Merge branch 'main' of https://github.com/MicrosoftDocs/azure-ai-docs-pr into mrb_03_28_2025_batch_expiration

Author: mrbullwinkle

.openpublishing.redirection.json

@@ -264,6 +264,11 @@
       "source_path_from_root": "/articles/ai-services/openai/concepts/provisioned-reservation-update.md",
       "redirect_url": "/azure/ai-services/openai/concepts/provisioned-migration",
       "redirect_document_id": true
+    },
+    {
+      "source_path_from_root": "/articles/ai-services/custom-vision-service/logo-detector-mobile.md",
+      "redirect_url": "/azure/ai-services/custom-vision-service",
+      "redirect_document_id": false
     }
   ]
 }

articles/ai-services/agents/how-to/tools/fabric.md

@@ -0,0 +1,328 @@
+---
+title: 'How to use the data agents in Microsoft Fabric with Azure AI Agent Service'
+titleSuffix: Azure OpenAI
+description: Learn how to perform data analytics in Azure AI Agents using Microsoft Fabric data agent.
+services: cognitive-services
+manager: nitinme
+ms.service: azure-ai-agent-service
+ms.topic: how-to
+ms.date: 02/25/2025
+author: aahill
+ms.author: aahi
+zone_pivot_groups: selection-fabric-data-agent
+ms.custom: azure-ai-agents, references_regions
+---
+
+# Use the Microsoft Fabric data agent
+
+::: zone pivot="overview"
+
+Integrate your Azure AI Agent with the [**Microsoft Fabric data agent**](https://go.microsoft.com/fwlink/?linkid=2312815) to unlock powerful data analysis capabilities. The Fabric data agent transforms enterprise data into conversational Q&A systems, allowing users to interact with the data through chat and uncover data-driven and actionable insights. 
+
+You need to first build and publish a Fabric data agent and then connect your Fabric data agent with the published endpoint. When a user sends a query, Azure AI Agent will first determine if the Fabric data agent should be leveraged or not. If so, it will use the end user’s identity to generate queries over data they have access to. Lastly, Azure AI Agent will generate responses based on queries returned from Fabric data agents. With Identity Passthrough (On-Behalf-Of) authorization, this integration simplifies access to enterprise data in Fabric while maintaining robust security, ensuring proper access control and enterprise-grade protection. 
+
+## Usage support
+
+|Azure AI foundry support  | Python SDK |	C# SDK | JavaScript SDK | REST API |Basic agent setup | Standard agent setup |
+|---------|---------|---------|---------|---------|---------|---------|
+| ✔️ | ✔️ | - | ✔️ | ✔️ | ✔️ | ✔️ |
+
+## Prerequisites
+* You have created and published a Fabric data agent endpoint
+
+* Developers and end users have at least `AI Developer` RBAC role. 
+
+* Developers and end users have at least `READ` access to the Fabric data agent and the underlying data sources it connects with.
+
+## Setup  
+> [!NOTE]
+> * The model you selected in Azure AI Agent setup is only used for agent orchestration and response generation. It doesn't impact which model Fabric data agent uses for NL2SQL operation.
+> *  Supported regions: `westus`, `japaneast`.
+1. Create an Azure AI Agent by following the steps in the [quickstart](../../quickstart.md).
+
+1. Create and publish a [Fabric data agent](https://go.microsoft.com/fwlink/?linkid=2312910)
+
+1. You can add the Microsoft Fabric tool to an agent programatically using the code examples listed at the top of this article, or the Azure AI Foundry portal. If you want to use the portal, in the Create and debug screen for your agent, scroll down the Setup pane on the right to knowledge. Then select Add.
+   :::image type="content" source="../../media/tools/knowledge-tools.png" alt-text="A screenshot showing the available tool categories in the Azure AI Foundry portal." lightbox="../../media/tools/knowledge-tools.png":::
+
+1. Select **Microsoft Fabric** and follow the prompts to add the tool. You can add only one per agent.
+
+1. Click to add new connections. Once you have added a connection, you can directly select from existing list.
+   1. To create a new connection, you need to find `workspace-id` and `artifact-id` in your published Fabric data agent endpoint. Your Fabric data agent endpoint would look like `https://fabric.microsoft.com/groups/<workspace_id>/aiskills/<artifact-id>`
