Merge pull request #6520 from MicrosoftDocs/main

Auto Publish – main to live - 2025-08-11 22:05 UTC

Author: learn-build-service-prod[bot]

articles/ai-foundry/agents/concepts/model-region-support.md

@@ -25,7 +25,7 @@ All deployments can perform the exact same inference operations, however the bil
 Azure AI Foundry Agent Service supports the following Azure OpenAI models in the listed regions.
 
 > [!NOTE]
-> * [Hub based projects](../../what-is-azure-ai-foundry.md#project-types) are limited to the following models: gpt-4o, gpt-4o-mini, gpt-4, gpt-35-turbo
+> * [Hub-based projects](../../what-is-azure-ai-foundry.md#project-types) are limited to the following models: gpt-4o, gpt-4o-mini, gpt-4, gpt-35-turbo
 > * For information on class A subnet support, see the setup guide on [GitHub](https://github.com/azure-ai-foundry/foundry-samples/tree/main/samples/microsoft/infrastructure-setup/15-private-network-standard-agent-setup).
 > * The [file search tool](../how-to/tools/file-search.md) is currently unavailable in the following regions:
 >     * Italy north

articles/ai-foundry/agents/how-to/tools/code-interpreter-samples.md

@@ -5,7 +5,7 @@ description: Find code samples to enable code interpreter for Azure AI Agents.
 author: aahill
 ms.author: aahi
 manager: nitinme
-ms.date: 06/30/2025
+ms.date: 08/11/2025
 ms.service: azure-ai-agent-service
 ms.topic: how-to
 ms.custom:
@@ -146,161 +146,112 @@ This ensures proper resource management and prevents unnecessary resource consum
 
 :::zone pivot="csharp" 
 
-## Create a project client
+## Create a client and agent
 
-Create a client object, which will contain the project endpoint for connecting to your AI project and other resources.
+First, set up the configuration using `appsettings.json`, create a `PersistentAgentsClient`, and then create a `PersistentAgent` with the Code Interpreter tool enabled.
 
 ```csharp
 using Azure;
 using Azure.AI.Agents.Persistent;
 using Azure.Identity;
+using Microsoft.Extensions.Configuration;
+using System.Diagnostics;
 
-var projectEndpoint = System.Environment.GetEnvironmentVariable("ProjectEndpoint");
-var projectEndpoint = System.Environment.GetEnvironmentVariable("ModelDeploymentName");
-var projectEndpoint = System.Environment.GetEnvironmentVariable("BingConnectionId");
+IConfigurationRoot configuration = new ConfigurationBuilder()
+    .SetBasePath(AppContext.BaseDirectory)
+    .AddJsonFile("appsettings.json", optional: false, reloadOnChange: true)
+    .Build();
 
-// Create the Agent Client
-PersistentAgentsClient agentClient = new(projectEndpoint, new DefaultAzureCredential());
-```
-
-## Create an Agent with the Grounding with Bing search tool enabled
-
-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/?cid=learnDocs).
-
-```csharp
+var projectEndpoint = configuration["ProjectEndpoint"];
+var modelDeploymentName = configuration["ModelDeploymentName"];
 
-BingGroundingToolDefinition bingGroundingTool = new(
-    new BingGroundingSearchToolParameters(
-        [new BingGroundingSearchConfiguration(bingConnectionId)]
-    )
-);
+PersistentAgentsClient client = new(projectEndpoint, new DefaultAzureCredential());
 
-// Create the Agent
-PersistentAgent agent = agentClient.Administration.CreateAgent(
+PersistentAgent agent = client.Administration.CreateAgent(
     model: modelDeploymentName,
-    name: "my-agent",
-    instructions: "Use the bing grounding tool to answer questions.",
-    tools: [bingGroundingTool]
+    name: "My Friendly Test Agent",
+    instructions: "You politely help with math questions. Use the code interpreter tool when asked to visualize numbers.",
+    tools: [new CodeInterpreterToolDefinition()]
 );
 ```
 
