Merge pull request #3863 from MicrosoftDocs/main

4/1/2025 PM Publish

Author: Taojunshen

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

@@ -925,7 +925,7 @@
     {
       "source_path_from_root": "/articles/ai-services/translator/modifications-deprecations.md",
       "redirect_url": "/azure/ai-services/translator/reference/release-history",
-      "redirect_document_id": true
+      "redirect_document_id": false
     },
     {
       "source_path_from_root": "/articles/ai-services/translator/neural-dictionary.md",
@@ -965,7 +965,7 @@
     {
       "source_path_from_root": "/articles/ai-services/translator/translator-faq.md",
       "redirect_url": "/azure/ai-services/translator/faq",
-      "redirect_document_id": true
+      "redirect_document_id": false
     },
     {
       "source_path_from_root": "/articles/ai-services/translator/word-alignment.md",
@@ -978,13 +978,8 @@
       "redirect_document_id": true
     },
     {
-      "source_path_from_root": "/articles/ai-services/translator/reference/known-issues.md",
+      "source_path_from_root": "/articles/ai-services/translator/known-issues.md",
       "redirect_url": "/azure/ai-services/translator/text-translation/reference/known-issues",
-      "redirect_document_id": true
-    },
-    {
-      "source_path_from_root": "/articles/ai-services/translator/reference/release-history.md",
-      "redirect_url": "/azure/ai-services/translator/text-translation/reference/release-history",
       "redirect_document_id": false
     },
     {
@@ -1058,8 +1053,18 @@
       "redirect_document_id": true
     },
     {
-      "source_path_from_root": "/articles/ai-services/translator/text-translation/reference/release-history.md",
-      "redirect_url": "/azure/ai-services/translator/release-history",
+      "source_path_from_root": "/articles/ai-services/translator/text-translation/reference/known-issues.md",
+      "redirect_url": "/azure/ai-services/translator/reference/known-issues",
+      "redirect_document_id": true
+    },
+    {
+      "source_path_from_root": "/articles/ai-services/translator/release-history.md",
+      "redirect_url": "/azure/ai-services/translator/reference/release-history",
+      "redirect_document_id": true
+    },
+    {
+      "source_path_from_root": "/articles/ai-services/translator/sovereign-clouds.md",
+      "redirect_url": "/azure/ai-services/translator/reference/sovereign-clouds",
       "redirect_document_id": true
     }
   ]

articles/ai-services/agents/how-to/tools/bing-grounding.md

@@ -33,7 +33,12 @@ Developers and end users don't have access to raw content returned from Groundin
 The user query is the message that an end user sends to an agent, such as *"should I take an umbrella with me today? I'm in Seattle."* Instructions are the system message a developer can provide to share context and provide instructions to the AI model on how to use various tools or behave. 
 
 When a user sends a query, the customer's AI model deployment first processes it (using the provided instructions) to later perform a Bing search query (which is [visible to developers](#how-to-display-grounding-with-bing-search-results)). 
-Grounding with Bing returns relevant search results to the customer's model deployment, which then generates the final output. When using Grounding with Bing Search, only the Bing search query and your resource key are sent to Bing, and no end user-specific information is included. Your resource key is sent to Bing solely for billing and rate limiting purposes. The authorization will happen between Grounding with Bing Search service and Azure AI Agent service. Any Bing search query that is generated and sent to Bing for the purposes of grounding is transferred, along with the resource key, outside of the Azure compliance boundary to the Grounding with Bing Search service. Grounding with Bing Search is subject to Bing's terms and do not have the same compliance standards and certifications as the Azure AI Agent Service, as described in the [Grounding with Bing Search Terms of Use](https://www.microsoft.com/bing/apis/grounding-legal). It is your responsibility to assess whether the use of Grounding with Bing Search in your agent meets your needs and requirements.
+Grounding with Bing returns relevant search results to the customer's model deployment, which then generates the final output. 
+
+> [!NOTE]
+> When using Grounding with Bing Search, only the Bing search query and your resource key are sent to Bing, and no end user-specific information is included. Your resource key is sent to Bing solely for billing and rate limiting purposes. 
+
+The authorization will happen between Grounding with Bing Search service and Azure AI Agent service. Any Bing search query that is generated and sent to Bing for the purposes of grounding is transferred, along with the resource key, outside of the Azure compliance boundary to the Grounding with Bing Search service. Grounding with Bing Search is subject to Bing's terms and do not have the same compliance standards and certifications as the Azure AI Agent Service, as described in the [Grounding with Bing Search Terms of Use](https://www.microsoft.com/bing/apis/grounding-legal). It is your responsibility to assess whether the use of Grounding with Bing Search in your agent meets your needs and requirements.
 