+
+   1. Then, you can add both to your connection. Make sure you have checked `is secret` for both of them
+   
+        :::image type="content" source="../../media/tools/fabric-foundry.png" alt-text="A screenshot showing the fabric connection in the Azure AI Foundry portal." lightbox="../../media/tools/fabric-foundry.png":::
+
+::: zone-end
+
+::: zone pivot="code-example"
+## Step 1: Create a project client
+
+Create a client object, which will contain the connection string for connecting to your AI project and other resources.
+
+# [Python](#tab/python)
+
+```python
+import os
+from azure.ai.projects import AIProjectClient
+from azure.identity import DefaultAzureCredential
+from azure.ai.projects.models import FabricTool
+```
+# [JavaScript](#tab/javascript)
+
+```javascript
+const connectionString =
+  process.env["AZURE_AI_PROJECTS_CONNECTION_STRING"] || "<project connection string>";
+
+if (!connectionString) {
+  throw new Error("AZURE_AI_PROJECTS_CONNECTION_STRING must be set.");
+}
+const client = AIProjectsClient.fromConnectionString(
+    connectionString || "",
+    new DefaultAzureCredential(),
+);
+```
+
+# [REST API](#tab/rest)
+
+>[!IMPORTANT]
+> This REST API allows developers to invoke the Grounding with Bing Search tool through the Azure AI Agent service. It does not send calls to the Grounding with Bing Search API directly. 
+
+Follow the [REST API Quickstart](../../quickstart.md?pivots=rest-api) to set the right values for the environment variables `AZURE_AI_AGENTS_TOKEN` and `AZURE_AI_AGENTS_ENDPOINT`. The client creation is demonstrated in the next section.
+
+---
+
+## Step 2: Create an agent with the Microsoft Fabric tool enabled
+
+To make the Microsoft Fabric 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.
+
+# [Python](#tab/python)
+
+```python
+# The Fabric connection id can be found in the Azure AI Foundry project as a property of the Fabric tool
+# Your connection id is in the format /subscriptions/<your-subscription-id>/resourceGroups/<your-resource-group>/providers/Microsoft.MachineLearningServices/workspaces/<your-project-name>/connections/<your-fabric-connection-name>
+conn_id = "your-connection-id"
+
+# Initialize agent fabric tool and add the connection id
+fabric = FabricTool(connection_id=conn_id)
+
+# Create agent with the fabric tool and process agent run
+with project_client:
+    agent = project_client.agents.create_agent(
+        model="gpt-4o",
+        name="my-assistant",
+        instructions="You are a helpful assistant",
+        tools=fabric.definitions,
+        headers={"x-ms-enable-preview": "true"},
+    )
+    print(f"Created agent, ID: {agent.id}")
+```
+# [JavaScript](#tab/javascript)
+
+```javascript
+const fabricConnection = await client.connections.getConnection("FABRICCONNECTIONNAME"
+);
+
+const connectionId = fabricConnection.id;
+
+// Initialize agent Microsoft Fabric tool with the connection id
+const fabricTool = ToolUtility.createFabricTool(connectionId);
+
+// Create agent with the Microsoft Fabric tool and process assistant run
+const agent = await client.agents.createAgent("gpt-4o", {
+  name: "my-agent",
+  instructions: "You are a helpful agent",
+  tools: [fabricTool.definition],
+  toolResources: {}, // Add empty tool_resources which is required by the API
+});
+console.log(`Created agent, agent ID : ${agent.id}`);
+
+```
+
+# [REST API](#tab/rest)
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/assistants?api-version=2024-12-01-preview \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+        "instructions": "You are a helpful agent.",
+        "name": "my-agent",
+        "model": "gpt-4o",
+        "tools": [
+          {
+            "type": "fabric_dataagent",
+            "fabric_dataagent": {
+                "connections": [
+                    {
+                        "connection_id": "/subscriptions/<your-subscription-id>/resourceGroups/<your-resource-group>/providers/Microsoft.MachineLearningServices/workspaces/<your-project-name>/connections/<your-fabric-connection-name>"
+                    }
+                ]
+            }
+          }
+        ]
+      }'
+```
+---
+
+## Step 3: Create a thread
+
+# [Python](#tab/python)
+
