Merge branch 'main' into 438940-update-toc-kate

Author: laujan

articles/ai-foundry/how-to/develop/langchain.md

@@ -7,7 +7,7 @@ ms.service: azure-ai-foundry
 ms.custom:
   - ignite-2024
 ms.topic: how-to
-ms.date: 06/24/2025
+ms.date: 06/26/2025
 ms.reviewer: fasantia
 ms.author: sgilley
 author: sdgilley
@@ -31,7 +31,7 @@ To run this tutorial, you need:
 
 * An [Azure subscription](https://azure.microsoft.com).
 
-* A model deployment supporting the [Model Inference API](https://aka.ms/azureai/modelinference) deployed. In this example, we use a `Mistral-medium-2505` deployment in the [Foundry Models](../../../ai-foundry/model-inference/overview.md).
+* A model deployment supporting the [Model Inference API](https://aka.ms/azureai/modelinference) deployed. In this example, we use a `Mistral-Large-2411` deployment in the [Foundry Models](../../../ai-foundry/model-inference/overview.md).
 * Python 3.9 or later installed, including pip.
 * LangChain installed. You can do it with:
 
@@ -76,7 +76,7 @@ Once configured, create a client to connect with the chat model by using the `in
 ```python
 from langchain.chat_models import init_chat_model
 
-llm = init_chat_model(model="mistral-medium-2505", model_provider="azure_ai")
+llm = init_chat_model(model="Mistral-Large-2411", model_provider="azure_ai")
 ```
 
 You can also use the class `AzureAIChatCompletionsModel` directly.
@@ -97,7 +97,7 @@ from langchain_azure_ai.chat_models import AzureAIChatCompletionsModel
 model = AzureAIChatCompletionsModel(
     endpoint=os.environ["AZURE_INFERENCE_ENDPOINT"],
     credential=DefaultAzureCredential(),
-    model="mistral-medium-2505",
+    model="Mistral-Large-2411",
 )
 ```
 
@@ -115,7 +115,7 @@ from langchain_azure_ai.chat_models import AzureAIChatCompletionsModel
 model = AzureAIChatCompletionsModel(
     endpoint=os.environ["AZURE_INFERENCE_ENDPOINT"],
     credential=DefaultAzureCredentialAsync(),
-    model="mistral-medium-2505",
+    model="Mistral-Large-2411",
 )
 ```
 
@@ -169,7 +169,7 @@ chain.invoke({"language": "italian", "text": "hi"})
 
 Models deployed to Azure AI Foundry support the Model Inference API, which is standard across all the models. Chain multiple LLM operations based on the capabilities of each model so you can optimize for the right model based on capabilities. 
 
-In the following example, we create two model clients. One is a producer and another one is a verifier. To make the distinction clear, we're using a multi-model endpoint like the [Foundry Models API](../../model-inference/overview.md) and hence we're passing the parameter `model` to use a `Mistral-Medium` and a `Mistral-Small` model, quoting the fact that **producing content is more complex than verifying it**.
+In the following example, we create two model clients. One is a producer and another one is a verifier. To make the distinction clear, we're using a multi-model endpoint like the [Foundry Models API](../../model-inference/overview.md) and hence we're passing the parameter `model` to use a `Mistral-Large` and a `Mistral-Small` model, quoting the fact that **producing content is more complex than verifying it**.
 
