Skip to content

Commit 44ebca9

Browse files
learn-build-service-prod[bot]learn-build-service-prod[bot]
authored
Merge pull request #5758 from MicrosoftDocs/main
Merged by Learn.Build PR Management system
2 parents 759070a + 500cab3 commit 44ebca9

File tree

16 files changed

+174
-124
lines changed

16 files changed

+174
-124
lines changed

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

Lines changed: 7 additions & 29 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ ms.service: azure-ai-foundry
77
ms.custom:
88
- ignite-2024
99
ms.topic: how-to
10-
ms.date: 06/24/2025
10+
ms.date: 06/26/2025
1111
ms.reviewer: fasantia
1212
ms.author: sgilley
1313
author: sdgilley
@@ -31,7 +31,7 @@ To run this tutorial, you need:
3131

3232
* An [Azure subscription](https://azure.microsoft.com).
3333

34-
* 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).
34+
* 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).
3535
* Python 3.9 or later installed, including pip.
3636
* LangChain installed. You can do it with:
3737

@@ -47,36 +47,14 @@ To run this tutorial, you need:
4747
4848
## Configure the environment
4949
50-
To use LLMs deployed in Azure AI Foundry portal, you need the endpoint and credentials to connect to it. Follow these steps to get the information you need from the model you want to use:
51-
52-
[!INCLUDE [tip-left-pane](../../includes/tip-left-pane.md)]
53-
54-
1. Go to the [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs).
55-
56-
1. Open the project where the model is deployed, if it isn't already open.
57-
58-
1. Go to **Models + endpoints** and select the model you deployed as indicated in the prerequisites.
59-
60-
1. Copy the endpoint URL and the key.
61-
62-
:::image type="content" source="../../media/how-to/inference/serverless-endpoint-url-keys.png" alt-text="Screenshot of the option to copy endpoint URI and keys from an endpoint." lightbox="../../media/how-to/inference/serverless-endpoint-url-keys.png":::
63-
64-
> [!TIP]
65-
> If your model was deployed with Microsoft Entra ID support, you don't need a key.
66-
67-
In this scenario, set the endpoint URL and key as environment variables. (If the endpoint you copied includes additional text after `/models`, remove it so the URL ends at `/models` as shown below.)
68-
69-
```bash
70-
export AZURE_INFERENCE_ENDPOINT="https://<resource>.services.ai.azure.com/models"
71-
export AZURE_INFERENCE_CREDENTIAL="<your-key-goes-here>"
72-
```
50+
[!INCLUDE [set-endpoint](../../includes/set-endpoint.md)]
7351
7452
Once configured, create a client to connect with the chat model by using the `init_chat_model`. For Azure OpenAI models, configure the client as indicated at [Using Azure OpenAI models](#using-azure-openai-models).
7553
7654
```python
7755
from langchain.chat_models import init_chat_model
7856
79-
llm = init_chat_model(model="mistral-medium-2505", model_provider="azure_ai")
57+
llm = init_chat_model(model="Mistral-Large-2411", model_provider="azure_ai")
8058
```
8159
8260
You can also use the class `AzureAIChatCompletionsModel` directly.
@@ -97,7 +75,7 @@ from langchain_azure_ai.chat_models import AzureAIChatCompletionsModel
9775
model = AzureAIChatCompletionsModel(
9876
endpoint=os.environ["AZURE_INFERENCE_ENDPOINT"],
9977
credential=DefaultAzureCredential(),
100-
model="mistral-medium-2505",
78+
model="Mistral-Large-2411",
10179
)
10280
```
10381
@@ -115,7 +93,7 @@ from langchain_azure_ai.chat_models import AzureAIChatCompletionsModel
11593
model = AzureAIChatCompletionsModel(
11694
endpoint=os.environ["AZURE_INFERENCE_ENDPOINT"],
11795
credential=DefaultAzureCredentialAsync(),
118-
model="mistral-medium-2505",
96+
model="Mistral-Large-2411",
11997
)
12098
```
12199
@@ -169,7 +147,7 @@ chain.invoke({"language": "italian", "text": "hi"})
169147
170148
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.
171149
172-
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**.
150+
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**.
173151
174152
[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-chat-models.ipynb?name=create_producer_verifier)]
175153

