Merge pull request #1861 from MicrosoftDocs/main

Publish 12/6 11:00 AM IST

Author: Saisang

articles/ai-services/content-safety/whats-new.md

@@ -21,7 +21,7 @@ Learn what's new in the service. These items might be release notes, videos, blo
 ### Upcoming deprecations
 
 To align with Content Safety versioning and lifecycle management policies, the following versions are scheduled for deprecation:
-* **Effective October 28, 2024**: All versions except `2024-09-01`, `2024-09-15-preview`, and `2024-09-30-preview` will be deprecated and no longer supported. We encourage users to transition to the latest available versions to continue receiving full support and updates. If you have any questions about this process or need assistance with the transition, please reach out to our support team.
+* **Effective March 1st, 2025**: All versions except `2024-09-01`, `2024-09-15-preview`, and `2024-09-30-preview` will be deprecated and no longer supported. We encourage users to transition to the latest available versions to continue receiving full support and updates. If you have any questions about this process or need assistance with the transition, please reach out to our support team.
 
 ## September 2024
 

articles/ai-services/openai/how-to/content-filters.md

@@ -1,22 +1,26 @@
 ---
-title: 'Use content filters (preview) with Azure OpenAI Service'
+title: 'Use content filters (preview) with Azure AI Foundry'
 titleSuffix: Azure OpenAI
-description: Learn how to use and configure the content filters that come with Azure OpenAI Service, including getting approval for gated modifications.
+description: Learn how to use and configure the content filters that come with Azure AI Foundry, including getting approval for gated modifications.
 #services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 10/04/2024
+ms.date: 12/05/2024
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false
 ms.custom: FY25Q1-Linter
-# customer intent: As a developer, I want to learn how to configure content filters with Azure OpenAI Service so that I can ensure that my applications comply with our Code of Conduct.
+# customer intent: As a developer, I want to learn how to configure content filters with Azure AI Foundry so that I can ensure that my applications comply with our Code of Conduct.
 ---
 
-# How to configure content filters with Azure OpenAI Service
+# How to configure content filters with Azure AI Foundry
 
-The content filtering system integrated into Azure OpenAI Service runs alongside the core models, including DALL-E image generation models. It uses an ensemble of multi-class classification models to detect four categories of harmful content (violence, hate, sexual, and self-harm) at four severity levels respectively (safe, low, medium, and high), and optional binary classifiers for detecting jailbreak risk, existing text, and code in public repositories. The default content filtering configuration is set to filter at the medium severity threshold for all four content harms categories for both prompts and completions. That means that content that is detected at severity level medium or high is filtered, while content detected at severity level low or safe is not filtered by the content filters. Learn more about content categories, severity levels, and the behavior of the content filtering system [here](../concepts/content-filter.md). Jailbreak risk detection and protected text and code models are optional and off by default. For jailbreak and protected material text and code models, the configurability feature allows all customers to turn the models on and off. The models are by default off and can be turned on per your scenario. Some models are required to be on for certain scenarios to retain coverage under the [Customer Copyright Commitment](/legal/cognitive-services/openai/customer-copyright-commitment?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext).
+The content filtering system integrated into Azure AI Foundry runs alongside the core models, including DALL-E image generation models. It uses an ensemble of multi-class classification models to detect four categories of harmful content (violence, hate, sexual, and self-harm) at four severity levels respectively (safe, low, medium, and high), and optional binary classifiers for detecting jailbreak risk, existing text, and code in public repositories. 
+
+The default content filtering configuration is set to filter at the medium severity threshold for all four content harms categories for both prompts and completions. That means that content that is detected at severity level medium or high is filtered, while content detected at severity level low or safe is not filtered by the content filters. Learn more about content categories, severity levels, and the behavior of the content filtering system [here](../concepts/content-filter.md). 
+
+Jailbreak risk detection and protected text and code models are optional and off by default. For jailbreak and protected material text and code models, the configurability feature allows all customers to turn the models on and off. The models are by default off and can be turned on per your scenario. Some models are required to be on for certain scenarios to retain coverage under the [Customer Copyright Commitment](/legal/cognitive-services/openai/customer-copyright-commitment?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext).
 
