Merge branch 'main' into release-openai-audio-models

Author: v-alje

articles/ai-foundry/concepts/models-featured.md

@@ -171,9 +171,12 @@ Meta Llama models and tools are a collection of pretrained and fine-tuned genera
 - Small language models (SLMs) like 1B and 3B Base and Instruct models for on-device and edge inferencing
 - Mid-size large language models (LLMs) like 7B, 8B, and 70B Base and Instruct models
 - High-performant models like Meta Llama 3.1-405B Instruct for synthetic data generation and distillation use cases.
+- High-performant natively multimodal models, Llama 4 Scout and Llama 4 Maverick, leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.
 
 | Model  | Type | Capabilities |
 | ------ | ---- | ------------ |
+| [Llama-4-Scout-17B-16E-Instruct](https://aka.ms/aifoundry/landing/llama-4-scout-17b-16e-instruct) | [chat-completion](../model-inference/how-to/use-chat-completions.md?context=/azure/ai-foundry/context/context) | - **Input:** text and image (128,000 tokens) <br /> - **Output:** text (8,192 tokens) <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text |
+| [Llama 4-Maverick-17B-128E-Instruct-FP8](https://aka.ms/aifoundry/landing/llama-4-maverick-17b-128e-instruct-fp8) | [chat-completion](../model-inference/how-to/use-chat-completions.md?context=/azure/ai-foundry/context/context) | - **Input:** text and image (128,000 tokens) <br /> - **Output:** text (8,192 tokens) <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text |
 | [Llama-3.3-70B-Instruct](https://ai.azure.com/explore/models/Llama-3.3-70B-Instruct/version/4/registry/azureml-meta) | [chat-completion](../model-inference/how-to/use-chat-completions.md?context=/azure/ai-foundry/context/context) | - **Input:** text (128,000 tokens) <br /> - **Output:** text (8,192 tokens) <br /> - **Tool calling:** No <br /> - **Response formats:** Text |
 | [Llama-3.2-90B-Vision-Instruct](https://ai.azure.com/explore/models/Llama-3.2-90B-Vision-Instruct/version/1/registry/azureml-meta) | [chat-completion (with images)](../model-inference/how-to/use-chat-multi-modal.md?context=/azure/ai-foundry/context/context) | - **Input:** text and image (128,000 tokens) <br /> - **Output:** text (8,192 tokens) <br /> - **Tool calling:** No <br /> - **Response formats:** Text |
 | [Llama-3.2-11B-Vision-Instruct](https://ai.azure.com/explore/models/Llama-3.2-11B-Vision-Instruct/version/1/registry/azureml-meta) | [chat-completion (with images)](../model-inference/how-to/use-chat-multi-modal.md?context=/azure/ai-foundry/context/context) | - **Input:** text and image (128,000 tokens) <br /> - **Output:** text (8,192 tokens) <br /> - **Tool calling:** No <br /> - **Response formats:** Text |

articles/ai-foundry/toc.yml

@@ -557,8 +557,6 @@ items:
     href: ai-services/content-safety-overview.md
   - name: Content safety for models deployed with serverless APIs
     href: concepts/model-catalog-content-safety.md
-  - name: Use Azure AI Content Safety in AI Foundry portal
-    href: /azure/ai-services/content-safety/how-to/foundry?context=/azure/ai-foundry/context/context
   - name: Content filtering
     href: concepts/content-filtering.md
   - name: Use blocklists

articles/ai-services/.openpublishing.redirection.ai-services.json

@@ -160,6 +160,16 @@
       "redirect_url": "/azure/ai-services/content-safety/quickstart-custom-categories",
       "redirect_document_id": true
     },
+    {
+      "source_path_from_root": "/articles/ai-services/content-safety/how-to/foundry.md",
+      "redirect_url": "/azure/ai-foundry/ai-services/content-safety-overview",
+      "redirect_document_id": false
+    },
+    {
+      "source_path_from_root": "/articles/ai-services/content-safety/studio-quickstart.md",
+      "redirect_url": "/azure/ai-foundry/ai-services/content-safety-overview?context=/azure/ai-services/content-safety/context/context",
+      "redirect_document_id": false
+    },
     {
       "source_path_from_root": "/articles/ai-services/speech-service/how-to-custom-voice-create-voice.md",
       "redirect_url": "/azure/ai-services/speech-service/professional-voice-train-voice",