 ## Usage support
 
@@ -44,7 +49,7 @@ Grounding with Bing returns relevant search results to the customer's model depl
 ## Setup  
 
 > [!NOTE]
-> 1. Grounding with Bing Search only works with the following Azure OpenAI models: `gpt-3.5-turbo-0125`, `gpt-4-0125-preview`, `gpt-4-turbo-2024-04-09`, `gpt-4o-0513`
+> 1. Grounding with Bing Search works with [all Azure OpenAI models](../../concepts/model-region-support.md) that Azure AI Agent Service supports, except `gpt-4o-mini, 2024-07-18`. 
 
 1. Create an Azure AI Agent by following the steps in the [quickstart](../../quickstart.md).
 

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

@@ -48,7 +48,7 @@ You need to first build and publish a Fabric data agent and then connect your Fa
 1. Select **Microsoft Fabric** and follow the prompts to add the tool. You can add only one per agent.
 
 1. Click to add new connections. Once you have added a connection, you can directly select from existing list.
-   1. To create a new connection, you need to find `workspace-id` and `artifact-id` in your published Fabric data agent endpoint. Your Fabric data agent endpoint would look like `https://fabric.microsoft.com/groups/<workspace_id>/aiskills/<artifact-id>`
+   1. To create a new connection, you need to find `workspace-id` and `artifact-id` in your published Fabric data agent endpoint. Your Fabric data agent endpoint would look like `https://<environment>.fabric.microsoft.com/groups/<workspace_id>/aiskills/<artifact-id>`
 
    1. Then, you can add both to your connection. Make sure you have checked `is secret` for both of them
 
@@ -325,4 +325,4 @@ curl $AZURE_AI_AGENTS_ENDPOINT/threads/thread_abc123/messages?api-version=2024-1
 
 ## Next steps
 
-[See the full sample for Fabric data agent.](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-projects/samples/agents/sample_agents_fabric.py)
+[See the full sample for Fabric data agent.](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-projects/samples/agents/sample_agents_fabric.py)

articles/ai-services/translator/document-translation/how-to-guides/use-rest-api-programmatically.md

