 # Work with the Azure AI Foundry for Visual Studio Code extension (Preview)
@@ -42,8 +42,6 @@ Before using the Azure AI Foundry for Visual Studio Code extension, you must:
 
 - Download, install, and configure Visual Studio Code. More information: [Download Visual Studio Code](https://code.visualstudio.com/Download)
 
-- [An existing Azure AI Foundry project](/azure/ai-foundry/how-to/create-projects?tabs=ai-studio). The extension interacts with Azure AI Foundry at the project level.
-
 - Your subscription needs to be below your [quota limit](../quota.md) to [deploy a new model in this quickstart](#deploy-a-model-from-the-model-catalog). Otherwise you already need to have a [deployed chat model](../deploy-models-openai.md).
 
 ## Installation
@@ -110,13 +108,44 @@ The Azure AI Foundry Extension opens in its own view, with the Azure AI Foundry
     - **Model Playground**: The link to the model playground for interacting with your deployed models in your Azure AI Foundry project.
     - **Agent Playground**: The link to the agent playground for interacting with your deployed agents in your Azure AI Foundry project.
 
-- **Help and Feedback**: This section contains links to the Azure AI Foundry documentation, feedback, and support. It contains the following subsections:
+- **Help and Feedback**: This section contains links to the Azure AI Foundry documentation, feedback, support, and the Microsoft Privacy Statement. It contains the following subsections:
     - **Documentation**: The link to the Azure AI Foundry Extension documentation.
     - **GitHub**: The link to the Azure AI Foundry extension GitHub repository.
+    - **Microsoft Privacy Statement**: The link to the Microsoft Privacy Statement.
 
 >[!NOTE]
 > To learn more about working with Agents and Threads in the Azure AI Foundry Extension, see the [Work with Azure AI Foundry Agent Service in Visual Studio Code](./vs-code-agents.md) article. 
 
+## Create a project
+
+You can create a new Azure AI Foundry project from the Azure AI Foundry Extension view with the following steps:
+
+1. Select the **plus** icon next to **Resources** in the **Resources** section of the Azure AI Foundry Extension view.
+
+1. In the top center, enter the Azure AI Foundry Project name to use in the **Enter project name** textbox and press Enter.
+
+    :::image type="content" source="../../media/how-to/get-started-projects-vs-code/enter-project-name.png" alt-text="Screenshot of the Enter project name textbox." lightbox="../../media/how-to/get-started-projects-vs-code/enter-project-name.png":::
+
+You can either create a new resource group or select an existing one.
+- To create a new resource group:
+    1. In the top center, select **Create new resource group** and press Enter.
+
+    :::image type="content" source="../../media/how-to/get-started-projects-vs-code/select-resource-group.png" alt-text="Screenshot of the Choose resource group dropdown with the Create new resource group item highlighted." lightbox="../../media/how-to/get-started-projects-vs-code/select-resource-group.png":::  
+    
+    1. In the top center, enter the Azure Resource Group name to use in the **Enter new resource group** textbox and press Enter.
+
+    1. In the top center, select the location you want to use from the list of available locations and press Enter.
+
+- To use an existing resource group:
+    1. In the top center, select the resource group you want to use from the list of available resource groups and press Enter.
+
+After project deployment, a popup appears with the message **Project deployed successfully**.
+
+:::image type="content" source="../../media/how-to/get-started-projects-vs-code/project-deployed.png" alt-text="A screenshot of the Project deployed successfully popup with the Deploy a model button highlighted." lightbox="../../media/how-to/get-started-projects-vs-code/project-deployed.png":::
+
+To deploy a model to the newly created project, select the **Deploy a model** button in the popup.
+This action opens the **Model Catalog** page in the Azure AI Foundry Extension view to select the desired model to [deploy.](#deploy-a-model-from-the-model-catalog) 
+
 ### The default Azure AI Foundry Project
 
 When you open a project in the Azure AI Foundry Extension, that project is set as your default project. 
@@ -131,7 +160,6 @@ Your selected project will now display **Default** after the project name.
 
 :::image type="content" source="../../media/how-to/get-started-projects-vs-code/default-project.png" alt-text="A screenshot of the designated default project." lightbox="../../media/how-to/get-started-projects-vs-code/default-project.png"::: 
 
-
 ## Work with models
 
 The Azure AI Foundry for Visual Studio Code extension enables you to create, interact with, and deploy Large Language Models from within Visual Studio Code.
@@ -187,7 +215,7 @@ Deploy a selected model in the model catalog using the following steps:
 
 1. In the top center, select the AI service to use in the **Choose an AI service** dropdown and press Enter.
 
-    :::image type="content" source="../../media/how-to/get-started-projects-vs-code/choose-ai-service.png" alt-text="Screenshot of the Chosen AI service dropdown." lightbox="../../media/how-to/get-started-projects-vs-code/choose-ai-service.png":::
+    :::image type="content" source="../../media/how-to/get-started-projects-vs-code/choose-ai-service.png" alt-text="Screenshot of the Choose an AI service dropdown." lightbox="../../media/how-to/get-started-projects-vs-code/choose-ai-service.png":::
 