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

@@ -34,6 +34,8 @@ You need to first build and publish a Fabric data agent and then connect your Fa
 
 * Developers and end users have at least `READ` access to the Fabric data agent and the underlying data sources it connects with.
 
+* Your Fabric Data Agent and Azure AI Agent need to be in the same tenant.
+
 ## 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.

articles/ai-services/content-safety/how-to/foundry.md

@@ -0,0 +1,33 @@
+---
+title: "Quickstart: Use a blocklist in the Foundry portal"
+author: PatrickFarley
+manager: nitinme
+ms.service: azure-ai-content-safety
+ms.custom:
+ms.topic: include
+ms.date: 04/10/2025
+ms.author: pafarley
+---
+
+## Prerequisites
+
+- An Azure account. If you don't have one, you can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?icid=ai-services). 
+- An [Azure AI resource](https://ms.portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/AIServices). 
+
+
+## Setup
+
+Follow these steps to use the Content Safety **try it out** page: 
+
+1. Go to [Azure AI Foundry](https://ai.azure.com/) and navigate to your project/hub. Then select the **Safety+ Security** tab on the left nav and select the **Try it out** tab.
+1. On the **Try it out** page, you can experiment with various content safety features such as text and image content, using adjustable thresholds to filter for inappropriate or harmful content.
+
+:::image type="content" source="/azure/ai-foundry/media/content-safety/try-it-out.png" alt-text="Screenshot of the try it out page for content safety.":::
+
+
+### Use a blocklist 
+
+The **Use blocklist** tab lets you create, edit, and add a blocklist to the moderation workflow. If you have a blocklist enabled when you run the test, you get a **Blocklist detection** panel under **Results**. It reports any matches with the blocklist.
+
+:::image type="content" source="/azure/ai-foundry/media/content-safety/blocklist-panel.png" alt-text="Screenshot of the Use blocklist panel.":::
+

articles/ai-services/content-safety/includes/quickstarts/foundry-quickstart-blocklist.md

@@ -0,0 +1,39 @@
+---
+title: "Quickstart: Use custom categories in the Foundry portal"
+author: PatrickFarley
+manager: nitinme
+ms.service: azure-ai-content-safety
+ms.custom:
+ms.topic: include
+ms.date: 04/10/2025
+ms.author: pafarley
+---
+
+
+## Prerequisites 
+
+- An Azure account. If you don't have one, you can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?icid=ai-services). 
+- An [Azure AI resource](https://ms.portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/AIServices). 
+
+
+## Setup
+
+Follow these steps to use the Content Safety **try it out** page: 
+
+1. Go to [Azure AI Foundry](https://ai.azure.com/) and navigate to your project/hub. Then select the **Safety+ Security** tab on the left nav and select the **Try it out** tab.
+1. On the **Try it out** page, you can experiment with various content safety features such as text and image content, using adjustable thresholds to filter for inappropriate or harmful content.
+
+:::image type="content" source="/azure/ai-foundry/media/content-safety/try-it-out.png" alt-text="Screenshot of the try it out page for content safety.":::
+    
+
+## Use custom categories
+
+This feature lets you create and train your own custom content categories and scan text for matches. 
+
+1. Select the **Custom categories** panel.
+1. Select **Add a new category** to open a dialog box. Enter your category name and a text description, and connect a blob storage container with text training data. Select **Create and train**. 
+1. Select a category and enter your sample input text, and select **Run test**. 
+    The service returns the custom category result.
+
+
+For more information, see the [Custom categories conceptual guide](/azure/ai-services/content-safety/concepts/custom-categories).

articles/ai-services/content-safety/includes/quickstarts/foundry-quickstart-custom-categories.md

@@ -0,0 +1,42 @@
+---
+title: "Quickstart: Use groundedness detection"
+author: PatrickFarley
+manager: nitinme
+ms.service: azure-ai-content-safety
+ms.custom:
+ms.topic: include
+ms.date: 04/10/2025
+ms.author: pafarley
+---
+
+
+## Prerequisites 
+
+- An Azure account. If you don't have one, you can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?icid=ai-services). 
+- An [Azure AI resource](https://ms.portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/AIServices). 
+
+
+## Setup
+
+Follow these steps to use the Content Safety **try it out** page: 
+
+1. Go to [Azure AI Foundry](https://ai.azure.com/) and navigate to your project/hub. Then select the **Safety+ Security** tab on the left nav and select the **Try it out** tab.
+1. On the **Try it out** page, you can experiment with various content safety features such as text and image content, using adjustable thresholds to filter for inappropriate or harmful content.
+
+:::image type="content" source="/azure/ai-foundry/media/content-safety/try-it-out.png" alt-text="Screenshot of the try it out page for content safety.":::
+
+
+
+## Use Groundedness detection
+
+The Groundedness detection panel lets you detect whether the text responses of large language models (LLMs) are grounded in the source materials provided by the users.
+
+1. Select the **Groundedness detection** panel.
+1. Select a sample content set on the page, or input your own for testing.
+1. Optionally, enable the reasoning feature and select your Azure OpenAI resource from the dropdown.
+1. Select **Run test**. 
+    The service returns the groundedness detection result.
+
+
+For more information, see the [Groundedness detection conceptual guide](/azure/ai-services/content-safety/concepts/groundedness).
+

articles/ai-services/content-safety/includes/quickstarts/foundry-quickstart-groundedness.md

@@ -0,0 +1,40 @@
+---
+title: "Quickstart: Analyze image content"
+description: In this quickstart, get started using Azure AI Content Safety to analyze image content for objectionable material.
+author: PatrickFarley
+manager: nitinme
+ms.service: azure-ai-content-safety
+ms.custom: 
+ms.topic: include
+ms.date: 04/10/2025
+ms.author: pafarley
+---
+
+## Prerequisites
+
+- An Azure account. If you don't have one, you can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?icid=ai-services). 
+- An [Azure AI resource](https://ms.portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/AIServices). 
+
+## Setup
+
+Follow these steps to use the Content Safety **try it out** page: 
+
+1. Go to [Azure AI Foundry](https://ai.azure.com/) and navigate to your project/hub. Then select the **Safety+ Security** tab on the left nav and select the **Try it out** tab.
+1. On the **Try it out** page, you can experiment with various content safety features such as text and image content, using adjustable thresholds to filter for inappropriate or harmful content.
+
+:::image type="content" source="/azure/ai-foundry/media/content-safety/try-it-out.png" alt-text="Screenshot of the try it out page for content safety.":::
+
+## Analyze images
+
+The **Moderate image** page provides capability for you to quickly try out image moderation.
+
+1. Select the **Moderate image content** panel. 
+1. Select a sample image from the panels on the page, or upload your own image. 
+1. Select **Run test**. 
+    The service returns all the categories that were detected, with the severity level for each: 0-Safe, 2-Low, 4-Medium, 6-High. It also returns a binary **Accepted**/**Rejected** result, based on the filters you configure. Use the matrix in the **Configure filters** tab on the right to set your allowed/prohibited severity levels for each category. Then you can run the text again to see how the filter works.
+
+## View and export code 
+
+You can use the **View Code** feature in either the **Analyze text content** or **Analyze image content** pages to view and copy the sample code, which includes configuration for severity filtering, blocklists, and moderation functions. You can then deploy the code on your end.
+
+:::image type="content" source="/azure/ai-foundry/media/content-safety/view-code-option.png" alt-text="Screenshot of the View code button.":::