-## Create a thread and run
+## Create a thread and add a message
+
+Next, create a `PersistentAgentThread` for the conversation and add the initial user message.
 
 ```csharp
-PersistentAgentThread thread = agentClient.Threads.CreateThread();
+PersistentAgentThread thread = client.Threads.CreateThread();
 
-// Create message and run the agent
-PersistentThreadMessage message = agentClient.Messages.CreateMessage(
+client.Messages.CreateMessage(
     thread.Id,
     MessageRole.User,
-    "How does wikipedia explain Euler's Identity?");
-ThreadRun run = agentClient.Runs.CreateRun(thread, agent);
-
+    "Hi, Agent! Draw a graph for a line with a slope of 4 and y-intercept of 9.");
 ```
 
-## Wait for the agent to complete and print the output
+## Create and monitor a run
 
-First, wait for the agent to complete the run by polling its status. Observe that the model uses the Grounding with Bing Search tool to provide a response to the user's question.
+Then, create a `ThreadRun` for the thread and agent. Poll the run's status until it completes or requires action.
 
 ```csharp
-// Wait for the agent to finish running
+ThreadRun run = client.Runs.CreateRun(
+    thread.Id,
+    agent.Id,
+    additionalInstructions: "Please address the user as Jane Doe. The user has a premium account.");
+
 do
 {
     Thread.Sleep(TimeSpan.FromMilliseconds(500));
-    run = agentClient.Runs.GetRun(thread.Id, run.Id);
+    run = client.Runs.GetRun(thread.Id, run.Id);
 }
 while (run.Status == RunStatus.Queued
-    || run.Status == RunStatus.InProgress);
-
-// Confirm that the run completed successfully
-if (run.Status != RunStatus.Completed)
-{
-    throw new Exception("Run did not complete successfully, error: " + run.LastError?.Message);
-}
+    || run.Status == RunStatus.InProgress
+    || run.Status == RunStatus.RequiresAction);
 ```
 
-Then, retrieve and process the messages from the completed run.
+## Process the results and handle files
+
+Once the run is finished, retrieve all messages from the thread. Iterate through the messages to display text content and handle any generated image files by saving them locally and opening them.
 
 ```csharp
-// Retrieve all messages from the agent client
-Pageable<PersistentThreadMessage> messages = agentClient.Messages.GetMessages(
+Pageable<PersistentThreadMessage> messages = client.Messages.GetMessages(
     threadId: thread.Id,
-    order: ListSortOrder.Ascending
-);
+    order: ListSortOrder.Ascending);
 
-// Process messages in order
 foreach (PersistentThreadMessage threadMessage in messages)
 {
-    Console.Write($"{threadMessage.CreatedAt:yyyy-MM-dd HH:mm:ss} - {threadMessage.Role,10}: ");
-    foreach (MessageContent contentItem in threadMessage.ContentItems)
+    foreach (MessageContent content in threadMessage.ContentItems)
     {
-        if (contentItem is MessageTextContent textItem)
+        switch (content)
         {
-            string response = textItem.Text;
-
-            // If we have Text URL citation annotations, reformat the response to show title & URL for citations
-            if (textItem.Annotations != null)
-            {
-                foreach (MessageTextAnnotation annotation in textItem.Annotations)
+            case MessageTextContent textItem:
+                Console.WriteLine($"[{threadMessage.Role}]: {textItem.Text}");
+                break;
+            case MessageImageFileContent imageFileContent:
+                Console.WriteLine($"[{threadMessage.Role}]: Image content file ID = {imageFileContent.FileId}");
+                BinaryData imageContent = client.Files.GetFileContent(imageFileContent.FileId);
+                string tempFilePath = Path.Combine(AppContext.BaseDirectory, $"{Guid.NewGuid()}.png");
+                File.WriteAllBytes(tempFilePath, imageContent.ToArray());
+                client.Files.DeleteFile(imageFileContent.FileId);
+
+                ProcessStartInfo psi = new()
                 {
-                    if (annotation is MessageTextUriCitationAnnotation urlAnnotation)
-                    {
-                        response = response.Replace(urlAnnotation.Text, $" [{urlAnnotation.UriCitation.Title}]({urlAnnotation.UriCitation.Uri})");
-                    }
-                }
-            }
-            Console.Write($"Agent response: {response}");
-        }
-        else if (contentItem is MessageImageFileContent imageFileItem)
-        {
-            Console.Write($"<image from ID: {imageFileItem.FileId}");
+                    FileName = tempFilePath,
+                    UseShellExecute = true
+                };
+                Process.Start(psi);
+                break;
         }
-        Console.WriteLine();
     }
 }
-
-```
-
-## Optionally output the run steps used by the agent
-
-```csharp
-// Retrieve the run steps used by the agent and print those to the console
-Console.WriteLine("Run Steps used by Agent:");
-Pageable<RunStep> runSteps = agentClient.Runs.GetRunSteps(run);
-
-foreach (var step in runSteps)
-{
-    Console.WriteLine($"Step ID: {step.Id}, Total Tokens: {step.Usage.TotalTokens}, Status: {step.Status}, Type: {step.Type}");
-
-    if (step.StepDetails is RunStepMessageCreationDetails messageCreationDetails)
-    {
-        Console.WriteLine($"   Message Creation Id: {messageCreationDetails.MessageCreation.MessageId}");
-    }
-    else if (step.StepDetails is RunStepToolCallDetails toolCallDetails)
-    {
-        // We know this agent only has the Bing Grounding tool, so we can cast it directly
-        foreach (RunStepBingGroundingToolCall toolCall in toolCallDetails.ToolCalls)
-        {
-            Console.WriteLine($"   Tool Call Details: {toolCall.GetType()}");
-
-            foreach (var result in toolCall.BingGrounding)
-            {
-                Console.WriteLine($"      {result.Key}: {result.Value}");
-            }
-        }
-    }
-}
-
 ```
 
