Merge pull request #134 from MicrosoftDocs/main

9/5 11:00 AM IST Publish

Author: PhilKang0704

.openpublishing.publish.config.json

@@ -12,7 +12,8 @@
       "monikers": [],
       "open_to_public_contributors": true,
       "type_mapping": {
-        "Conceptual": "Content"
+        "Conceptual": "Content",
+        "ZonePivotGroups": "Toc"
       },
       "build_entry_point": "docs"
     }
@@ -169,8 +170,6 @@
       "branch_mapping": {}
     }
   ],
-  "git_repository_url_open_to_public_contributors": "https://github.com/MicrosoftDocs/azure-ai-docs",
-  "git_repository_branch_open_to_public_contributors": "main",
   "branch_target_mapping": {},
   "targets": {}
 }

articles/ai-services/content-safety/faq.yml

@@ -8,10 +8,10 @@ metadata:
 
   ms.service: azure-ai-content-safety
   ms.topic: faq
-  ms.date: 04/30/2024
+  ms.date: 09/04/2024
   ms.author: pafarley
   ms.custom:
-title: Azure AI Content Safety API Frequently Asked Questions
+title: Azure AI Content Safety Frequently Asked Questions
 summary: |
   > [!TIP]
   > If you can't find answers to your questions in this FAQ, ask the Cognitive Services API community on [StackOverflow](https://stackoverflow.com/questions/tagged/project-oxford+or+microsoft-cognitive) or contact Help and Support on [UserVoice](https://feedback.azure.com/d365community/forum/09041fae-0b25-ec11-b6e6-000d3a4f0858)
@@ -25,8 +25,8 @@ sections:
         answer: |
           The main differences between the two services are:
 
-          - Azure Content Moderator uses binary classification for each content type (such as `profanity` or `adult`), while Azure AI Content Safety uses multiple classes (such as `sexual`, `violent`, `hate`, and `self-harm`) with different severity levels.
-          - Azure AI Content Safety supports multilingual content moderation in English, German, Japanese, Spanish, French, Italian, Portuguese, and Chinese, while Azure Content Moderator's AI classifiers only support English.
+          - Azure Content Moderator uses binary classification for each content type (such as `profanity` or `adult`), while Azure AI Content Safety uses different classes (such as `sexual`, `violent`, `hate`, and `self-harm`) with multiple severity levels.
+          - Azure AI Content Safety supports multilingual content moderation (see [Language support](./language-support.md)), while Azure Content Moderator's AI classifiers only support English.
           - Azure Content Moderator has a built-in term list and a custom term list feature, while Azure AI Content Safety does not have a built-in term list but relies on advanced language and vision models to detect harmful content. It also provides a custom term list feature for customization.
           - Azure AI Content Safety has an interactive studio for exploring and testing the service capabilities, while Azure Content Moderator does not.
       - question: |
@@ -35,7 +35,7 @@ sections:
           Microsoft recommends that customers who are using Azure Content Moderator migrate to Azure AI Content Safety because:
 
           - Azure AI Content Safety offers more accurate and granular detection of harmful content in text and images using state-of-the-art AI models.
-          - Azure AI Content Safety supports multilingual content moderation in English, Japanese, German, Spanish, French, Portuguese, Italian, and Chinese.
+          - Azure AI Content Safety supports multilingual content moderation (see [Language support](./language-support.md)).
           - Azure AI Content Safety enables responsible AI practices by monitoring both user-generated and AI-generated content.
       - question: |
           Can I detect harmful content in custom categories that I define myself?
@@ -44,8 +44,8 @@ sections:
       - question: |
           How does billing work for the Azure AI Content Safety service?
         answer: |
-          In the S tier, there are two types of APIs. For the Text API, the service is billed for the amount of text records submitted to the service. For the Image API, the service is billed for the number of images submitted to the service.
+          In the **S0** tier, there are two types of APIs. For the Text API, the service is billed for the amount of text records submitted to the service. For the Image API, the service is billed for the number of images submitted to the service. See the Azure [pricing page](https://aka.ms/content-safety-pricing) for more information.
       - question: |
           What happens if I exceed the transaction limit on my free tier for Azure AI Content Safety?
         answer: |
-          Usage is throttled if the transaction limit is reached on the Free tier. Customers cannot accrue overages on the free tier.
+          Service usage is throttled if you reach the transaction limit on the Free tier. Customers cannot accrue overages on the free tier.

articles/ai-services/content-safety/includes/language-notice.md

@@ -0,0 +1,14 @@
+---
+title: "Language notice"
+#services: cognitive-services
+author: PatrickFarley
+manager: nitinme
+ms.service: azure-ai-content-safety
+ms.topic: include
+ms.date: 05/03/2023
+ms.author: pafarley
+---
+
+The Azure AI Content Safety models for protected material, groundedness detection, and custom categories (standard) work with English only.
+
+Other Azure AI Content Safety models have been specifically trained and tested on the following languages: Chinese, English, French, German, Spanish, Italian, Japanese, Portuguese. However, these features can work in many other languages, but the quality might vary. In all cases, you should do your own testing to ensure that it works for your application.