 > [!NOTE]
 > All customers have the ability to modify the content filters and configure the severity thresholds (low, medium, high). Approval is required for turning the content filters partially or fully off. Managed customers only may apply for full content filtering control via this form: [Azure OpenAI Limited Access Review: Modified Content Filters](https://ncv.microsoft.com/uEfCgnITdR). At this time, it is not possible to become a managed customer.
@@ -37,7 +41,7 @@ You can configure the following filter categories in addition to the default har
 
 |Filter category  |Status |Default setting  |Applied to prompt or completion?  |Description  |
 |---------|---------|---------|---------|---|
-|Prompt Shields for direct attacks (jailbreak)     |GA|    On     |   User prompt      |   Filters / annotates user prompts that might present a Jailbreak Risk. For more information about annotations, visit [Azure OpenAI Service content filtering](/azure/ai-services/openai/concepts/content-filter?tabs=python#annotations-preview). |
+|Prompt Shields for direct attacks (jailbreak)     |GA|    On     |   User prompt      |   Filters / annotates user prompts that might present a Jailbreak Risk. For more information about annotations, visit [Azure AI Foundry content filtering](/azure/ai-services/openai/concepts/content-filter?tabs=python#annotations-preview). |
 |Prompt Shields for indirect attacks  | GA| Off | User prompt | Filter / annotate Indirect Attacks, also referred to as Indirect Prompt Attacks or Cross-Domain Prompt Injection Attacks, a potential vulnerability where third parties place malicious instructions inside of documents that the generative AI system can access and process. Requires: [Document embedding and formatting](/azure/ai-services/openai/concepts/content-filter?tabs=warning%2Cuser-prompt%2Cpython-new#embedding-documents-in-your-prompt). |
 | Protected material - code |GA| On | Completion | Filters protected code or gets the example citation and license information in annotations for code snippets that match any public code sources, powered by GitHub Copilot. For more information about consuming annotations, see the [content filtering concepts guide](/azure/ai-services/openai/concepts/content-filter#annotations-preview) |
 | Protected material - text | GA| On | Completion | Identifies and blocks known text content from being displayed in the model output (for example, song lyrics, recipes, and selected web content).  |
@@ -60,5 +64,5 @@ We recommend informing your content filtering configuration decisions through an
 ## Related content
 
 - Learn more about Responsible AI practices for Azure OpenAI: [Overview of Responsible AI practices for Azure OpenAI models](/legal/cognitive-services/openai/overview?context=/azure/ai-services/openai/context/context).
-- Read more about [content filtering categories and severity levels](../concepts/content-filter.md) with Azure OpenAI Service.
+- Read more about [content filtering categories and severity levels](../concepts/content-filter.md) with Azure AI Foundry.
 - Learn more about red teaming from our: [Introduction to red teaming large language models (LLMs) article](../concepts/red-teaming.md).

articles/ai-services/openai/how-to/dall-e.md

@@ -24,13 +24,13 @@ OpenAI's DALL-E models generate images based on user-provided text prompts. This
 #### [DALL-E 3](#tab/dalle3)
 
 - An Azure subscription. You can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?icid=ai-services).
-- An Azure OpenAI resource created in the *Sweden Central* region. For more information, see [Create and deploy an Azure OpenAI Service resource](../how-to/create-resource.md).
-- Deploy a *dall-e-3* model with your Azure OpenAI resource.
+- An Azure OpenAI resource created in a supported region. See [Region availability](/azure/ai-services/openai/concepts/models#model-summary-table-and-region-availability).
+- - Deploy a *dall-e-3* model with your Azure OpenAI resource.
 
 #### [DALL-E 2 (preview)](#tab/dalle2)
 
 - An Azure subscription. You can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?icid=ai-services).
-- An Azure OpenAI resource created in the *East US* region. For more information, see [Create and deploy an Azure OpenAI Service resource](../how-to/create-resource.md).
+- An Azure OpenAI resource created in a supported region. See [Region availability](/azure/ai-services/openai/concepts/models#model-summary-table-and-region-availability). For more information, see [Create and deploy an Azure OpenAI Service resource](../how-to/create-resource.md).
 
 ---
 

articles/ai-services/openai/how-to/risks-safety-monitor.md

@@ -1,30 +1,28 @@
 ---
-title: How to use Risks & Safety monitoring in Azure OpenAI Studio
+title: How to use Risks & Safety monitoring in Azure AI Foundry
 titleSuffix: Azure OpenAI Service
 description: Learn how to check statistics and insights from your Azure OpenAI content filtering activity.
 author: PatrickFarley 
 ms.author: pafarley 
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 10/03/2024
+ms.date: 12/05/2024
 manager: nitinme
 ---
 
-# Use Risks & Safety monitoring in Azure OpenAI Studio (preview) 
+# Use Risks & Safety monitoring in Azure AI Foundry (preview) 
 
-When you use an Azure OpenAI model deployment with a content filter, you may want to check the results of the filtering activity. You can use that information to further adjust your filter configuration to serve your specific business needs and Responsible AI principles.  
+When you use an Azure OpenAI model deployment with a content filter, you may want to check the results of the filtering activity. You can use that information to further adjust your [filter configuration](/azure/ai-services/openai/how-to/content-filters) to serve your specific business needs and Responsible AI principles.  
 