 ## Clean up resources
 
-Clean up the resources from this sample.
+Finally, delete the thread and the agent to clean up the resources created in this sample.
 
 ```csharp
-// Delete thread and agent
-agentClient.Threads.DeleteThread(threadId: thread.Id);
-agentClient.Administration.DeleteAgent(agentId: agent.Id);
+    client.Threads.DeleteThread(threadId: thread.Id);
+    client.Administration.DeleteAgent(agentId: agent.Id);
 ```
 
 :::zone-end
@@ -566,7 +517,6 @@ curl --request GET \
 
 :::zone-end
 
-
 :::zone pivot="java" 
 
 ## Download an example file

articles/ai-foundry/concepts/ai-resources.md

@@ -5,7 +5,7 @@ description: This article introduces concepts about Azure AI Foundry hubs for yo
 ms.author: sgilley
 author: sdgilley
 ms.reviewer: deeikele
-ms.date: 04/28/2025
+ms.date: 08/11/2025
 ms.service: azure-ai-foundry
 ms.topic: concept-article
 ms.custom:
@@ -20,9 +20,9 @@ ms.custom:
 # Hub resources overview
 
 > [!NOTE]
-> You must use a **[!INCLUDE [hub](../includes/hub-project-name.md)]** for the features mentioned in this article. A **[!INCLUDE [fdp](../includes/fdp-project-name.md)]** is not supported. For more information, see [Project types](../what-is-azure-ai-foundry.md#which-type-of-project-do-i-need).
+> You must use a **[!INCLUDE [hub](../includes/hub-project-name.md)]** for the features mentioned in this article. A **[!INCLUDE [fdp](../includes/fdp-project-name.md)]** isn't supported. For more information, see [Project types](../what-is-azure-ai-foundry.md#which-type-of-project-do-i-need).
 
-Azure AI Hub is a resource type that is used in combination with Azure AI Foundry resource type, and is only required for selected use cases. Hub resources provides access to open-source model hosting and finetuning capabilities, as well as Azure Machine Learning capabilities, next to capabilities supported by its associated AI Foundry resource.
+Azure AI Hub is a resource type that is used in combination with Azure AI Foundry resource type, and is only required for selected use cases. Hub resources provide access to open-source model hosting and fine-tuning capabilities, as well as Azure Machine Learning capabilities, next to capabilities supported by its associated AI Foundry resource.
 
 When you create an AI Hub, an Azure AI Foundry resource is automatically provisioned. Hub resources can be used in [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs) and [Azure Machine Learning studio](https://ml.azure.com).
 