‎articles/ai-foundry/how-to/develop/llama-index.md

Lines changed: 4 additions & 23 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ ms.service: azure-ai-foundry
77
ms.custom:
88
- ignite-2024
99
ms.topic: how-to
10-
ms.date: 03/11/2025
10+
ms.date: 06/26/2025
1111
ms.reviewer: fasantia
1212
ms.author: sgilley
1313
author: sdgilley
@@ -54,26 +54,7 @@ To run this tutorial, you need:
5454
5555
## Configure the environment
5656
57-
To use LLMs deployed in Azure AI Foundry portal, you need the endpoint and credentials to connect to it. Follow these steps to get the information you need from the model you want to use:
58-
59-
[!INCLUDE [tip-left-pane](../../includes/tip-left-pane.md)]
60-
61-
1. Go to the [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs).
62-
1. Open the project where the model is deployed, if it isn't already open.
63-
1. Go to **Models + endpoints** and select the model you deployed as indicated in the prerequisites.
64-
1. Copy the endpoint URL and the key.
65-
66-
:::image type="content" source="../../media/how-to/inference/serverless-endpoint-url-keys.png" alt-text="Screenshot of the option to copy endpoint URI and keys from an endpoint." lightbox="../../media/how-to/inference/serverless-endpoint-url-keys.png":::
67-
68-
> [!TIP]
69-
> If your model was deployed with Microsoft Entra ID support, you don't need a key.
70-
71-
In this scenario, we placed both the endpoint URL and key in the following environment variables:
72-
73-
```bash
74-
export AZURE_INFERENCE_ENDPOINT="<your-model-endpoint-goes-here>"
75-
export AZURE_INFERENCE_CREDENTIAL="<your-key-goes-here>"
76-
```
57+
[!INCLUDE [set-endpoint](../../includes/set-endpoint.md)]
7758
7859
Once configured, create a client to connect to the endpoint.
7960
@@ -100,7 +81,7 @@ from llama_index.llms.azure_inference import AzureAICompletionsModel
10081
llm = AzureAICompletionsModel(
10182
endpoint=os.environ["AZURE_INFERENCE_ENDPOINT"],
10283
credential=os.environ["AZURE_INFERENCE_CREDENTIAL"],
103-
model_name="mistral-large-2407",
84+
model_name="mistral-large-2411",
10485
)
10586
```
10687
@@ -146,7 +127,7 @@ from llama_index.llms.azure_inference import AzureAICompletionsModel
146127
llm = AzureAICompletionsModel(
147128
endpoint="https://<resource>.services.ai.azure.com/models",
148129
credential=os.environ["AZURE_INFERENCE_CREDENTIAL"],
149-
model_name="mistral-large-2407",
130+
model_name="mistral-large-2411",
150131
)
151132
```
152133

‎articles/ai-foundry/includes/set-endpoint.md

Lines changed: 35 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,35 @@
1+
---
2+
title: Include file
3+
description: Include file
4+
author: sdgilley
5+
ms.reviewer: sgilley
6+
ms.author: sgilley
7+
ms.service: azure-ai-foundry
8+
ms.topic: include
9+
ms.date: 06/26/2025
10+
ms.custom: include
11+
---
12+
13+
To use LLMs deployed in Azure AI Foundry portal, you need the endpoint and credentials to connect to it. Follow these steps to get the information you need from the model you want to use:
14+
15+
[!INCLUDE [tip-left-pane](tip-left-pane.md)]
16+
17+
1. Go to the [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs).
18+
19+
1. Open the project where the model is deployed, if it isn't already open.
20+
21+
1. Go to **Models + endpoints** and select the model you deployed as indicated in the prerequisites.
22+
23+
1. Copy the endpoint URL and the key.
24+
25+
:::image type="content" source="../media/how-to/inference/serverless-endpoint-url-keys.png" alt-text="Screenshot of the option to copy endpoint URI and keys from an endpoint." lightbox="../media/how-to/inference/serverless-endpoint-url-keys.png":::
26+
27+
> [!TIP]
28+
> If your model was deployed with Microsoft Entra ID support, you don't need a key.
29+
30+
In this scenario, set the endpoint URL and key as environment variables. (If the endpoint you copied includes additional text after `/models`, remove it so the URL ends at `/models` as shown below.)
31+
32+
```bash
33+
export AZURE_INFERENCE_ENDPOINT="https://<resource>.services.ai.azure.com/models"
34+
export AZURE_INFERENCE_CREDENTIAL="<your-key-goes-here>"
35+
```

