Merge pull request #280572 from MicrosoftDocs/main

7/11 11:00 AM IST Publish

Author: PhilKang0704

articles/ai-services/document-intelligence/concept-custom.md

@@ -54,7 +54,7 @@ To create a custom extraction model, label a dataset of documents with the value
 > Starting with version 4.0 (2024-02-29-preview) API, custom neural models now support **overlapping fields** and **table, row and cell level confidence**.
 >
 
-The custom neural (custom document) model uses deep learning models and  base model trained on a large collection of documents. This model is then fine-tuned or adapted to your data when you train the model with a labeled dataset. Custom neural models support structured, semi-structured, and unstructured documents to extract fields. Custom neural models currently support English-language documents. When you're choosing between the two model types, start with a neural model to determine if it meets your functional needs. See [neural models](concept-custom-neural.md) to learn more about custom document models.
+The custom neural (custom document) model uses deep learning models and  base model trained on a large collection of documents. This model is then fine-tuned or adapted to your data when you train the model with a labeled dataset. Custom neural models support structured, semi-structured, and unstructured documents to extract fields. When you're choosing between the two model types, start with a neural model to determine if it meets your functional needs. See [neural models](concept-custom-neural.md) to learn more about custom document models.
 
 ### Custom template model
 
@@ -131,7 +131,7 @@ The `build custom model` operation adds support for the *template* and *neural*
 
 * Template models only accept documents that have the same basic page structure—a uniform visual appearance—or the same relative positioning of elements within the document.
 
-* Neural models support documents that have the same information, but different page structures. Examples of these documents include United States W2 forms, which share the same information, but vary in appearance across companies. Neural models currently only support English text.
+* Neural models support documents that have the same information, but different page structures. Examples of these documents include United States W2 forms, which share the same information, but vary in appearance across companies.
 
 This table provides links to the build mode programming language SDK references and code samples on GitHub:
 

articles/ai-services/language-support.md

@@ -7,7 +7,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-services
 ms.topic: conceptual
-ms.date: 07/18/2023
+ms.date: 07/08/2024
 ms.author: lajanuar
 ---
 
@@ -25,7 +25,7 @@ The following table provides links to language support reference articles by sup
 |![Document Intelligence icon](~/reusable-content/ce-skilling/azure/media/ai-services/document-intelligence.svg)</br>[Document Intelligence](./document-intelligence/language-support.md) | Turn documents into intelligent data-driven solutions. |
 |![Immersive Reader icon](media/service-icons/immersive-reader.svg)</br>[Immersive Reader](./immersive-reader/language-support.md) | Help users read and comprehend text. |
 |![Language icon](~/reusable-content/ce-skilling/azure/media/ai-services/language.svg)</br>[Language service](./language-service/concepts/language-support.md) | Build apps with industry-leading natural language understanding capabilities. |
-|![Language Understanding icon](media/service-icons/luis.svg)</br>[Language Understanding (LUIS)](./luis/luis-language-support.md) (retired) | Understand natural language in your apps. |
+|![Language Understanding icon](media/service-icons/luis.svg)</br>[Language Understanding (`LUIS`)](./luis/luis-language-support.md) (retired) | Understand natural language in your apps. |
 |![QnA Maker icon](media/service-icons/luis.svg)</br>[QnA Maker](./qnamaker/overview/language-support.md) (retired) | Distill information into easy-to-navigate questions and answers. |
 |![Speech icon](~/reusable-content/ce-skilling/azure/media/ai-services/speech.svg)</br>[Speech Service](./speech-service/language-support.md)| Configure speech-to-text, text-to-speech, translation, and speaker recognition applications. |
 |![Translator icon](~/reusable-content/ce-skilling/azure/media/ai-services/translator.svg)</br>[Translator](./translator/language-support.md) |  Translate more than 100 in-use, at-risk, and endangered languages and dialects.|
@@ -46,4 +46,4 @@ These Azure AI services are language agnostic and don't have limitations based o
 ## See also
 
 * [What are Azure AI services?](./what-are-ai-services.md)
-* [Create an account](multi-service-resource.md?pivots=azportal)
+* [How to create an account](multi-service-resource.md?pivots=azportal)

articles/ai-services/openai/concepts/model-retirements.md

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
 description: Learn about the model deprecations and retirements in Azure OpenAI.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 06/19/2024
+ms.date: 07/10/2024
 ms.custom: 
 manager: nitinme
 author: mrbullwinkle
@@ -25,16 +25,43 @@ Azure OpenAI Service models are continually refreshed with newer and more capabl
 * Deprecation
 	* When a model is deprecated, it's no longer available for new customers. It continues to be available for use by customers with existing deployments until the model is retired.
 