@@ -36,7 +36,7 @@ Hubs group one or more projects together with common settings including data acc
 
 ## Create a hub-based project
 
-To start developing, [create a [!INCLUDE [hub-project-name](../includes/hub-project-name.md)]](../how-to/create-projects.md?pivots=hub-project). Hub-projects can be accessed in [AI Foundry Portal](https://ai.azure.com/?cid=learnDocs) to build with generative AI tools, and [ML Studio](https://ml.azure.com) to build with tools designed for custom machine learning model training.
+To start developing, [create a [!INCLUDE [hub-project-name](../includes/hub-project-name.md)]](../how-to/create-projects.md?pivots=hub-project). Hub-based projects can be accessed in [AI Foundry Portal](https://ai.azure.com/?cid=learnDocs) to build with generative AI tools, and [ML Studio](https://ml.azure.com) to build with tools designed for custom machine learning model training.
 
 ## Project concepts
 
@@ -61,7 +61,7 @@ Projects also have specific settings that only hold for that project:
 
 ## Share configurations across projects using hub
 
-A hub shares configurations for a group of projects. As a team lead, consider creating a hub for use cases that share the same security configurations or business domain to avoid repetitive setup and let developers create their own project against the pre-configured environment.
+A hub shares configurations for a group of projects. All projects in the hub share the same security configurations or business domain.
 
 Shared configurations managed on the hub include:
 * **Security** including public network access, customer-managed key encryption, and identity controls. Security settings configured on the hub automatically pass down to each project. A managed virtual network is shared between all projects that share the same hub.
@@ -74,7 +74,7 @@ Shared configurations managed on the hub include:
 
 Hubs let you manage connections to existing Azure OpenAI or Azure AI Foundry resources, so you can use their models and selected customization capabilities in hub-based projects. 
 
-After a connection is created, model deployments are accessible via playground experiences. When you use Finetuning experiences in a hub-based project, your finetuning jobs are implicitly executed on the connected AI Foundry resource (default project context).
+After a connection is created, model deployments are accessible via playground experiences. When you use Fine-tuning experiences in a hub-based project, your fine-tuning jobs are implicitly executed on the connected AI Foundry resource (default project context).
 
 ## Storage and Key Vault dependent resources
 

articles/ai-foundry/concepts/fine-tuning-overview.md

@@ -96,11 +96,11 @@ To find steps to fine-tuning a model in AI Foundry, see [Fine-tune Models in AI
 
 Now that you know when to use fine-tuning for your use case, you can go to Azure AI Foundry to find models available to fine-tune.
 
-**To fine-tune an AI Foundry model using Serverless** you must have a hub/project in the region where the model is available for fine tuning. See [Region availability for models in serverless API deployment](../how-to/deploy-models-serverless-availability.md) for detailed information on model and region availability, and [How to Create a Hub based project](../how-to/create-projects.md) to create your project.
+**To fine-tune an AI Foundry model using Serverless** you must have a hub/project in the region where the model is available for fine tuning. See [Region availability for models in serverless API deployment](../how-to/deploy-models-serverless-availability.md) for detailed information on model and region availability, and [How to Create a Hub-based project](../how-to/create-projects.md) to create your project.
 
 **To fine-tune an OpenAI model** you can use an Azure OpenAI Resource, a Foundry resource or default project, or a hub/project. GPT 4.1, 4.1-mini and 4.1-nano are available in all regions with Global Training. For regional availability, see [Regional Availability and Limits for Azure OpenAI Fine Tuning](../openai/concepts/models.md). See [Create a project for Azure AI Foundry](../how-to/create-projects.md) for instructions on creating a new project.
 
-**To fine-tune a model using Managed Compute** you must have a hub/project and available VM quota for training and inferencing. See [Fine-tune models using managed compute (preview)](../how-to/fine-tune-managed-compute.md) for more details on how to use managed compute fine tuning, and [How to Create a Hub based project](../how-to/create-projects.md) to create your project.
+**To fine-tune a model using Managed Compute** you must have a hub/project and available VM quota for training and inferencing. See [Fine-tune models using managed compute (preview)](../how-to/fine-tune-managed-compute.md) for more details on how to use managed compute fine tuning, and [How to Create a Hub-based project](../how-to/create-projects.md) to create your project.
 