 [!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-chat-models.ipynb?name=create_producer_verifier)]
 

articles/ai-foundry/media/how-to/inference/serverless-endpoint-url-keys.png

@@ -5,8 +5,8 @@ ms.author: lajanuar
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: include
-ms.date: 06/12/2025
+ms.date: 06/26/2025
 ---
 
 > [!IMPORTANT]
-> LUIS will be retired on October 1st 2025 and starting April 1st 2023 you will not be able to create new LUIS resources. We recommend [migrating your LUIS applications](../../language-service/conversational-language-understanding/how-to/migrate-from-luis.md) to [conversational language understanding](../../language-service/conversational-language-understanding/overview.md) to benefit from continued product support and multilingual capabilities.
+> Language Understanding Intelligent Service (LUIS) will be fully retired on March 31, 2026. LUIS resource creation isn't available. Beginning on October 31, 2025, the LUIS portal will no longer be available. We recommend [migrating your LUIS applications](../../language-service/conversational-language-understanding/how-to/migrate-from-luis.md) to [conversational language understanding](../../language-service/conversational-language-understanding/overview.md) to benefit from continued product support and multilingual capabilities.

articles/ai-services/luis/includes/deprecation-notice.md

@@ -3,7 +3,7 @@ title: Azure OpenAI in Azure Government
 titleSuffix: Azure OpenAI
 description: Learn how to use Azure OpenAI in the Azure Government cloud.
 author: challenp
-ms.date: 5/29/2025
+ms.date: 6/25/2025
 ms.service: azure-ai-openai
 ms.topic: how-to
 ms.custom:
@@ -25,17 +25,21 @@ The following sections show model availability by region and deployment type. Mo
 
 <br>
 
-## Standard deployment model availability
-|   **Region**  | **o3-mini USGov DataZone** | **gpt-4o**, **2024-05-13** | **gpt-4o-mini**, **2024-07-18** | **gpt-35-turbo**, **0125** | **text-embedding-3-large**, **1** | **text-embedding-3-small**, **1** | **text-embedding-ada-002**, **2** |
-|:--------------|:--------------------------:|:--------------------------:|:-------------------------------:|:--------------------------:|:---------------------------------:|:---------------------------------:|:---------------------------------:|
-| usgovarizona  | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
-| usgovvirginia | ✅ | ✅ | -  | ✅ | - | - | ✅ |
+### USGov DataZone
+Data zone deployments are available in the same Azure OpenAI resource as all other Azure OpenAI deployment types but allow you to leverage Azure Government infrastructure to dynamically route traffic to the data center within the USGov data zone with the best availability for each request.
 
 * USGov DataZone provides access to the model from both usgovarizona and usgovvirginia.
 * Data stored at rest remains in the designated Azure region of the resource.
-* Data may be processed for inferencing in either of the two Azure Government regions. 
+* Data may be processed for inferencing in either of the two Azure Government regions.
 
-Data zone standard deployments are available in the same Azure OpenAI resource as all other Azure OpenAI deployment types but allow you to leverage Azure Government infrastructure to dynamically route traffic to the data center within the USGov data zone with the best availability for each request.
+<br>
+
+### Standard deployment model availability
+|   **Region**   | **o3-mini** | **gpt-4o**, **2024-11-20** | **gpt-4o**, **2024-05-13** | **gpt-4o-mini**, **2024-07-18** | **gpt-35-turbo**, **0125** | **text-embedding-3-large**, **1** | **text-embedding-3-small**, **1** | **text-embedding-ada-002**, **2** |
+|:---------------|:--------------------------:|:--------------------------:|:--------------------------:|:-------------------------------:|:--------------------------:|:---------------------------------:|:---------------------------------:|:---------------------------------:|
+| usgovarizona   | - | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
+| usgovvirginia  | - | ✅ | ✅ | -  | ✅ | - | - | ✅ |
+| USGov DataZone |✅| ✅ | - | -  | - | - | - | - |
 
 To request quota increases for these models, submit a request at [https://aka.ms/AOAIGovQuota](https://aka.ms/AOAIGovQuota). Note the following maximum quota limits allowed via that form:
 
@@ -45,11 +49,12 @@ To request quota increases for these models, submit a request at [https://aka.ms
 