-## Preretirement notification
+## Notifications
 
 Azure OpenAI notifies customers of active Azure OpenAI Service deployments for models with upcoming retirements. We notify customers of upcoming retirements as follows for each deployment:
 
-* At least 60 days before retirement 
-* At least 30 days before retirement 
-* At retirement
+1. At model launch, we programmatically designate a "not sooner than" retirement date (typically six months to one year out).
+2. At least 60 days notice before model retirement for Generally Available (GA) models.
+3. At least 14 days notice before preview model version upgrades.  
 
 Retirements are done on a rolling basis, region by region.
 
+## Model availability
+
+1. At least one year of model availability for GA models after the release date of a model in at least one region worldwide
+2. For global deployments, all future model versions starting with `gpt-4o` and `gpt-4 0409` will be available with their (`N`) next succeeding model (`N+1`) for comparison together. 
+1. Customers have 60 days to try out a new GA model in at least one global, or standard region, before any upgrades happen to a newer GA model.  
+
+### Considerations for the Azure public cloud
+
+Be aware of the following: 
+
+1. All model version combinations will **not** be available in all regions.
+2. Model version `N` and `N+1` might not always be available in the same region. 
+3. GA model version `N` might upgrade to a future model version `N+X` in some regions based on capacity limitations, and without the new model version `N+X` separately being available to test in the same region. The new model version will be available to test in other regions before any upgrades are scheduled.   
+4. Preview model versions and GA versions of the same model won't always be available to test together in the same region. There will be preview and GA versions available to test in different regions. 
+5.	We reserve the right to limit future customers using a particular region to balance service quality for existing customers.
+6.	As always at Microsoft, security is of the utmost importance. If a model or model version is found to have compliance or security issues, we reserve the right to invoke the need to do emergency retirements. See the terms of service for more information.
+
+### Special considerations for Azure Government clouds
+
+1.	Global standard deployments won't be available in government clouds.
+2.	Not all models or model versions available in commercial / public cloud will be available in government clouds.
+3.	In the Azure Government clouds, we intend to support only one version of a given model at a time.
+    1. For example only one version of `gpt-35-turbo 0125` and `gpt-4o (2024-05-13)`.
+4.	There will however be a 30 day overlap between new model versions, where more than two will be available.
+    1. For example if `gpt-35-turbo 0125` or `gpt-4o (2024-05-13)` is updated to a future version, or
+    2. for model family changes beyond version updates, such as when moving from `gpt-4 1106-preview` to `gpt-4o (2024-05-13)`. 
+
 ### Who is notified of upcoming retirements
 
 Azure OpenAI notifies those who are members of the following roles for each subscription with a deployment of a model with an upcoming retirement.

articles/ai-services/translator/connector/document-translation-flow.md

@@ -7,7 +7,7 @@ manager: nitinme
 ms.service: azure-ai-translator
 ms.custom: build-2023, build-2023-dataai
 ms.topic: tutorial
-ms.date: 07/18/2023
+ms.date: 07/09/2024
 ms.author: lajanuar
 ---
 
@@ -133,7 +133,7 @@ Next, assign a **`Storage Blob Data Contributor`** role to the managed identity
 
 ### Configure a Document Translation flow
 
-Now that you've completed the prerequisites and initial setup, let's get started using the Translator V3 connector to create your document translation flow:
+Now that you completed the prerequisites and initial setup, let's get started using the Translator V3 connector to create your document translation flow:
 
 1. Sign in to [Power Automate](https://powerautomate.microsoft.com/).
 
@@ -181,7 +181,7 @@ Here are the steps to translate a file in Azure Blob Storage using the Translato
 
    * **Translator resource name**. Enter the name of your Translator resource found at the top of your resource page in the Azure portal. Select **Create**.
 
