Merge pull request #2658 from MicrosoftDocs/main

v-alje · web-flow · commit 1ac6df1d7cf1 · 2025-01-30T15:01:50.000-08:00
01/30/2025 PM Publishing
diff --git a/articles/ai-foundry/model-inference/concepts/models.md b/articles/ai-foundry/model-inference/concepts/models.md
@@ -18,7 +18,7 @@ ms.custom: references_regions, tool_generated
 Azure AI model inference in Azure AI Foundry gives you access to flagship models in Azure AI to consume them as APIs without hosting them on your infrastructure.
 
 > [!TIP]
-> DeepSeek-R1 is available for deployment as [Serverless API endpoint](../../../ai-studio/how-to/deploy-models-deepseek.md).
+> DeepSeek-R1 (preview) is available for deployment as [Serverless API endpoint](../../../ai-studio/how-to/deploy-models-deepseek.md).
 
 :::image type="content" source="../media/models/models-catalog.gif" alt-text="An animation showing Azure AI studio model catalog section and the models available." lightbox="../media/models/models-catalog.gif":::
 
diff --git a/articles/ai-foundry/model-inference/reference/reference-model-inference-api.md b/articles/ai-foundry/model-inference/reference/reference-model-inference-api.md
@@ -49,7 +49,8 @@ Models deployed to [serverless API endpoints](../../../ai-studio/how-to/deploy-m
 > * [Mistral-Large](../../../ai-studio/how-to/deploy-models-mistral.md)
 > * [Jais](../../../ai-studio/how-to/deploy-jais-models.md) family of models
 > * [Jamba](../../../ai-studio/how-to/deploy-models-jamba.md) family of models
-> * [Phi-3](../../../ai-studio/how-to/deploy-models-phi-3.md) family of models
+> * [Phi-3](../../../ai-studio/how-to/deploy-models-phi-3.md) and [Phi-4](../../../ai-studio/how-to/deploy-models-phi-4.md) family of models
+> * [DeepSeek-R1](../../../ai-studio/how-to/deploy-models-deepseek.md) family of models.
 
 Models deployed to [managed inference](../../../ai-studio/concepts/deployments-overview.md):
 
diff --git a/articles/ai-services/agents/how-to/tools/azure-functions.md b/articles/ai-services/agents/how-to/tools/azure-functions.md
@@ -6,7 +6,7 @@ services: azure-ai-agent-service
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 12/11/2024
+ms.date: 01/30/2025
 author: aahill
 ms.author: aahi
 ms.custom: azure-ai-agents
diff --git a/articles/ai-services/agents/how-to/tools/function-calling.md b/articles/ai-services/agents/how-to/tools/function-calling.md
@@ -6,7 +6,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 12/11/2024
+ms.date: 01/30/2025
 author: aahill
 ms.author: aahi
 zone_pivot_groups: selection-function-calling
@@ -22,12 +22,6 @@ Azure AI Agents supports function calling, which allows you to describe the stru
 > [!NOTE]
 > Runs expire ten minutes after creation. Be sure to submit your tool outputs before the expiration.
 
-### Supported models
-
-The [models page](../../concepts/model-region-support.md) contains the most up-to-date information on regions/models where Agents are supported.
-
-To use all features of function calling including parallel functions, you need to use a model that was released after November 6, 2023.
-
 ::: zone-end
 
 ::: zone pivot="code-example"
diff --git a/articles/ai-services/agents/includes/quickstart-csharp.md b/articles/ai-services/agents/includes/quickstart-csharp.md
@@ -16,8 +16,6 @@ ms.date: 01/15/2025
 * Make sure you have the **Azure AI Developer** [RBAC role](../../../ai-studio/concepts/rbac-ai-studio.md) assigned at the appropriate level.
 * Install [the Azure CLI and the machine learning extension](/azure/machine-learning/how-to-configure-cli). If you have the CLI already installed, make sure it's updated to the latest version.
 