+```python
+# Create thread for communication
+thread = project_client.agents.create_thread()
+print(f"Created thread, ID: {thread.id}")
+
+# Create message to thread
+# Remember to update the message with your data
+message = project_client.agents.create_message(
+    thread_id=thread.id,
+    role="user",
+    content="what is top sold product in Contoso last month?",
+)
+print(f"Created message, ID: {message.id}")
+```
+# [JavaScript](#tab/javascript)
+
+```javascript
+// create a thread
+const thread = await client.agents.createThread();
+
+// add a message to thread
+await client.agents.createMessage(
+    thread.id, {
+    role: "user",
+    content: "<Ask a question related to your Fabric data>",
+});
+```
+
+# [REST API](#tab/rest)
+### Create a thread
+
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/threads?api-version=2024-12-01-preview \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d ''
+```
+
+### Add a user question to the thread
+
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/threads/thread_abc123/messages?api-version=2024-12-01-preview \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+      "role": "user",
+      "content": "<question related to your data>"
+    }'
+```
+
+---
+
+## Step 4: Create a run and check the output
+
+Create a run and observe that the model uses the Fabric data agent tool to provide a response to the user's question.
+
+# [Python](#tab/python)
+
+```python
+# Create and process agent run in thread with tools
+run = project_client.agents.create_and_process_run(thread_id=thread.id, agent_id=agent.id)
+print(f"Run finished with status: {run.status}")
+
+if run.status == "failed":
+    print(f"Run failed: {run.last_error}")
+
+# Delete the assistant when done
+project_client.agents.delete_agent(agent.id)
+print("Deleted agent")
+
+# Fetch and log all messages
+messages = project_client.agents.list_messages(thread_id=thread.id)
+print(f"Messages: {messages}")
+```
+
+# [JavaScript](#tab/javascript)
+
+```javascript
+
+// create a run
+const streamEventMessages = await client.agents.createRun(thread.id, agent.id).stream();
+
+for await (const eventMessage of streamEventMessages) {
+  switch (eventMessage.event) {
+    case RunStreamEvent.ThreadRunCreated:
+      break;
+    case MessageStreamEvent.ThreadMessageDelta:
+      {
+        const messageDelta = eventMessage.data;
+        messageDelta.delta.content.forEach((contentPart) => {
+          if (contentPart.type === "text") {
+            const textContent = contentPart;
+            const textValue = textContent.text?.value || "No text";
+          }
+        });
+      }
+      break;
+
+    case RunStreamEvent.ThreadRunCompleted:
+      break;
+    case ErrorEvent.Error:
+      console.log(`An error occurred. Data ${eventMessage.data}`);
+      break;
+    case DoneEvent.Done:
+      break;
+  }
+}
+
+// Print the messages from the agent
+const messages = await client.agents.listMessages(thread.id);
+
+// Messages iterate from oldest to newest
+// messages[0] is the most recent
+for (let i = messages.data.length - 1; i >= 0; i--) {
+  const m = messages.data[i];
+  if (isOutputOfType<MessageTextContentOutput>(m.content[0], "text")) {
+    const textContent = m.content[0];
+    console.log(`${textContent.text.value}`);
+    console.log(`---------------------------------`);
+  }
+}
+```
+
+
+# [REST API](#tab/rest)
+### Run the thread
+
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/threads/thread_abc123/runs?api-version=2024-12-01-preview \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "assistant_id": "asst_abc123",
+  }'
+```
+
+### Retrieve the status of the run
+
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/threads/thread_abc123/runs/run_abc123?api-version=2024-12-01-preview \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN"
+```
+
+### Retrieve the agent response
+
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/threads/thread_abc123/messages?api-version=2024-12-01-preview \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN"
+```
+
+---
+
+::: zone-end
+
+## Next steps
+
+[See the full sample for Fabric data agent.](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-projects/samples/agents/sample_agents_fabric.py)