-      :::image type="content" source="../media/connectors/add-connection.png" alt-text="Screenshot showing the add connection window.":::
+      :::image type="content" source="../media/connectors/add-connection.png" alt-text="Screenshot showing the  how-to-add connection window.":::
 
       > [!NOTE]
       > After you've set up your connection, you won't be required to reenter your credentials for subsequent flows.
@@ -190,7 +190,7 @@ Here are the steps to translate a file in Azure Blob Storage using the Translato
 
    * For **Storage type of the input documents**. Select **File** or **Folder**.
    * Select a **Source Language** from the dropdown menu or keep the default **Auto-detect** option.
-   * **Location of the source documents**. Enter the URL for your document(s) in your Azure storage source document container.
+   * **Location of the source documents**. Enter the URL for your documents in your Azure storage source document container.
    * **Location of the translated documents**. Enter the URL for your Azure storage target document container.
 
       To find your source and target URLs:
@@ -209,7 +209,7 @@ Here are the steps to translate a file in Azure Blob Storage using the Translato
 
 ## Get documents status
 
-Now that you've submitted your document(s) for translation, let's check the status of the operation.
+Now that you submitted your documents for translation, let's check the status of the operation.
 
 1. Select **New step**.
 
@@ -278,13 +278,13 @@ Here are the steps to upload a file from your SharePoint site to Azure Blob Stor
 
 ##### Get file content
 
- 1. In the Choose an operation pop-up window, enter **SharePoint**, then select the **Get file content** content. Power Automate automatically signs you into your SharePoint account(s).
+ 1. In the Choose an operation pop-up window, enter **SharePoint**, then select the **Get file content** content. Power Automate automatically signs you into your SharePoint accounts.
 
       :::image type="content" source="../media/connectors/get-file-content.png" alt-text="Screenshot of the SharePoint Get file content action.":::
 
 1. On the **Get file content** step window, complete the following fields:
     * **Site Address**. Select the SharePoint site URL where your file is located from the dropdown list.
-    * **File Identifier**. Select the folder icon and choose the document(s) for translation.
+    * **File Identifier**. Select the folder icon and choose the documents for translation.
 
 ##### Create a storage blob
 
@@ -300,7 +300,7 @@ Here are the steps to upload a file from your SharePoint site to Azure Blob Stor
 
 1. Choose the Microsoft Entra account associated with your Azure Blob Storage and Translator resource accounts.
 
-1. After you have completed the **Azure Blob Storage** authentication, the **Create blob** step appears. Complete the fields as follows:
+1. After you completed the **Azure Blob Storage** authentication, the **Create blob** step appears. Complete the fields as follows:
 
    * **Storage account name or blob endpoint**. Select **Enter custom value** and enter your storage account name.
    * **Folder path**. Select the folder icon and select your source document container.
@@ -324,7 +324,7 @@ Here are the steps to upload a file from your SharePoint site to Azure Blob Stor
    * **Translator resource name**. Enter the name of your Translator resource found at the top of your resource page in the Azure portal.
    * Select **Create**.
 
-      :::image type="content" source="../media/connectors/add-connection.png" alt-text="Screenshot showing the add connection window.":::
+      :::image type="content" source="../media/connectors/add-connection.png" alt-text="Screenshot showing the how-to-add connection window.":::
 
       > [!NOTE]
       > After you've setup your connection, you won't be required to reenter your credentials for subsequent Translator flows.
@@ -351,7 +351,7 @@ Here are the steps to upload a file from your SharePoint site to Azure Blob Stor
 
 ##### Get documents status
 
-Prior to retrieving the documents status, let's schedule a 30-second delay to ensure that the file has been processed for translation:
+Before retrieving the documents status, let's schedule a 30-second delay to ensure that the file is processed for translation:
 
 1. Select **New step**. Enter **Schedule** in the search box and choose **Delay**.
    * For **Count**. Enter **30**.
@@ -404,7 +404,7 @@ In this step, you retrieve the translated document from Azure Blob Storage and u
 
 1. Select **Add an action**, enter **Azure Blob Storage** in the search box, and select the **Get blob content using path (V2)** action.
 1. In the **Storage account name or blob endpoint** field, select **Enter custom value** and enter your storage account name.
-1. Select the **Blob path** field to show the **Dynamic content** window, select **Expression** and enter the following logic in the formula field:
+1. Select the **Blob path** field to show the **Dynamic content** window, select **Expression**, and enter the following logic in the formula field:
 
    ```powerappsfl
 
@@ -415,7 +415,7 @@ In this step, you retrieve the translated document from Azure Blob Storage and u
 1. Select **Add an action**, enter **Azure Blob Storage** in the search box, and select the **Get Blob Metadata using path (V2)** action.
 1. In the **Storage account name or blob endpoint** field, select **Enter custom value** and enter your storage account name.
 
