Merge pull request #259838 from MicrosoftDocs/main

11/29/2023 PM Publish

Author: Taojunshen

articles/ai-services/document-intelligence/how-to-guides/use-sdk-rest-api.md

@@ -125,10 +125,6 @@ Congratulations! You've learned to use Document Intelligence models to analyze v
 > [Explore the Document Intelligence REST API](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-2023-07-31&preserve-view=true&tabs=HTTP)
 ::: moniker-end
 
-::: moniker range="doc-intel-2.1.0"
-[!INCLUDE [applies to v2.1](../includes/applies-to-v21.md)]
-::: moniker-end
-
 ::: moniker range="doc-intel-2.1.0"
 In this how-to guide, you learn how to add Document Intelligence to your applications and workflows. Use a programming language of your choice or the REST API. Azure AI Document Intelligence is a cloud-based Azure AI service that uses machine learning to extract key-value pairs, text, and tables from your documents. We recommend that you use the free service while you learn the technology. Remember that the number of free pages is limited to 500 per month.
 

articles/ai-services/openai/concepts/content-filter.md

@@ -363,7 +363,6 @@ Annotations are currently in preview for Completions and Chat Completions (GPT m
 
 # [OpenAI Python 0.28.1](#tab/python)
 
-
 ```python
 # os.getenv() for the endpoint and key assumes that you are using environment variables.
 
@@ -591,6 +590,49 @@ main().catch((err) => {
   console.error("The sample encountered an error:", err);
 });
 ```
+
+# [PowerShell](#tab/powershell)
+
+```powershell-interactive
+# Env: for the endpoint and key assumes that you are using environment variables.
+$openai = @{
+    api_key     = $Env:AZURE_OPENAI_KEY
+    api_base    = $Env:AZURE_OPENAI_ENDPOINT # your endpoint should look like the following https://YOUR_RESOURCE_NAME.openai.azure.com/
+    api_version = '2023-10-01-preview' # this may change in the future
+    name        = 'YOUR-DEPLOYMENT-NAME-HERE' #This will correspond to the custom name you chose for your deployment when you deployed a model.
+}
+
+$prompt = 'Example prompt where a severity level of low is detected'
+    # Content that is detected at severity level medium or high is filtered, 
+    # while content detected at severity level low isn't filtered by the content filters.
+
+$headers = [ordered]@{
+    'api-key' = $openai.api_key
+}
+
+$body = [ordered]@{
+    prompt    = $prompt
+    model      = $openai.name
+} | ConvertTo-Json
+
+# Send a completion call to generate an answer
+$url = "$($openai.api_base)/openai/deployments/$($openai.name)/completions?api-version=$($openai.api_version)"
+
+$response = Invoke-RestMethod -Uri $url -Headers $headers -Body $body -Method Post -ContentType 'application/json'
+return $response.prompt_filter_results.content_filter_results | format-list
+```
+
+The `$response` object contains a property named `prompt_filter_results` that contains annotations
+about the filter results. If you prefer JSON to a .NET object, pipe the output to `ConvertTo-JSON`
+instead of `Format-List`.
+
+```output
+hate      : @{filtered=False; severity=safe}
+self_harm : @{filtered=False; severity=safe}
+sexual    : @{filtered=False; severity=safe}
+violence  : @{filtered=False; severity=safe}
+```
+
 ---
 
 For details on the inference REST API endpoints for Azure OpenAI and how to create Chat and Completions please follow [Azure OpenAI Service REST API reference guidance](../reference.md). Annotations are returned for all scenarios when using `2023-06-01-preview`.
@@ -648,5 +690,3 @@ As part of your application design, consider the following best practices to del
 - Azure OpenAI content filtering is powered by [Azure AI Content Safety](https://azure.microsoft.com/products/cognitive-services/ai-content-safety).
 - Learn more about understanding and mitigating risks associated with your application: [Overview of Responsible AI practices for Azure OpenAI models](/legal/cognitive-services/openai/overview?context=/azure/ai-services/openai/context/context).
 - Learn more about how data is processed in connection with content filtering and abuse monitoring: [Data, privacy, and security for Azure OpenAI Service](/legal/cognitive-services/openai/data-privacy?context=/azure/ai-services/openai/context/context#preventing-abuse-and-harmful-content-generation).
-
-

articles/ai-services/policy-reference.md

@@ -1,7 +1,7 @@
 ---
 title: Built-in policy definitions for Azure AI services
 description: Lists Azure Policy built-in policy definitions for Azure AI services. These built-in policy definitions provide common approaches to managing your Azure resources.
-ms.date: 11/21/2023
+ms.date: 11/29/2023
 author: nitinme
 ms.author: nitinme
 ms.service: azure-ai-services