 <br>
 
-## Provisioned deployment model availability
-|   **Region**  | **gpt-4o**, **2024-05-13** | **gpt-4o-mini**, **2024-07-18** | **gpt-35-turbo**, **0125** |
-|:--------------|:--------------------------:|:-------------------------------:|:--------------------------:|
-| usgovarizona  | ✅ | - | ✅ |
-| usgovvirginia | ✅ | - | ✅ |
+### Provisioned deployment model availability
+|   **Region**  | **gpt-4o**, **2024-11-20** | **gpt-4o**, **2024-05-13** | **gpt-4o-mini**, **2024-07-18** | **gpt-35-turbo**, **0125** |
+|:---------------|:--------------------------:|:--------------------------:|:-------------------------------:|:--------------------------:|
+| usgovarizona   | - | ✅ | - | ✅ |
+| usgovvirginia  | ✅ | ✅ | - | ✅ |
+| USGov DataZone | ✅| -  | -  | -  |
 
 <br>
 

articles/ai-services/openai/azure-government.md

@@ -45,10 +45,12 @@ ms.custom:
 >- Poland Central
 >- Southeast Asia
 >- South Africa North
+>- South Central US
 >- Spain Central
 >- Sweden Central
 >- Switzerland West
 >- Switzerland North
 >- UK South
+>- West Europe
 >- West US
 >- West US3

articles/ai-services/openai/includes/fine-tune-models.md

@@ -1,26 +1,25 @@
 ---
-title: Azure OpenAI in Azure AI Foundry Models Realtime API Reference
+title: Audio events reference
 titleSuffix: Azure OpenAI
-description: Learn how to use the Realtime API to interact with the Azure OpenAI in real-time.
+description: Learn how to use events with the Realtime API and Voice Live API.
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 4/28/2025
+ms.date: 6/27/2025
 author: eric-urban
 ms.author: eur
 recommendations: false
 ---
 
-# Realtime events reference
+# Audio events reference
 
-[!INCLUDE [Feature preview](includes/preview-feature.md)]
+Realtime events are used to communicate between the client and server in real-time audio applications. The events are sent as JSON objects over various endpoints, such as WebSockets or WebRTC. The events are used to manage the conversation, audio buffers, and responses in real-time.
 
-The Realtime API is a WebSocket-based API that allows you to interact with the Azure OpenAI in real-time. 
+You can use audio client and server events with these APIs:
+- [Azure OpenAI Realtime API](/azure/ai-services/openai/realtime-audio-quickstart)
+- [Azure AI Voice Live API](/azure/ai-services/speech-service/voice-live)
 
-The Realtime API (via `/realtime`) is built on [the WebSockets API](https://developer.mozilla.org/docs/Web/API/WebSockets_API) to facilitate fully asynchronous streaming communication between the end user and model. Device details like capturing and rendering audio data are outside the scope of the Realtime API. It should be used in the context of a trusted, intermediate service that manages both connections to end users and model endpoint connections. Don't use it directly from untrusted end user devices.
-
-> [!TIP]
-> To get started with the Realtime API, see the [quickstart](realtime-audio-quickstart.md) and [how-to guide](./how-to/realtime-audio.md).
+Unless otherwise specified, the events described in this document are applicable to both APIs.
 
 ## Client events
 

articles/ai-services/openai/realtime-audio-reference.md

@@ -441,7 +441,7 @@ items:
               displayName: RAG, rag
     - name: Azure OpenAI monitoring data reference
       href: monitor-openai-reference.md
-    - name: Realtime API (preview) events reference
+    - name: Audio events reference
       href: realtime-audio-reference.md
 - name: Resources
   items: 

articles/ai-services/openai/toc.yml

@@ -5,8 +5,8 @@ ms.topic: include
 ms.custom: include file
 ms.service: azure-ai-language
 ms.subservice: azure-ai-qna-maker
-ms.date: 06/12/2025
+ms.date: 06/26/2025
 ---
 