 
 ## Related content

articles/ai-foundry/concepts/management-center.md

@@ -38,7 +38,7 @@ Use the management center to create and configure [!INCLUDE [FDP](../includes/fd
 For more information, see [Create a [!INCLUDE [fdp-project-name](../includes/fdp-project-name.md)]](../how-to/create-projects.md?pivots=fdp-project)
 
 
-### Manage Azure AI Foundry hubs and hub based projects
+### Manage Azure AI Foundry hubs and hub-based projects
 
 You can also manage [!INCLUDE [hub](../includes/hub-project-name.md)]s from the management center. They're listed in the __All resources__ section, and when selected are displayed in the left menu.
 

articles/ai-foundry/concepts/planning.md

@@ -5,7 +5,7 @@ description: Learn how to plan the rollout of Azure AI Foundry across your organ
 ms.service: azure-ai-foundry
 author: sdgilley
 ms.topic: concept-article
-ms.date: 06/25/2025
+ms.date: 08/11/2025
 ms.author: sgilley
 ms.reviewer: deeikele
 ---

articles/ai-foundry/how-to/azure-policy.md

@@ -70,7 +70,7 @@ To control who can access your Azure AI Foundry hubs and projects, use [Microsof
 |---|---|---|
 | Azure AI Foundry App | cb2ff863-7f30-4ced-ab89-a00194bcf6d9 | Use to control access to the Azure AI Foundry portal. |
 | Azure Machine Learning Web App | d7304df8-741f-47d3-9bc2-df0e24e2071f | Use to control access to Azure Machine Learning studio. |
-| Azure Machine Learning | 0736f41a-0425-bdb5-1563eff02385 | Use to control direct access to the Azure Machine Learning API. For example, when using the SDK or REST API. Azure AI Foundry hub based projects rely on the Azure Machine Learning API. |
+| Azure Machine Learning | 0736f41a-0425-bdb5-1563eff02385 | Use to control direct access to the Azure Machine Learning API. For example, when using the SDK or REST API. Azure AI Foundry hub-based projects rely on the Azure Machine Learning API. |
 
 ## Configure built-in policies
 

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

@@ -2,7 +2,7 @@
 
 title: Add a new connection to your project
 titleSuffix: Azure AI Foundry
-description: Learn how to add a new connection to your hub based or Foundry project.
+description: Learn how to add a new connection to your hub-based or Foundry project.
 ms.service: azure-ai-foundry
 ms.custom:
   - ignite-2023

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

@@ -78,11 +78,11 @@ A Table (`uri_table`) data source type points to a *table* on a storage resource
 
 [!INCLUDE [tip-left-pane](../includes/tip-left-pane.md)]
 
-These steps explain how to add an existing file, folder, or table data resource from Azure Storage to your hub based project workspace in the Azure AI Foundry portal:
+These steps explain how to add an existing file, folder, or table data resource from Azure Storage to your hub-based project workspace in the Azure AI Foundry portal:
 
 1. Navigate to the [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs).
 
-1. Select the hub based project where you want to add the data.
+1. Select the hub-based project where you want to add the data.
 
 1. From the collapsible **My assets** menu on the left, select **Data + indexes**, then select **New data** as shown in this screenshot:
 
@@ -99,7 +99,7 @@ These steps explain how to add an existing file, folder, or table data resource
 
 ## Manage data
 
-After you add data to your hub based project, you can you can delete, archive, restore, tag, archive, and preview the data in the Azure AI Foundry.
+After you add data to your hub-based project, you can you can delete, archive, restore, tag, archive, and preview the data in the Azure AI Foundry.
 
 ### Delete data
 

articles/ai-foundry/how-to/evaluation-azure-devops.md

@@ -105,7 +105,7 @@ agent-ids: "<your-ai-agent-ids>
 
 ```
 
-# [Hub based project](#tab/hub-project)
+# [Hub-based project](#tab/hub-project)
 
 ```yaml