-   :::image type="content" source="../media/connectors/enter-custom-value.png" alt-text="Screenshot showing 'enter custom value' from the Create blob (V2) window.":::
+   :::image type="content" source="../media/connectors/enter-custom-value.png" alt-text="Screenshot showing 'enter custom value' from the create-blob-(V2) window.":::
 
 1. Select the **Blob path** field to show the **Dynamic content** window, select **Expression** and enter the following logic in the formula field:
 
@@ -461,7 +461,7 @@ Let's check your document translation flow and results.
 
 ---
 
-That's it! You've learned to automate document translation processes using the Microsoft Translator V3 connector and Power Automate.
+That's it! You learned to automate document translation processes using the Microsoft Translator V3 connector and Power Automate.
 
 ## Next steps
 

articles/ai-services/translator/connector/text-translator-flow.md

@@ -7,7 +7,7 @@ manager: nitinme
 ms.service: azure-ai-translator
 ms.custom: build-2023
 ms.topic: how-to
-ms.date: 07/18/2023
+ms.date: 07/10/2024
 ms.author: lajanuar
 ---
 
@@ -39,7 +39,7 @@ To get started, you need  an active Azure subscription. If you don't have an Azu
 
 ## Configure the Translator V3 connector
 
-Now that you've completed the prerequisites, let's get started.
+Now that you completed the prerequisites, let's get started.
 
 1. Sign in to [Power Automate](https://powerautomate.microsoft.com/).
 
@@ -76,7 +76,7 @@ Let's select an action. Choose to translate or transliterate text.
    * **Subscription Key**. Enter one of your keys that you copied from the Azure portal.
    * **Translator resource name**. Enter the name of your Translator resource found at the top of your resource page in the Azure portal. Select **Create**.
 
-      :::image type="content" source="../media/connectors/add-connection.png" alt-text="Screenshot showing the add connection window.":::
+      :::image type="content" source="../media/connectors/add-connection.png" alt-text="Screenshot showing the add-connection window.":::
 
       > [!NOTE]
       > After you've setup your connection, you won't be required to reenter your credentials for subsequent Translator flows.
@@ -87,7 +87,7 @@ Let's select an action. Choose to translate or transliterate text.
 1. Enter the **Body Text**.
 1. Select **Save**.
 
-   :::image type="content" source="../media/connectors/translate-text-step.png" alt-text="Screenshot showing the translate text step.":::
+   :::image type="content" source="../media/connectors/translate-text-step.png" alt-text="Screenshot showing the translate-text step.":::
 
 #### [Transliterate text](#tab/transliterate)
 
@@ -100,15 +100,15 @@ Let's select an action. Choose to translate or transliterate text.
    * **Subscription Key**. Enter one of your keys that you copied from the Azure portal.
    * **Translator resource name**. Enter the name of your Translator resource found at the top of your resource page in the Azure portal. Select **Create**.
 
-      :::image type="content" source="../media/connectors/add-connection.png" alt-text="Screenshot showing the add connection window.":::
+      :::image type="content" source="../media/connectors/add-connection.png" alt-text="Screenshot showing the add-connection window.":::
 
 1. Next, the **Transliterate** action window appears.
 1. **Language**. Select the language of the text that is to be converted.
 1. **Source script**. Select the name of the input text script.
 1. **Target script**. Select the name of transliterated text script.
 1. Select **Save**.
 
-   :::image type="content" source="../media/connectors/transliterate-text-step.png" alt-text="Screenshot showing the transliterate text step.":::
+   :::image type="content" source="../media/connectors/transliterate-text-step.png" alt-text="Screenshot showing the transliterate-text step.":::
 
 ---
 

articles/ai-services/translator/containers/deploy-user-managed-glossary.md

@@ -7,7 +7,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-translator
 ms.topic: how-to
-ms.date: 08/15/2023
+ms.date: 07/10/2024
 ms.author: lajanuar
 recommendations: false
 ---