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

-58.8 KB
Loading

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

Lines changed: 24 additions & 26 deletions
Original file line numberDiff line numberDiff line change
@@ -28,7 +28,7 @@ items:
2828
href: glossary.md
2929
- name: Quickstarts
3030
items:
31-
- name: Try Azure AI Foundry portal
31+
- name: Try Content Understanding in the Azure AI Foundry portal
3232
items:
3333
- name: Use Content Understanding with a single file
3434
displayName: quickstart, extract, text, images, OCR, optical character recognition, foundry, standard, mode
@@ -63,39 +63,37 @@ items:
6363
displayName: video, audio, voice, recognition, synthesis, speaker, identification, verification, diarization, transcription, translation, language, understanding, sentiment, analysis, emotion, detection, pronunciation, model
6464
- name: Concepts
6565
items:
66-
- name: Analyzer templates in Azure AI Foundry
67-
displayName: analyzer, templates, document, text, images, video, audio, multimodal, visual, structured, content, field, extraction
68-
href: concepts/analyzer-templates.md
69-
- name: Prebuilt analyzers 🆕
70-
displayName: analyzer, templates, document, text, images, video, audio, multimodal, visual, structured, content, field, extraction
71-
href: concepts/prebuilt-analyzers.md
72-
- name: "Modes: standard and pro 🆕"
73-
displayName: standard, pro, modes, analyzers, optimization, fields
74-
href: concepts/standard-pro-modes.md
75-
- name: Best practices
76-
displayName: best practices, analyzers, optimization, fields
77-
href: concepts/best-practices.md
66+
- name: Analyzers
67+
items:
68+
- name: Analyzer templates in Azure AI Foundry
69+
displayName: analyzer, templates, document, text, images, video, audio, multimodal, visual, structured, content, field, extraction
70+
href: concepts/analyzer-templates.md
71+
- name: Prebuilt analyzers 🆕
72+
displayName: analyzer, templates, document, text, images, video, audio, multimodal, visual, structured, content, field, extraction
73+
href: concepts/prebuilt-analyzers.md
74+
- name: "Modes: standard and pro 🆕"
75+
displayName: standard, pro, modes, analyzers, optimization, fields
76+
href: concepts/standard-pro-modes.md
77+
- name: Best practices
78+
displayName: best practices, analyzers, optimization, fields
79+
href: concepts/best-practices.md
80+
- name: What are classifiers? 🆕
81+
displayName: classifier, text, images, video, audio, multimodal, visual, structured, content, field, extraction
82+
href: concepts/classifier.md
83+
- name: What is face detection?🆕
84+
displayName: recognition, detection, analysis, identification, verification
85+
href: face/overview.md
7886
- name: Tutorials
7987
items:
8088
- name: Create a custom analyzer 🆕
8189
displayName: custom, analyzer, document, text, images, video, audio, multimodal, visual, structured, content, field, extraction
8290
href: tutorial/create-custom-analyzer.md
91+
- name: Build a face-data person directory 🆕
92+
displayName: person, directory, search, index, vector
93+
href: tutorial/build-person-directory.md
8394
- name: Build a retrieval-augmented solution
8495
displayName: RAG, retrieval, augmented, generation, knowledge, base, search, index, vector
8596
href: tutorial/build-rag-solution.md
86-
- name: Classifiers 🆕
87-
items:
88-
- name: Overview
89-
displayName: classifier, text, images, video, audio, multimodal, visual, structured, content, field, extraction
90-
href: concepts/classifier.md
91-
- name: Face 🆕
92-
items:
93-
- name: Overview
94-
displayName: face, recognition, detection, analysis, identification, verification
95-
href: face/overview.md
96-
- name: "Tutorial: Build a person directory"
97-
displayName: person, directory, search, index, vector
98-
href: tutorial/build-person-directory.md
9997
- name: Responsible AI
10098
items:
10199
- name: Transparency note

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

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -5,8 +5,8 @@ ms.author: lajanuar
55
manager: nitinme
66
ms.service: azure-ai-language
77
ms.topic: include
8-
ms.date: 06/12/2025
8+
ms.date: 06/26/2025
99
---
1010

1111
> [!IMPORTANT]
12-
> 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.
12+
> 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/openai/azure-government.md

Lines changed: 18 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ title: Azure OpenAI in Azure Government
33
titleSuffix: Azure OpenAI
44
description: Learn how to use Azure OpenAI in the Azure Government cloud.
55
author: challenp
6-
ms.date: 5/29/2025
6+
ms.date: 6/25/2025
77
ms.service: azure-ai-openai
88
ms.topic: how-to
99
ms.custom:
@@ -25,17 +25,21 @@ The following sections show model availability by region and deployment type. Mo
2525

