Merge pull request #277203 from MicrosoftDocs/main

6/4/2024 PM Publish

Author: Taojunshen

articles/active-directory-b2c/TOC.yml

@@ -537,8 +537,6 @@
             href: partner-nok-nok.md
           - name: Transmit Security for passwordless
             href: partner-bindid.md
-          - name: Transmit Security for risk detection
-            href: partner-transmit-security.md
           - name: Trusona
             href: partner-trusona.md
           - name: Twilio
@@ -571,6 +569,8 @@
         - name: Microsoft Dynamics 365 Fraud Protection
           href: partner-dynamics-365-fraud-protection.md
           displayName: m365 dynamics, dynamics fraud protection, fraud, 365 protection
+        - name: Transmit Security
+          href: partner-transmit-security.md
       - name: Investigate risk with Identity Protection
         href: identity-protection-investigate-risk.md
       - name: Configure Conditional Access

articles/active-directory-b2c/partner-transmit-security.md

@@ -6,7 +6,7 @@ author: yoelh
 manager: martinco
 ms.service: active-directory
 ms.topic: how-to
-ms.date: 05/13/2024
+ms.date: 06/04/2024
 ms.author: yoelh
 ms.reviewer: kengaderdus
 ms.subservice: B2C
@@ -16,7 +16,7 @@ zone_pivot_groups: b2c-policy-type
 ---
 
 
-# Configure Transmit Security with Azure Active Directory B2C for risk detection and prevention
+# Configure Transmit Security with Azure Active Directory B2C for Fraud Prevention
 
 In this tutorial, learn to integrate Azure Active Directory B2C (Azure AD B2C) authentication with [Transmit Security's Detection and Response Services (DRS)](https://transmitsecurity.com/platform/detection-and-response). Transmit Security allows you to detect risk in customer interactions on digital channels, and to enable informed identity and trust decisions across the consumer experience.
 

articles/ai-services/content-safety/language-support.md

@@ -14,7 +14,8 @@ ms.author: pafarley
 
 # Language support for Azure AI Content Safety
 
-Some capabilities of Azure AI Content Safety support multiple languages; any capabilities not listed here only support English.
+> [!IMPORTANT]
+> Azure AI Content Safety features not listed in this article, such as Prompt Shields, Protected material detection, Groundedness detection, and Custom categories (rapid) only support English.
 
 ## Text moderation
 

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

@@ -45,12 +45,13 @@ There are different types of analysis available from this service. The following
 
 | Type                        | Functionality           |
 | :-------------------------- | :---------------------- |
-| [Analyze text](/rest/api/cognitiveservices/contentsafety/text-operations/analyze-text) API          | Scans text for sexual content, violence, hate, and self harm with multi-severity levels. |
-| [Analyze image](/rest/api/cognitiveservices/contentsafety/image-operations/analyze-image) API         | Scans images for sexual content, violence, hate, and self harm with multi-severity levels. |
 | [Prompt Shields](/rest/api/cognitiveservices/contentsafety/text-operations/detect-text-jailbreak) (preview) | Scans text for the risk of a [User input attack](./concepts/jailbreak-detection.md) on a Large Language Model. [Quickstart](./quickstart-jailbreak.md) |
 | [Groundedness detection](/rest/api/cognitiveservices/contentsafety/text-groundedness-detection-operations/detect-groundedness-options) (preview) | Detects whether the text responses of large language models (LLMs) are grounded in the source materials provided by the users. [Quickstart](./quickstart-groundedness.md) |
 | [Protected material text detection](/rest/api/cognitiveservices/contentsafety/text-operations/detect-text-protected-material) (preview) | Scans AI-generated text for known text content (for example, song lyrics, articles, recipes, selected web content). [Quickstart](./quickstart-protected-material.md)|
 | Custom categories (rapid) API (preview) | Lets you define [emerging harmful content patterns](./concepts/custom-categories-rapid.md) and scan text and images for matches. [How-to guide](./how-to/custom-categories-rapid.md) |
+| [Analyze text](/rest/api/cognitiveservices/contentsafety/text-operations/analyze-text) API          | Scans text for sexual content, violence, hate, and self harm with multi-severity levels. |
+| [Analyze image](/rest/api/cognitiveservices/contentsafety/image-operations/analyze-image) API         | Scans images for sexual content, violence, hate, and self harm with multi-severity levels. |
+
 
 ## Content Safety Studio
 
@@ -98,9 +99,29 @@ Currently, Azure AI Content Safety has an **F0 and S0** pricing tier. See the Az
 