@@ -209,6 +209,29 @@ The following headers are included with each Document Translation API request:
 }
 ```
 
+### 🆕 Translate text embedded in images within documents
+
+> [!Note]
+>
+> * This feature is optional and must be enabled for each translation request.
+> * Enabling this feature will incur additional costs based on usage. For more information, *see* [Azure AI Vision pricing](https://azure.microsoft.com/pricing/details/cognitive-services/computer-vision/)
+> * This feature is currently available only with the Batch Document Translation API.
+> * The Supported file format is `.docx` only.
+> * An Azure AI Services resource (not the standalone Translator resource) is required to use this feature.
+
+### Request configuration
+
+* Use the optional `translateTextWithinImage` parameter in the `options` field
+
+   * Data type: Boolean (`true` or `false`) 
+   * Default Boolean setting is `false`. Set the option to `true` to enable image text translation.
+
+* **Response Details**. When the feature is enabled, added image processing information is included with the response: 
+
+   * **`totalImageScansSucceeded`**. The number of successfully translated image scans.
+
+   * **`totalImageScansFailed`**. The number of image scans that failed processing.
+
 ## Use code to submit Document Translation requests
 
 ### Set up your coding Platform

articles/ai-services/translator/index.yml

@@ -154,7 +154,7 @@ landingContent:
       - linkListType: reference
         links:
           - text: Translator Service in sovereign clouds
-            url: sovereign-clouds.md
+            url: reference/sovereign-clouds.md
           - text: Text translation code samples on GitHub
             url: https://github.com/MicrosoftTranslator/Text-Translation-Code-Samples
           - text: stack overflow

articles/ai-services/translator/reference/known-issues.md

@@ -0,0 +1,47 @@
+---
+title: Azure AI Translator known issues
+titlesuffix: Azure AI services
+description: Known and common issues with Azure AI Translator.
+manager: nitinme
+ms.service: azure-ai-translator
+ms.topic: reference
+ms.date: 04/01/2025
+ms.author: lajanuar
+---
+
+# Azure AI Translator known issues
+
+Azure AI Translator is updated regularly and we're continually improving and enhancing its features and capabilities. This page details known issues related to Azure AI Translator and provides steps to resolve them. Before submitting a support request, review the following list to see if your problem is already being addressed and to find a possible solution.
+
+## Active known issues
+
+* For more information regarding service-level outages, *see* the [Azure status page](https://azure.status.microsoft/en-us/status). 
+* To set up outage notifications and alerts, *see* the [Azure Service Health Portal](/azure/service-health/service-health-portal-update).
+
+### Text Translation
+
+This table lists the current known issues and workarounds for the `Text Translator` feature:
+
+| **Issue ID** | **Category / Feature Area** | **Title**  |**Description** | **Workaround** | **Issues publish date** |
+| ---| --- | ---| --- | --- |
+| `1006` | Content| Translating sentences with mixed language text | The Text Translation API doesn't support translating sentences that contain mixed language input. As a result, translations can be incorrect or incomplete when a single sentence includes multiple languages.  | Specify the intended source language, remove the mixed-language sentence, or split the text into single-language segments. | February 5, 2025|
+| `1004` | Model| Preserving context and pronouns| Some translation models don't handle pronouns well; especially third-person pronouns. This issue is due to an inherent problem with sentence-level training and inference where context isn't preserved. We're actively working to shift all our models to document-level training and inference to preserve the context.| Currently, there's no direct workaround. Users should manually review and adjust pronoun usage as needed.  | February 5, 2025|
+
+
+
+### Document Translation
+
+This table lists the active known issues for the `Document Translator` feature. This table includes existing challenges and new items related to complex or mixed content inputs.
+
+| **Issue ID** | **Category / Feature Area** | **Title**  | **Description**| **Workaround**| **Issues publish date** |
+| --- | --- | --- | --- | --- | --- |
+| `3009` |Formatting | Translating documents containing borderless charts and tables|Complex tables and charts can present significant challenges during translation, especially when they're large and intricate. Charts and tables with mixed horizontal and vertical text, varying cell sizes, or grid structures that are borderless, are difficult to format accurately. These types of tables may require added processing to ensure precision without compromising overall performance. | To improve the quality of translation output, consider recreating documents using bordered tables and charts rather than borderless ones. |April 1, 2025  |
+| `3008` | File types  | Translating complex documents | Translating documents with thousands of intricate pages can be challenging. These documents often include images, embedded text within images, and manually typed text. As a result, the batch translation request can encounter failures during the extraction, translation, and reassembly processes.| Split the large document into smaller sections (for example, divide a 1000-page file into approximately 10 files of 100 pages each) and submit them individually for the best results.| February 5, 2025|
+| `3007` | Content| Translating documents with mixed source languages  | In some cases, document translation doesn't translate source documents with multiple languages leading to incorrect or incomplete results. For example, a sentence that contains more than one language.| To ensure that the desired language is translated to the target language, specify the intended source language. Alternatively, remove the mixed-language sentence, or split the text into segments containing only one language. | February 5, 2025|
+| `3001` | Formatting  | Formatting of mathematical expressions| In some cases, translated documents don't fully retain the formatting of mathematical expressions. Superscript and subscript numbers can be reformatted incorrectly, leading to discrepancies between expected and actual output.   | Currently, there's no direct workaround. Users should manually adjust the formatting of mathematical expressions as needed.  | February 5, 2025|
+
+## Related content
+
+* [Azure Service Health Portal](/azure/service-health/service-health-portal-update)
+* [Azure Status overview](/azure/service-health/azure-status-overview)
+* [What's new in Azure AI Translator?](../whats-new.md)