2626
<br>
2727

28-
## Standard deployment model availability
29-
| **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** |
30-
|:--------------|:--------------------------:|:--------------------------:|:-------------------------------:|:--------------------------:|:---------------------------------:|:---------------------------------:|:---------------------------------:|
31-
| usgovarizona | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
32-
| usgovvirginia | ✅ | ✅ | - | ✅ | - | - | ✅ |
28+
### USGov DataZone
29+
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.
3330

3431
* USGov DataZone provides access to the model from both usgovarizona and usgovvirginia.
3532
* Data stored at rest remains in the designated Azure region of the resource.
36-
* Data may be processed for inferencing in either of the two Azure Government regions.
33+
* Data may be processed for inferencing in either of the two Azure Government regions.
3734

38-
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.
35+
<br>
36+
37+
### Standard deployment model availability
38+
| **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** |
39+
|:---------------|:--------------------------:|:--------------------------:|:--------------------------:|:-------------------------------:|:--------------------------:|:---------------------------------:|:---------------------------------:|:---------------------------------:|
40+
| usgovarizona | - | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
41+
| usgovvirginia | - | ✅ | ✅ | - | ✅ | - | - | ✅ |
42+
| USGov DataZone |✅| ✅ | - | - | - | - | - | - |
3943

4044
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:
4145

@@ -45,11 +49,12 @@ To request quota increases for these models, submit a request at [https://aka.ms
4549

4650
<br>
4751

48-
## Provisioned deployment model availability
49-
| **Region** | **gpt-4o**, **2024-05-13** | **gpt-4o-mini**, **2024-07-18** | **gpt-35-turbo**, **0125** |
50-
|:--------------|:--------------------------:|:-------------------------------:|:--------------------------:|
51-
| usgovarizona | ✅ | - | ✅ |
52-
| usgovvirginia | ✅ | - | ✅ |
52+
### Provisioned deployment model availability
53+
| **Region** | **gpt-4o**, **2024-11-20** | **gpt-4o**, **2024-05-13** | **gpt-4o-mini**, **2024-07-18** | **gpt-35-turbo**, **0125** |
54+
|:---------------|:--------------------------:|:--------------------------:|:-------------------------------:|:--------------------------:|
55+
| usgovarizona | - | ✅ | - | ✅ |
56+
| usgovvirginia | ✅ | ✅ | - | ✅ |
57+
| USGov DataZone | ✅| - | - | - |
5358

5459
<br>
5560

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

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -45,10 +45,12 @@ ms.custom:
4545
>- Poland Central
4646
>- Southeast Asia
4747
>- South Africa North
48+
>- South Central US
4849
>- Spain Central
4950
>- Sweden Central
5051
>- Switzerland West
5152
>- Switzerland North
5253
>- UK South
54+
>- West Europe
5355
>- West US
5456
>- West US3

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

Lines changed: 9 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -1,26 +1,25 @@
11
---
2-
title: Azure OpenAI in Azure AI Foundry Models Realtime API Reference
2+
title: Audio events reference
33
titleSuffix: Azure OpenAI
4-
description: Learn how to use the Realtime API to interact with the Azure OpenAI in real-time.
4+
description: Learn how to use events with the Realtime API and Voice Live API.
55
manager: nitinme
66
ms.service: azure-ai-openai
77
ms.topic: conceptual
8-
ms.date: 4/28/2025
8+
ms.date: 6/27/2025
99
author: eric-urban
1010
ms.author: eur
1111
recommendations: false
1212
---
1313

14-
# Realtime events reference
14+
# Audio events reference
1515

16-
[!INCLUDE [Feature preview](includes/preview-feature.md)]
16+
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.
1717

18-
The Realtime API is a WebSocket-based API that allows you to interact with the Azure OpenAI in real-time.
18+
You can use audio client and server events with these APIs:
19+
- [Azure OpenAI Realtime API](/azure/ai-services/openai/realtime-audio-quickstart)
20+
- [Azure AI Voice Live API](/azure/ai-services/speech-service/voice-live)
1921

20-
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.
21-
22-
> [!TIP]
23-
> To get started with the Realtime API, see the [quickstart](realtime-audio-quickstart.md) and [how-to guide](./how-to/realtime-audio.md).
22+
Unless otherwise specified, the events described in this document are applicable to both APIs.
2423

2524
## Client events
2625

‎articles/ai-services/openai/toc.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -441,7 +441,7 @@ items:
441441
displayName: RAG, rag
442442
- name: Azure OpenAI monitoring data reference
443443
href: monitor-openai-reference.md
444-
- name: Realtime API (preview) events reference
444+
- name: Audio events reference
445445
href: realtime-audio-reference.md
446446
- name: Resources
447447
items:

0 commit comments

Comments
 (0)