articles/ai-services/speech-service/includes/language-support/stt.md

@@ -74,7 +74,7 @@ ms.author: eur
 | `es-PR` | Spanish (Puerto Rico) | Plain text<br/><br/>Structured text<br/><br/>Pronunciation |
 | `es-PY` | Spanish (Paraguay) | Plain text<br/><br/>Structured text<br/><br/>Pronunciation |
 | `es-SV` | Spanish (El Salvador) | Plain text<br/><br/>Pronunciation |
-| `es-US` | Spanish (United States) | Plain text<br/><br/>Structured text<br/><br/>Pronunciation |
+| `es-US`<sup>1</sup> | Spanish (United States) | Plain text<br/><br/>Structured text<br/><br/>Pronunciation |
 | `es-UY` | Spanish (Uruguay) | Plain text<br/><br/>Structured text<br/><br/>Pronunciation |
 | `es-VE` | Spanish (Venezuela) | Plain text<br/><br/>Structured text<br/><br/>Pronunciation |
 | `et-EE` | Estonian (Estonia) | Plain text<br/><br/>Pronunciation |
@@ -83,7 +83,7 @@ ms.author: eur
 | `fi-FI` | Finnish (Finland) | Plain text<br/><br/>Pronunciation |
 | `fil-PH` | Filipino (Philippines) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Pronunciation |
 | `fr-BE` | French (Belgium) | Audio + human-labeled transcript<br/><br/>Plain text |
-| `fr-CA` | French (Canada) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Pronunciation<br/><br/>Phrase list |
+| `fr-CA`<sup>1</sup> | French (Canada) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Pronunciation<br/><br/>Phrase list |
 | `fr-CH` | French (Switzerland) | Plain text<br/><br/>Pronunciation |
 | `fr-FR` | French (France) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Pronunciation<br/><br/>Phrase list |
 | `ga-IE` | Irish (Ireland) | Plain text<br/><br/>Pronunciation |
@@ -151,3 +151,5 @@ ms.author: eur
 | `zh-HK` | Chinese (Cantonese, Traditional) | Audio + human-labeled transcript<br/><br/>Plain text |
 | `zh-TW` | Chinese (Taiwanese Mandarin, Traditional) | Audio + human-labeled transcript<br/><br/>Plain text |
 | `zu-ZA` | Zulu (South Africa) | Plain text |
+
+<sup>1</sup> It is a bilingual model with support for the English language as well.

articles/ai-services/speech-service/includes/release-notes/release-notes-stt.md

@@ -8,6 +8,19 @@ ms.author: eur
 
 ### November 2023 release
 
+#### Introducing Bilingual Speech Modeling!
+We're thrilled to unveil a groundbreaking addition to our real-time speech modeling—Bilingual Speech Modeling. This significant enhancement allows our speech model to seamlessly support bilingual language pairs, such as English and Spanish, as well as English and French. This feature empowers users to effortlessly switch between languages during real-time interactions, marking a pivotal moment in our commitment to enhancing communication experiences.
+ 
+Key Highlights:
+- Bilingual Support: With our latest release, users can seamlessly switch between English and Spanish or between English and French during real-time speech interactions. This functionality is tailored to accommodate bilingual speakers who frequently transition between these two languages.
+- Enhanced User Experience: Bilingual speakers, whether at work, home, or in various community settings, will find this feature immensely beneficial. The model's ability to comprehend and respond to both English and Spanish in real time opens up new possibilities for effective and fluid communication.
+ 
+How to Use:
+
+Choose es-US (Spanish and English) or fr-CA (French and English) when you call the Speech Service API or try it out on Speech Studio. Feel free to speak either language or mix them together—the model is designed to adapt dynamically, providing accurate and context-aware responses in both languages.
+
+It's time to elevate your communication game with our latest feature release—seamless, multilingual communication at your fingertips!
+
 #### Speech To text models update
 
 We're excited to introduce a significant update to our speech models, promising enhanced accuracy, improved readability, and refined entity recognition. This upgrade comes with a robust new structure, bolstered by an expanded training dataset, ensuring a marked advancement in overall performance. It includes newly released models for en-US, zh-CN, ja-JP, it-IT, pt-BR, es-MX, es-ES, fr-FR, de-DE, ko-KR, tr-TR, sv-SE, and he-IL.

articles/aks/TOC.yml

@@ -699,6 +699,8 @@
           href: /virtualization/windowscontainers/manage-docker/optimize-windows-dockerfile?context=/azure/aks/context/aks-context
         - name: Windows AKS partner solutions
           href: windows-aks-partner-solutions.md
+        - name: Windows AKS Customer Stories
+          href: windows-aks-customer-stories.md
     - name: Develop and run applications
       items:
         - name: Install existing applications with Helm
@@ -815,4 +817,4 @@
     - name: Support options for AKS
       href: aks-support-help.md
     - name: Troubleshooting documentation for AKS
-      href: /troubleshoot/azure/azure-kubernetes/welcome-azure-kubernetes
+      href: /troubleshoot/azure/azure-kubernetes/welcome-azure-kubernetes