 > [!NOTE]
-> The QnA Maker service is being retired on the 31st of March, 2025. A newer version of the question and answering capability is now available as part of [Azure AI Language](../../language-service/index.yml). For question answering capabilities within the Language Service, see [question answering](../../language-service/question-answering/overview.md). Starting 1st October, 2022 you won't be able to create new QnA Maker resources. For information on migrating existing QnA Maker knowledge bases to question answering, consult the [migration guide](../../language-service/question-answering/how-to/migrate-qnamaker.md).
+> The QnA Maker service is being retired on the October 31, 2025 (extended from March 31, 2025). A newer version of the question and answering capability is now available as part of [Azure AI Language](../../language-service/index.yml). For question answering capabilities within the Language Service, see [question answering](../../language-service/question-answering/overview.md). As of October 1, 2022, you're no longer able to create new QnA Maker resources. Beginning on March 31, 2025, the QnA Maker portal is no longer available. For information on migrating existing QnA Maker knowledge bases to question answering, consult the [migration guide](../../language-service/question-answering/how-to/migrate-qnamaker.md).

articles/ai-services/qnamaker/includes/new-version.md

@@ -4,7 +4,7 @@ author: eric-urban
 ms.author: eur
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 5/19/2025
+ms.date: 6/27/2025
 ---
 
 ## Prerequisites
@@ -151,6 +151,7 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
             session_update = {
                 "type": "session.update",
                 "session": {
+                    "instructions": "You are a helpful AI assistant responding in natural, engaging language.",
                     "turn_detection": {
                         "type": "azure_semantic_vad",
                         "threshold": 0.3,
@@ -170,7 +171,7 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
                         "type": "server_echo_cancellation"
                     },
                     "voice": {
-                        "name": "en-US-Aria:DragonHDLatestNeural",
+                        "name": "en-US-Ava:DragonHDLatestNeural",
                         "type": "azure-standard",
                         "temperature": 0.8,
                     },
@@ -417,7 +418,7 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 The output of the script is printed to the console. You see messages indicating the status of the connection, audio stream, and playback. The audio is played back through your speakers or headphones.
 
 ```text
-Session created:  {"type": "session.update", "session": {"turn_detection": {"type": "azure_semantic_vad", "threshold": 0.3, "prefix_padding_ms": 200, "silence_duration_ms": 200, "remove_filler_words": false, "end_of_utterance_detection": {"model": "semantic_detection_v1", "threshold": 0.1, "timeout": 4}}, "input_audio_noise_reduction": {"type": "azure_deep_noise_suppression"}, "input_audio_echo_cancellation": {"type": "server_echo_cancellation"}, "voice": {"name": "en-US-Aria:DragonHDLatestNeural", "type": "azure-standard", "temperature": 0.8}}, "event_id": ""}
+Session created:  {"type": "session.update", "session": {"instructions": "You are a helpful AI assistant responding in natural, engaging language.","turn_detection": {"type": "azure_semantic_vad", "threshold": 0.3, "prefix_padding_ms": 200, "silence_duration_ms": 200, "remove_filler_words": false, "end_of_utterance_detection": {"model": "semantic_detection_v1", "threshold": 0.1, "timeout": 4}}, "input_audio_noise_reduction": {"type": "azure_deep_noise_suppression"}, "input_audio_echo_cancellation": {"type": "server_echo_cancellation"}, "voice": {"name": "en-US-Ava:DragonHDLatestNeural", "type": "azure-standard", "temperature": 0.8}}, "event_id": ""}
 Starting the chat ...
 Received event: {'session.created'}
 Press 'q' and Enter to quit the chat.

articles/ai-services/speech-service/includes/quickstarts/voice-live-api/realtime-python.md

@@ -239,7 +239,7 @@ items:
       href: voice-live-quickstart.md
     - name: How to use Voice Live API
       href: voice-live-how-to.md
-    - name: Realtime API events reference documentation
+    - name: Audio events reference
       href: /azure/ai-services/openai/realtime-audio-reference?context=/azure/ai-services/speech-service/context/context
 - name: Intent recognition
   items: