Merge pull request #3388 from laujan/disable-content-filtering

modify content filtering

Author: denrea

articles/ai-services/content-understanding/overview.md

@@ -7,7 +7,7 @@ ms.author: lajanuar
 manager: nitinme
 ms.service: azure-ai-content-understanding
 ms.topic: overview
-ms.date: 02/19/2025
+ms.date: 03/06/2025
 ms.custom: ignite-2024-understanding-release
 
 #customer intent: As a user, I want to learn more about Content Understanding solutions.
@@ -73,17 +73,20 @@ See [Quickstart](quickstart/use-ai-foundry.md) for more examples.
 
 
 ## Responsible AI
+
  Azure AI Content Understanding is designed to guard against processing harmful content, such as graphic violence and gore, hateful speech and bullying, exploitation, abuse, and more. For more information and a full list of prohibited content, *see* our [**Transparency note**](/legal/cognitive-services/content-understanding/transparency-note?toc=/azure/ai-services/content-understanding/toc.json&bc=/azure/ai-services/content-understanding/breadcrumb/toc.json) and our [**Code of Conduct**](https://aka.ms/AI-CoC).
 
 ### Modified Content Filtering
 
-Azure AI Content Understanding now supports turning off content filtering for approved customers. The subscription IDs with approved modified content filtering impacts the Azure AI Content Understanding output.
+Content Understanding now supports modified content filtering for approved customers. The subscription IDs with approved modified content filtering impacts Content Understanding output. By default, Content Understanding employs a content filtering system that identifies specific risk categories for potentially harmful content in both submitted prompts and generated outputs. Modified content filtering allows the system to annotate rather than block potentially harmful output, giving you the ability to determine how to handle potentially harmful content. For more information on content filter types, *see* [Content filtering: filter types](../openai/concepts/content-filter.md#content-filter-types).
 
 > [!IMPORTANT]
 >
 > * Apply for modified content filters via this form: [Azure OpenAI Limited Access Review: Modified Content Filters](https://ncv.microsoft.com/uEfCgnITdR).
 > * For more information, *see* [**Content Filtering**](../openai/concepts/content-filter.md).
 
+To learn more about how to add modified content filtering to your requests, *see* our [REST API quickstart](quickstart/use-rest-api.md#modified-content-filtering).
+
 ## Data privacy and security
 Developers using the Content Understanding service should review Microsoft's policies on customer data. For more information, visit our [**Data, protection and privacy**](https://www.microsoft.com/trust-center/privacy) page.
 

articles/ai-services/content-understanding/quickstart/use-rest-api.md

@@ -22,7 +22,7 @@ ms.date: 11/19/2024
 
 ## Prerequisites
 
-To get started, you need **An active Azure subscription**. If you don't have an Azure account, you can [create a free subscription](https://azure.microsoft.com/free/). 
+To get started, you need **An active Azure subscription**. If you don't have an Azure account, you can [create a free subscription](https://azure.microsoft.com/free/).
 
 * Once you have your Azure subscription, create an [Azure AI Services resource](https://portal.azure.com/#create/Microsoft.CognitiveServicesAIServices) in the Azure portal. This multi-service resource enables access to multiple Azure AI services with a single set of credentials.
 
@@ -174,6 +174,118 @@ First, create a JSON file named `request_body.json` with the following content:
 
 ---
 
+### Modified content filtering
+
+* Customers, who are approved, can customize the Content Understanding default content filtering system. After modifications, the output filters will annotate content rather than block it, offering improved control over content filtering in the Content Understanding output.
+
+* To request approval for modified content filtering, complete the following form: [Azure OpenAI Limited Access Review: Modified Content Filters](https://ncv.microsoft.com/uEfCgnITdR).
+
+* Once approved, create or update your `request_body.json` file to include the `"disableContentFiltering": true` property.
+
+# [Document](#tab/document)
+
+ Here's a document modality code sample using the`"disableContentFiltering": true` property:
+
+   ```json
+   {
+     "description": "Sample invoice analyzer",
+     "scenario": "document",
+     "config": {
+
+       "disableContentFiltering": true,
+
+       "enableFace": true,
+       "returnDetails": true,
+       },
+       "fieldSchema": {
+
+      <insert your schema here>
+
+       }
+   }
+
+   ```
+
+For more information, *see* [**Content Filtering**](../../openai/concepts/content-filter.md).
+
+# [Image](#tab/image)
+
+Here's an image modality code sample using the`"disableContentFiltering": true` property:
+
+   ```json
+   {
+     "description": "Sample chart analyzer",
+     "scenario": "image",
+     "config": {
+
+       "disableContentFiltering": true,
+
+       "returnDetails": true,
+       },
+       "fieldSchema": { 
+
+       <insert your schema here>
+
+       }
+   }
+
+   ```
+
+For more information, *see* [**Content Filtering**](../../openai/concepts/content-filter.md).
+
+# [Audio](#tab/audio)
+
+Here's an audio modality code sample using the`"disableContentFiltering": true` property:
+
+   ```json
+   {
+     "description": "Sample call transcript analyzer",
+     "scenario": "callCenter",
+     "config": {
+
+       "disableContentFiltering": true,
+
+       "returnDetails": true,
+       "locales": ["en-US"]
+       },
+       "fieldSchema": {
+
+       <insert your schema here>
+
+       }
+   }
+
+   ```
+
+For more information, *see* [**Content Filtering**](../../openai/concepts/content-filter.md).
+
+
+# [Video](#tab/video)
+
+ Here's a video modality code sample using the`"disableContentFiltering": true` property:
+
+   ```json
+   {
+     "description": "Sample marketing video analyzer",
+     "scenario": "videoShot",
+     "config": {
+
+       "disableContentFiltering": true,
+
+       },
+       "fieldSchema": {
+
+       <insert your schema here>
+
+       }
+   }
+
+   ```
+For more information, *see* [**Content Filtering**](../../openai/concepts/content-filter.md).
+
+---
+
+
 Before running the following `cURL` commands, make the following changes to the HTTP request:
 
 1. Replace `{endpoint}` and `{key}` with the endpoint and key values from your Azure portal Azure AI Services instance.
@@ -540,8 +652,8 @@ The 200 (`OK`) JSON response includes a `status` field indicating the status of
 
 ---
 
-## Next steps 
+## Next steps
 
-* In this quickstart, you learned how to call the [REST API](/rest/api/contentunderstanding/operation-groups?view=rest-contentunderstanding-2024-12-01-preview&preserve-view=true) to create a custom analyzer. For a user experience, try [**Azure AI Foundry portal**](https://ai.azure.com/). 
+* In this quickstart, you learned how to call the [REST API](/rest/api/contentunderstanding/operation-groups?view=rest-contentunderstanding-2024-12-01-preview&preserve-view=true) to create a custom analyzer. For a user experience, try [**Azure AI Foundry portal**](https://ai.azure.com/).
 
 

articles/ai-services/content-understanding/toc.yml

@@ -5,7 +5,7 @@ items:
   expanded: true
   items:
   - name: What is Azure AI Content Understanding?
-    displayName: document, text, images, video, audio, multimodal, visual, structured, content, field, extraction
+    displayName: document, text, images, video, audio, multimodal, visual, structured, content, field, extraction, content filtering, filter
     href: overview.md
   - name: Create an Azure AI Services resource
     displayName: extract, text, images, OCR, optical character recognition
@@ -29,7 +29,7 @@ items:
 - name: Quickstarts
   items:
   - name: Content Understanding REST API
-    displayName: quickstart, extract, text, images, OCR, optical character recognition
+    displayName: quickstart, extract, text, images, OCR, optical character recognition, content filtering, filter
     href: quickstart/use-rest-api.md
   - name: Content Understanding Azure AI Foundry portal
     displayName: quickstart, extract, text, images, OCR, optical character recognition