 ### Input requirements
 
-The default maximum length for text submissions is 10K characters. If you need to analyze longer blocks of text, you can split the input text (for example, by punctuation or spacing) across multiple related submissions.
+See the following list for the input requirements for each feature.
+
+<!--
+|  | Analyze text API | Analyze image API |  Prompt Shields<br>(preview) | Groundedness<br>detection (preview) | Protected material<br>detection (preview) |
+|-------|---|----------|----------|-----|-----|
+| Input requirements:   | Default maximum length: 10K characters (split longer texts as needed). | Maximum image file size: 4 MB<br>Dimensions between 50x50 and 2048x2048 pixels.<br>Images can be in JPEG, PNG, GIF, BMP, TIFF, or WEBP formats. | Maximum prompt length: 10K characters.<br>Up to five documents with a total of 10D characters. | Maximum 55,000 characters for grounding sources per API call.<br>Maximum text and query length: 7,500 characters. | Default maximum: 1K characters.<br>Minimum: 111 characters (for scanning LLM completions, not user prompts). | -->
+
+- **Analyze text API**: 
+  - Default maximum length: 10K characters (split longer texts as needed).
+- **Analyze image API**: 
+  - Maximum image file size: 4 MB
+  - Dimensions between 50 x 50 and 2048 x 2048 pixels.
+  - Images can be in JPEG, PNG, GIF, BMP, TIFF, or WEBP formats.
+- **Prompt Shields (preview)**: 
+  - Maximum prompt length: 10K characters.
+  - Up to five documents with a total of 10K characters.
+- **Groundedness detection (preview)**: 
+  - Maximum length for grounding sources: 55,000 characters (per API call).
+  - Maximum text and query length: 7,500 characters.
+- **Protected material detection (preview)**: 
+  - Default maximum length: 1K characters.
+  - Minimum length: 111 characters (for scanning LLM completions, not user prompts).
 
-The maximum size for image submissions is 4 MB, and image dimensions must be between 50 x 50 pixels and 2,048 x 2,048 pixels. Images can be in JPEG, PNG, GIF, BMP, TIFF, or WEBP formats.
 
 ### Language support
 
@@ -112,7 +133,7 @@ For more information, see [Language support](/azure/ai-services/content-safety/l
 
 To use the Content Safety APIs, you must create your Azure AI Content Safety resource in the supported regions. Currently, the Content Safety features are available in the following Azure regions: 
 
-|Region | Moderation APIs | Prompt Shields |  Protected material<br>detection | Groundedness<br>detection | Incident response | Blocklists |
+|Region | Moderation APIs | Prompt Shields<br>(preview) |  Protected material<br>detection (preview) | Groundedness<br>detection (preview) | Custom categories<br>(rapid) (preview) | Blocklists |
 |---|---|---|---|---|---|---|
 | East US | ✅ | ✅| ✅ |✅ |✅ |✅ |
 | East US 2 | ✅ | | | ✅ | | ✅|
@@ -134,26 +155,12 @@ Feel free to [contact us](mailto:[email protected]) if you need
 
 ### Query rates
 
-#### Moderation APIs
-
-| Pricing Tier | Requests per 10 seconds  |
-| :----------- | :--------------------- |
-| F0           | 1000                     |
-| S0           | 1000                     |
-
-
-#### Prompt Shields
-| Pricing Tier | Requests per 10 seconds |
-| :----------- | :---------------------------- |
-| F0           | 1000         |
-| S0           | 1000         |
-
-#### Groundedness detection
-| Pricing Tier | Requests per 10 seconds |
-| :----------- | :--------------------------- |
-| F0           | 50                           |
-| S0           | 50                           |
+Content Safety features have query rate limits in requests-per-10-seconds. See the following table for the rate limits for each feature.
 
+|Pricing tier | Moderation APIs | Prompt Shields<br>(preview) |  Protected material<br>detection (preview) | Groundedness<br>detection (preview) | Custom categories<br>(rapid) (preview) | 
+|--------|---------|-------------|---------|---------|---------|
+| F0    | 1000     | 1000        | 1000     | 50      | 1000 |
+| S0    | 1000     | 1000        | 1000     | 50      | 1000 |
 
 If you need a faster rate, please [contact us](mailto:[email protected]) to request.
 