-[Azure OpenAI Studio](https://oai.azure.com/) provides a Risks & Safety monitoring dashboard for each of your deployments that uses a content filter configuration.
+[Azure AI Foundry](https://oai.azure.com/) provides a Risks & Safety monitoring dashboard for each of your deployments that uses a content filter configuration.
 
 ## Access Risks & Safety monitoring
 
 To access Risks & Safety monitoring, you need an Azure OpenAI resource in one of the supported Azure regions: East US, Switzerland North, France Central, Sweden Central, Canada East. You also need a model deployment that uses a content filter configuration.
 
-Go to [Azure OpenAI Studio](https://oai.azure.com/) and sign in with the credentials associated with your Azure OpenAI resource. Select the **Deployments** tab on the left and then select your model deployment from the list. On the deployment's page, select the **Risks & Safety** tab at the top.
+Go to [Azure AI Foundry](https://oai.azure.com/) and sign in with the credentials associated with your Azure OpenAI resource. Select a project. Then select the **Models + endpoints** tab on the left and then select your model deployment from the list. On the deployment's page, select the **Metrics** tab at the top. Then select **Open in Azure Monitor** to view the full report in the Azure portal.
 
-## Content detection   
-
-The **Content detection** pane shows information about content filter activity. Your content filter configuration is applied as described in the [Content filtering documentation](/azure/ai-services/openai/how-to/content-filters).
+## Configure metrics   
 
 ### Report description
 
@@ -35,7 +33,9 @@ Content filtering data is shown in the following ways:
 - **Severity distribution by category**: This view shows the severity levels detected for each harm category, across the whole selected time range. This is not limited to _blocked_ content but rather includes all content that was flagged by the content filters.
 - **Severity rate distribution over time by category**: This view shows the rates of detected severity levels over time, for each harm category. Select the tabs to switch between supported categories.
 
+<!--
 :::image type="content" source="../media/how-to/content-detection.png" alt-text="Screenshot of the content detection pane in the Risks & Safety monitoring page." lightbox="../media/how-to/content-detection.png":::
+-->
 
 ### Recommended actions
 
@@ -56,7 +56,7 @@ To use Potentially abusive user detection, you need:
 ### Set up your Azure Data Explorer database
 
 In order to protect the data privacy of user information and manage the permission of the data, we support the option for our customers to bring their own storage to get the detailed potentially abusive user detection insights (including user GUID and statistics on harmful request by category) stored in a compliant way and with full control. Follow these steps to enable it:
-1. In Azure OpenAI Studio, navigate to the model deployment that you'd like to set up user abuse analysis with, and select **Add a data store**. 
+1. In Azure AI Foundry, navigate to the model deployment that you'd like to set up user abuse analysis with, and select **Add a data store**. 
 1. Fill in the required information and select **Save**. We recommend you create a new database to store the analysis results.
 1. After you connect the data store, take the following steps to grant permission to write analysis results to the connected database:
     1. Go to your Azure OpenAI resource's page in the Azure portal, and choose the **Identity** tab.
@@ -81,14 +81,16 @@ The potentially abusive user detection relies on the user information that custo
     - **Total abuse request ratio/count**
     - **Abuse ratio/count by category** 
 
+<!--
 :::image type="content" source="../media/how-to/potentially-abusive-user.png" alt-text="Screenshot of the Potentially abusive user detection pane in the Risks & Safety monitoring page." lightbox="../media/how-to/potentially-abusive-user.png":::
+-->
 
 ### Recommended actions
 
 Combine this data with enriched signals to validate whether the detected users are truly abusive or not. If they are, then take responsive action such as throttling or suspending the user to ensure the responsible use of your application.
 
 ## Next steps
 
-Next, create or edit a content filter configuration in Azure OpenAI Studio.
+Next, create or edit a content filter configuration in Azure AI Foundry.
 
 - [Configure content filters with Azure OpenAI Service](/azure/ai-services/openai/how-to/content-filters)