-[!INCLUDE [rbac-roles](rbac-roles.md)]
-
 [!INCLUDE [bicep-setup](bicep-setup.md)]
 
 ## Configure and run an agent
diff --git a/articles/ai-services/agents/includes/quickstart-python-openai.md b/articles/ai-services/agents/includes/quickstart-python-openai.md
@@ -18,8 +18,6 @@ ms.date: 11/13/2024
 * You need the **Cognitive Services OpenAI User** role assigned to use the Azure AI Services resource.
 * Install [the Azure CLI and the machine learning extension](/azure/machine-learning/how-to-configure-cli). If you have the CLI already installed, make sure it's updated to the latest version.
 
-[!INCLUDE [rbac-roles](rbac-roles.md)]
-
 [!INCLUDE [bicep-setup](bicep-setup.md)]
 
 ## Configure and run an agent
diff --git a/articles/ai-services/agents/includes/quickstart-python.md b/articles/ai-services/agents/includes/quickstart-python.md
@@ -17,8 +17,6 @@ ms.date: 11/13/2024
 * Make sure you have the **Azure AI Developer** [RBAC role](../../../ai-studio/concepts/rbac-ai-studio.md) assigned at the appropriate level.
 * Install [the Azure CLI and the machine learning extension](/azure/machine-learning/how-to-configure-cli). If you have the CLI already installed, make sure it's updated to the latest version.
 
-[!INCLUDE [rbac-roles](rbac-roles.md)]
-
 [!INCLUDE [bicep-setup](bicep-setup.md)]
 
 ## Configure and run an agent
diff --git a/articles/ai-services/agents/includes/rbac-roles.md b/articles/ai-services/agents/includes/rbac-roles.md
diff --git a/articles/ai-services/document-intelligence/toc.yml b/articles/ai-services/document-intelligence/toc.yml
@@ -37,9 +37,6 @@ items:
     href: service-limits.md
   - name: Document Intelligence client libraries
     items:
-      - name: Changelog and migration guide
-        displayName: latest, update, beta, package, preview, version
-        href: changelog-release-history.md
       - name: "SDK targets: REST API v4.0 2024-11-30 latest (GA)"
         displayName: get started, installation, downloads, documentAnalysisClient, document analysis client, Azure AD, Azure Active Directory, identity, changelog, package, version,AzureKeyCredential, Azure key credential, key, endpoint
         href: sdk-overview-v4-0.md
@@ -52,7 +49,10 @@ items:
       - name:  "SDK targets: REST API v2.1 (GA)"
         displayName: get started, installation, downloads, formRecognizerClientClient, form recognizer client, Azure AD, Azure Active Directory, identity, changelog, package, version,AzureKeyCredential, Azure key credential, key, endpoint
         href: v21/sdk-overview-v2-1.md
-  - name: FAQ
+  - name: Changelog and migration guide
+    displayName: latest, update, beta, package, preview, version
+    href: changelog-release-history.md      
+  - name: Frequently asked questions (FAQ)
     displayName: storage, security, privacy, help, support, versions, development, migrate, migration, cognitive, applied, form recognizer, form, recognizer
     href: faq.yml
 - name: Prebuilt models
diff --git a/articles/ai-services/document-intelligence/versioning/changelog-release-history.md b/articles/ai-services/document-intelligence/versioning/changelog-release-history.md
@@ -1,7 +1,7 @@
 ---
-title: Document Intelligence changelog and release history
+title: Document Intelligence changelog, release history, and migration guide
 titleSuffix: Azure AI services
-description: A version-based description of Document Intelligence feature and capability releases, changes, enhancements,  and updates.
+description: A version-based description of Document Intelligence feature and capability releases, changes, enhancements, migration guidance, and updates.
 author: laujan
 manager: nitinme
 ms.service: azure-ai-document-intelligence
@@ -15,7 +15,7 @@ ms.author: lajanuar
 <!-- markdownlint-disable MD051 -->
 <!-- markdownlint-disable MD024 -->
 
-# SDK changelog and release history
+# SDK changelog, release history, and migration guide
 
 This reference article provides a version-based description of Document Intelligence feature and capability releases, changes, updates, and enhancements.
 