articles/ai-services/agents/includes/quickstart-csharp.md

@@ -4,7 +4,7 @@ author: aahill
 ms.author: aahi
 ms.service: azure-ai-agent-service
 ms.topic: include
-ms.date: 01/15/2025
+ms.date: 03/28/2025
 ---
 
 | [Reference documentation](/dotnet/api/overview/azure/ai.projects-readme) | [Samples](https://github.com/Azure/azure-sdk-for-net/tree/main/sdk/ai/Azure.AI.Projects/tests/Samples) | [Library source code](https://github.com/Azure/azure-sdk-for-net/tree/main/sdk/ai/Azure.AI.Projects) | [Package (NuGet)](https://www.nuget.org/packages/Azure.AI.Projects/) |
@@ -38,7 +38,7 @@ ms.date: 01/15/2025
 Install the .NET package to your project. For example if you're using the .NET CLI, run the following command.
 
 ```console
-dotnet add package Azure.AI.Projects
+dotnet add package Azure.AI.Projects --prerelease
 dotnet add package Azure.Identity
 ```
 

articles/ai-services/agents/media/tools/fabric-foundry.png

@@ -34,6 +34,8 @@ items:
             href: how-to/tools/file-search.md
           - name: Azure AI Search
             href: how-to/tools/azure-ai-search.md 
+          - name: Microsoft Fabric
+            href: how-to/tools/fabric.md
         - name: Action tools
           items:
           - name: Function calling

articles/ai-services/agents/toc.yml

@@ -15,6 +15,12 @@ ms.custom: azure-ai-agents
 
 This article provides a summary of the latest releases and major documentation updates for Azure AI Agent Service.
 
+## March 2025
+
+### Microsoft Fabric tool
+
+The Microsoft Fabric tool is now available for the Azure AI Agent Service, allowing users to interact with data you have in Microsoft Fabric through chat and uncover data-driven and actionable insights. See the [how-to article](./how-to/tools/fabric.md) for more information.
+
 ## February 2025
 
 ### Use Azure AI Agent Service in the Azure AI Foundry portal

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

@@ -40,7 +40,7 @@ The example application is available at the [Azure AI services ONNX Custom Visio
 
 To use your own image classifier model, follow these steps:
 
-1. Create and train a classifier with the Custom Vision Service. For instructions on how to do this, see [Create and train a classifier](./getting-started-build-a-classifier.md). Use one of the **compact** domains such as **General (compact)**. 
+1. Create and train a classifier with the Custom Vision Service. For instructions on how to do this, see [Create and train a classifier](./getting-started-build-a-classifier.md). Use one of the **compact** domains such as **General (compact)**.
    * If you have an existing classifier that uses a different domain, you can convert it to **compact** in the project settings. Then, re-train your project before continuing.
 1. Export your model. Switch to the Performance tab and select an iteration that was trained with a **compact** domain. Select the **Export** button that appears. Then select **ONNX**, and then **Export**. Once the file is ready, select the **Download** button. For more information on export options, see [Export your model](./export-your-model.md).
 1. Open the downloaded *.zip* file and extract the *model.onnx* file from it. This file contains your classifier model.
@@ -59,6 +59,5 @@ To discover other ways to export and use a Custom Vision model, see the followin
 * [Export your model](./export-your-model.md)
 * [Use exported TensorFlow model in an Android application](https://github.com/Azure-Samples/cognitive-services-android-customvision-sample)
 * [Use exported CoreML model in a Swift iOS application](https://go.microsoft.com/fwlink/?linkid=857726)
-* [Use exported CoreML model in an iOS application with Xamarin](https://github.com/xamarin/ios-samples/tree/master/ios11/CoreMLAzureModel)
 
 For more information on using ONNX models with Windows ML, see [Integrate a model into your app with Windows ML](/windows/ai/windows-ml/integrate-model).