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

@@ -17,19 +17,18 @@ items:
     href: faq.yml
 - name: Quickstarts
   items:
-  - name: Content Safety Studio
-    href: studio-quickstart.md
-  - name: Text moderation
-    href: quickstart-text.md
-  - name: Image moderation
-    href: quickstart-image.md
   - name: Prompt Shields (preview)
     href: quickstart-jailbreak.md
   - name: Groundedness detection (preview)
     href: quickstart-groundedness.md
   - name: Protected material detection (preview)
     href: quickstart-protected-material.md
-
+  - name: Content Safety Studio
+    href: studio-quickstart.md
+  - name: Text moderation
+    href: quickstart-text.md
+  - name: Image moderation
+    href: quickstart-image.md
 - name: Samples 
   items: 
   - name: Azure AI Content Safety Python samples
@@ -58,14 +57,14 @@ items:
         href: ../cognitive-services-virtual-networks.md?context=/azure/ai-services/content-safety/context/context
 - name: Concepts
   items:
-  - name: Harm categories
-    href: concepts/harm-categories.md
   - name: Prompt Shields
     href: concepts/jailbreak-detection.md
   - name: Groundedness detection
     href: concepts/groundedness.md
   - name: Custom categories (rapid)
     href: concepts/custom-categories-rapid.md
+  - name: Harm categories
+    href: concepts/harm-categories.md
 - name: Reference
   items:
   - name: Azure AI Content Safety REST API

articles/ai-services/openai/how-to/use-your-data-securely.md

@@ -334,47 +334,8 @@ Make sure your sign-in credential has `Cognitive Services OpenAI Contributor` ro
 
 ### Ingestion API
 
-
 See the [ingestion API reference article](/rest/api/azureopenai/ingestion-jobs?context=/azure/ai-services/openai/context/context) for details on the request and response objects used by the ingestion API.
 
-More notes:
-
-* `JOB_NAME` in the API path will be used as the index name in Azure AI Search.
-* Use the `Authorization` header rather than api-key.
-* Explicitly set `storageEndpoint` header.
-* Use `ResourceId=` format for `storageConnectionString` header, so Azure OpenAI and Azure AI Search use managed identity to authenticate the storage account, which is required to bypass network restrictions.
-* **Do not** set the `searchServiceAdminKey` header. The system-assigned identity of the Azure OpenAI resource is used to authenticate Azure AI Search.
-* **Do not** set `embeddingEndpoint` or `embeddingKey`. Instead, use the `embeddingDeploymentName` header to enable text vectorization.
-
-
-**Submit job example**
-
-```bash
-accessToken=$(az account get-access-token --resource https://cognitiveservices.azure.com/ --query "accessToken" --output tsv)
-curl -i -X PUT https://my-resource.openai.azure.com/openai/extensions/on-your-data/ingestion-jobs/vpn1025a?api-version=2023-10-01-preview \
--H "Content-Type: application/json" \
--H "Authorization: Bearer $accessToken" \
--H "storageEndpoint: https://mystorage.blob.core.windows.net/" \
--H "storageConnectionString: ResourceId=/subscriptions/1234567-abcd-1234-5678-1234abcd/resourceGroups/my-resource/providers/Microsoft.Storage/storageAccounts/mystorage" \
--H "storageContainer: my-container" \
--H "searchServiceEndpoint: https://mysearch.search.windows.net" \
--H "embeddingDeploymentName: ada" \
--d \
-'
-{
-}
-'
-```
-
-**Get job status example**
-
-```bash
-accessToken=$(az account get-access-token --resource https://cognitiveservices.azure.com/ --query "accessToken" --output tsv)
-curl -i -X GET https://my-resource.openai.azure.com/openai/extensions/on-your-data/ingestion-jobs/abc1234?api-version=2023-10-01-preview \
--H "Content-Type: application/json" \
--H "Authorization: Bearer $accessToken"
-```
-
 ### Inference API
 
 See the [inference API reference article](../references/on-your-data.md) for details on the request and response objects used by the inference API.

articles/ai-services/openai/quotas-limits.md

@@ -10,7 +10,7 @@ ms.custom:
   - ignite-2023
   - references_regions
 ms.topic: conceptual
-ms.date: 05/19/2024
+ms.date: 06/04/2024
 ms.author: mbullwin
 ---
 
@@ -45,6 +45,7 @@ The following sections provide you with a quick guide to the default quotas and
 | Max files per Assistant/thread | 20 |
 | Max file size for Assistants & fine-tuning | 512 MB |
 | Assistants token limit | 2,000,000 token limit |
+| GPT-4o max images per request (# of images in the messages array/conversation history) | 10 |
 
 ## Regional quota limits