@@ -414,7 +414,7 @@ This release includes the following updates:
 This release includes the following updates:
 
 > [!IMPORTANT]
-> The `DocumentAnalysisClient` and `DocumentModelAdministrationClient` now target API v3.0 GA, released 2022-08-31. These clients are no longer supported by APIs 2020-06-30-preview or earlier.
+> The `DocumentAnalysisClient` and `DocumentModelAdministrationClient` now target API v3.0 GA, released 2022-08-31. Document Intelligence no longer supports clients from 2020-06-30-preview APIs or earlier.
 
 ### [**C#**](#tab/csharp)
 
diff --git a/articles/ai-services/openai/how-to/structured-outputs.md b/articles/ai-services/openai/how-to/structured-outputs.md
@@ -19,6 +19,7 @@ Structured outputs make a model follow a [JSON Schema](https://json-schema.org/o
 > [!NOTE]
 > Currently structured outputs are not supported with:
 > - [Bring your own data](../concepts/use-your-data.md) scenarios.
+> - [Assistants](../how-to/assistant.md) or [Azure AI Agents Service](../../agents/overview.md).
 > - `gpt-4o-audio-preview` version: `2024-12-17`.
 
 ## Supported models
diff --git a/articles/ai-services/openai/includes/model-matrix/provisioned-global.md b/articles/ai-services/openai/includes/model-matrix/provisioned-global.md
@@ -11,25 +11,25 @@ ms.date: 01/15/2025
 
 | **Region**     | **gpt-4o**, **2024-05-13**   | **gpt-4o**, **2024-08-06**   | **gpt-4o**, **2024-11-20**   | **gpt-4o-mini**, **2024-07-18**   |
 |:-------------------|:--------------------------:|:--------------------------:|:--------------------------:|:-------------------------------:|
-| australiaeast      | ✅                       | ✅                       | -                      | ✅                            |
+| australiaeast      | ✅                       | ✅                       | ✅                       | ✅                            |
 | brazilsouth        | ✅                       | ✅                       | -                      | ✅                            |
 | canadacentral      | ✅                       | ✅                       | -                      | ✅                            |
 | canadaeast         | ✅                       | ✅                       | ✅                       | ✅                            |
-| eastus             | ✅                       | ✅                       | -                      | ✅                            |
-| eastus2            | ✅                       | ✅                       | -                      | ✅                            |
+| eastus             | ✅                       | ✅                       | ✅                       | ✅                            |
+| eastus2            | ✅                       | ✅                       | ✅                       | ✅                            |
 | francecentral      | ✅                       | ✅                       | -                      | ✅                            |
 | germanywestcentral | ✅                       | ✅                       | -                      | ✅                            |
 | japaneast          | ✅                       | ✅                       | -                      | ✅                            |
 | koreacentral       | ✅                       | ✅                       | -                      | ✅                            |
 | northcentralus     | ✅                       | ✅                       | -                      | ✅                            |
-| norwayeast         | ✅                       | ✅                       | -                      | ✅                            |
+| norwayeast         | ✅                       | ✅                       | ✅                       | ✅                            |
 | polandcentral      | ✅                       | ✅                       | -                      | ✅                            |
 | southafricanorth   | ✅                       | ✅                       | -                      | ✅                            |
 | southcentralus     | ✅                       | ✅                       | -                      | ✅                            |
 | southeastasia      | ✅                       | ✅                       | -                      | ✅                            |
 | southindia         | ✅                       | ✅                       | ✅                       | ✅                            |
 | spaincentral       | ✅                       | ✅                       | -                      | ✅                            |
-| swedencentral      | ✅                       | ✅                       | -                      | ✅                            |
+| swedencentral      | ✅                       | ✅                       | ✅                       | ✅                            |
 | switzerlandnorth   | ✅                       | ✅                       | -                      | ✅                            |
 | switzerlandwest    | ✅                       | ✅                       | -                      | ✅                            |
 | uaenorth           | ✅                       | ✅                       | -                      | ✅                            |
diff --git a/articles/ai-studio/how-to/deploy-models-deepseek.md b/articles/ai-studio/how-to/deploy-models-deepseek.md
@@ -21,6 +21,7 @@ zone_pivot_groups: azure-ai-model-catalog-samples-chat
 In this article, you learn about DeepSeek-R1 and how to use them.
 DeepSeek-R1 excels at reasoning tasks using a step-by-step training process, such as language, scientific reasoning, and coding tasks. It features 671B total parameters with 37B active parameters, and 128k context length.
 