 1. In the top center, select the model version to use in the **Choose model version** dropdown and press Enter.
 

articles/ai-foundry/media/how-to/get-started-projects-vs-code/enter-project-name.png

@@ -264,14 +264,20 @@ items:
       href: ../ai-services/speech-service/get-started-speech-to-text.md?context=/azure/ai-foundry/context/context
     - name: Fast transcription
       href: ../ai-services/speech-service/fast-transcription-create.md?context=/azure/ai-foundry/context/context
+    - name: Fine-tune your speech model
+      items:
+      - name: Custom speech fine-tuning
+        href: ../ai-services/speech-service/how-to-custom-speech-create-project.md?context=/azure/ai-foundry/context/context
+      - name: Custom voice fine-tuning
+        href: ../ai-services/speech-service/professional-voice-create-project.md?context=/azure/ai-foundry/context/context
+      - name: Custom avatar fine-tuning
+        href: ../ai-services/speech-service/text-to-speech-avatar/custom-avatar-create.md?context=/azure/ai-foundry/context/context
     - name: Pronunciation assessment
       href: ../ai-services/speech-service/pronunciation-assessment-tool.md?context=/azure/ai-foundry/context/context
     - name: Speech translation
       href: ../ai-services/speech-service/get-started-speech-translation.md?context=/azure/ai-foundry/context/context
     - name: Hear and speak with chat in the playground
       href: quickstarts/hear-speak-playground.md
-    - name: Custom speech fine-tuning
-      href: ../ai-services/speech-service/how-to-custom-speech-create-project.md?context=/azure/ai-foundry/context/context
   - name:  Translator
     items:
     - name: What is Azure AI Translator?

articles/ai-foundry/media/how-to/get-started-projects-vs-code/initial-view.png

@@ -6,7 +6,7 @@ services: azure-ai-agent-service
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 01/30/2025
+ms.date: 05/20/2025
 author: aahill
 ms.author: aahi
 ms.custom: azure-ai-agents
@@ -15,7 +15,7 @@ zone_pivot_groups: selection-azure-functions-samples
 
 # How to use Azure Functions with Azure AI Agents 
 
-Azure AI Agents supports function calling, which allows you to describe the structure of functions to an Assistant and then return the functions that need to be called along with their arguments. These examples show how to use Azure Functions to process the function calls through queue messages in Azure Storage. You can see a complete working sample on [GitHub](https://github.com/Azure-Samples/azure-functions-ai-services-agent-python)
+Azure AI Agents supports function calling, which allows you to describe the structure of functions to an Assistant and then return the functions that need to be called along with their arguments. These examples show how to use Azure Functions to process the function calls through queue messages in Azure Storage.
 
 
 ## Prerequisites
@@ -25,6 +25,8 @@ Azure AI Agents supports function calling, which allows you to describe the stru
 
 ::: zone pivot="python"
 
+> [!TIP]
+> You can find a complete working sample on [GitHub](https://github.com/Azure-Samples/azure-functions-ai-services-agent-python)
 
 ## Define a function for your agent to call
 
@@ -312,6 +314,9 @@ For any issues with the TypeScript code, create an issue on the [sample code rep
 -->
 ::: zone pivot="csharp"
 
+> [!TIP]
+> You can find a complete working sample on [GitHub](https://github.com/Azure-Samples/azure-functions-ai-services-agent-dotnet)
+
 ## Prerequisites for .NET Azure Function Sample
 To make a function call, we need to create and deploy the Azure function. In the code snippet, we have an example of function on C# which can be used by the earlier code.
 

articles/ai-foundry/media/how-to/get-started-projects-vs-code/project-deployed.png

@@ -166,11 +166,17 @@ PersistentAgentsClient agentClient = new(projectEndpoint, new DefaultAzureCreden
 To make the Grounding with Bing search tool available to your agent, use a connection to initialize the tool and attach it to the agent. You can find your connection in the **connected resources** section of your project in the [Azure AI Foundry portal](https://ai.azure.com/).
 
 ```csharp
+BingGroundingSearchConfiguration searchConfig = new BingGroundingSearchConfiguration(bingConnectionId)
+{ 
+    Count = 5,
+    Freshness = "Week"
+};
+
 // Create the BingGroundingToolDefinition object used when creating the agent
 BingGroundingToolDefinition bingGroundingTool = new BingGroundingToolDefinition(
     new BingGroundingSearchToolParameters(
         [
-            new BingGroundingSearchConfiguration(bingConnectionId)
+            searchConfig
         ]
     )
 );
@@ -498,4 +504,4 @@ curl --request GET \
 
 ## Next steps
 
-[See the full sample for Grounding with Bing Search.](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-projects/samples/agents/sample_agents_bing_grounding.py)
+[See the full sample for Grounding with Bing Search.](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/samples/agents_tools/sample_agents_bing_grounding.py)