+[!INCLUDE [models-preview](../includes/models-preview.md)]
 
 
 ::: zone pivot="programming-language-python"
@@ -240,7 +241,7 @@ print_stream(result)
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -507,7 +508,7 @@ for await (const event of sses) {
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -800,7 +801,7 @@ StreamMessageAsync(client).GetAwaiter().GetResult();
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
@@ -1086,7 +1087,7 @@ The last message in the stream has `finish_reason` set, indicating the reason fo
 
 ### Apply content safety
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
+The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
 The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
 
diff --git a/articles/ai-studio/how-to/model-catalog-overview.md b/articles/ai-studio/how-to/model-catalog-overview.md
@@ -78,6 +78,7 @@ The following list contains Serverless API models. For Azure OpenAI models, see
 Model | Managed compute | Serverless API (pay-per-token)
 --|--|--
 AI21 family models | Not available | Jamba-1.5-Mini <br> Jamba-1.5-Large
+Azure DeepSeek | Not available | DeepSeek-R1
 Cohere family models | Not available | Cohere-command-r-plus-08-2024 <br> Cohere-command-r-08-2024 <br> Cohere-command-r-plus <br> Cohere-command-r <br> Cohere-embed-v3-english <br> Cohere-embed-v3-multilingual <br> Cohere-rerank-v3-english <br> Cohere-rerank-v3-multilingual
 Gretel | Not available | Gretel-Navigator
 Healthcare AI family Models | MedImageParse<BR>  MedImageInsight<BR>  CxrReportGen<BR>  Virchow<BR>  Virchow2<BR>  Prism<BR>  BiomedCLIP-PubMedBERT<BR>  microsoft-llava-med-v1.5<BR>  m42-health-llama3-med4<BR>  biomistral-biomistral-7b<BR>  microsoft-biogpt-large-pub<BR>  microsoft-biomednlp-pub<BR>  stanford-crfm-biomedlm<BR>  medicalai-clinicalbert<BR>  microsoft-biogpt<BR>  microsoft-biogpt-large<BR>  microsoft-biomednlp-pub<BR> | Not Available
diff --git a/articles/ai-studio/includes/region-availability-maas.md b/articles/ai-studio/includes/region-availability-maas.md
@@ -10,6 +10,13 @@ ms.date: 08/05/2024
 ms.custom: include, references_regions
 ---
 
+### Azure DeepSeek models
+
+| Model | Offer Availability Region  | Hub/Project Region for Deployment  | Hub/Project Region for Fine tuning  |
+|---------|---------|---------|---------|
+DeepSeek-R1                       | Not applicable | East US <br> East US 2 <br> North Central US <br> South Central US <br> West US <br> West US 3  | Not available       |
+
+
 ### Cohere models
 
 
diff --git a/articles/machine-learning/how-to-custom-dns.md b/articles/machine-learning/how-to-custom-dns.md
diff --git a/articles/machine-learning/how-to-managed-network-compute.md b/articles/machine-learning/how-to-managed-network-compute.md
