Merge pull request #3657 from MicrosoftDocs/main

3/21/2025 AM Publish

Author: Taojunshen

articles/ai-foundry/concepts/models-featured.md

@@ -19,15 +19,7 @@ The Azure AI model catalog offers a large selection of models from a wide range
 
 [!INCLUDE [models-preview](../includes/models-preview.md)]
 
-To perform inferencing with the models, some models such as [Nixtla's TimeGEN-1](#nixtla) and [Cohere rerank](#cohere-rerank) require you to use custom APIs from the model providers. Others that belong to the following model types support inferencing using the [Azure AI model inference](../model-inference/overview.md):
-
-- [Chat completion](../model-inference/how-to/use-chat-completions.md?context=/azure/ai-foundry/context/context)
-- [Chat completion (with reasoning content)](../model-inference/how-to/use-chat-reasoning.md?context=/azure/ai-foundry/context/context)
-- [Chat completion (with image and audio content)](../model-inference/how-to/use-chat-multi-modal.md?context=/azure/ai-foundry/context/context)
-- [Embeddings](../model-inference/how-to/use-embeddings.md?context=/azure/ai-foundry/context/context)
-- [Image embeddings](../model-inference/how-to/use-image-embeddings.md?context=/azure/ai-foundry/context/context)
-
-You can find more details about individual models by reviewing their model cards in the [model catalog for Azure AI Foundry portal](https://ai.azure.com/explore/models).
+To perform inferencing with the models, some models such as [Nixtla's TimeGEN-1](#nixtla) and [Cohere rerank](#cohere-rerank) require you to use custom APIs from the model providers. Others support inferencing using the [Azure AI model inference](../model-inference/overview.md). You can find more details about individual models by reviewing their model cards in the [model catalog for Azure AI Foundry portal](https://ai.azure.com/explore/models).
 
 :::image type="content" source="../media/models-featured/models-catalog.gif" alt-text="An animation showing Azure AI studio model catalog section and the models available." lightbox="../media/models-featured/models-catalog.gif":::
 

articles/ai-foundry/model-inference/concepts/deployment-types.md

@@ -29,15 +29,15 @@ To learn more about deployment options for Azure OpenAI models see [Azure OpenAI
 
 ## Deployment types for Models-as-a-Service models
 
-Models from third-party model providers with pay-as-you-go billing (collectively called Models-as-a-Service), makes models available in Azure AI model inference under **standard** deployments with a Global processing option (`Global-Standard`). 
+Models with pay-as-you-go billing (collectively called Models-as-a-Service), makes models available in Azure AI model inference under **standard** deployments with a Global processing option (`Global-Standard`). 
+
+> [!TIP]
+> Models-as-a-Service offers regional deployment options under [Serverless API endpoints](../../../ai-studio/how-to/deploy-models-serverless.md) in Azure AI Foundry. However, those deployments can't be accessed using the Azure AI model inference endpoint in Azure AI Services and they need to be created within a project.
 
 ### Global-Standard
 
 Global deployments leverage Azure's global infrastructure to dynamically route traffic to the data center with best availability for each request. Global standard provides the highest default quota and eliminates the need to load balance across multiple resources. Data stored at rest remains in the designated Azure geography, while data may be processed for inferencing in any Azure location. Learn more about [data residency](https://azure.microsoft.com/explore/global-infrastructure/data-residency/).
 
-> [!NOTE]
-> Models-as-a-Service offers regional deployment options under [Serverless API endpoints](../../../ai-studio/how-to/deploy-models-serverless.md) in Azure AI Foundry. Prompts and outputs are processed within the geography specified during deployment. However, those deployments can't be accessed using the Azure AI model inference endpoint in Azure AI Services.
-
 ## Control deployment options
 
 Administrators can control which model deployment types are available to their users by using Azure Policies. Learn more about [How to control AI model deployment with custom policies](../../../ai-studio/how-to/custom-policy-model-deployment.md).

articles/ai-foundry/model-inference/includes/use-chat-multi-modal/java.md

@@ -14,7 +14,6 @@ ms.custom: references_regions, tool_generated
 zone_pivot_groups: azure-ai-inference-samples
 ---
 
-This article explains how to use chat completions API with models supporting images or audio deployed to Azure AI model inference in Azure AI services.
 This article explains how to use chat completions API with _multimodal_ models deployed to Azure AI model inference in Azure AI services. Apart from text input, multimodal models can accept other input types, such as images or audio input.
 
 ## Prerequisites

articles/ai-foundry/model-inference/toc.yml

@@ -66,6 +66,8 @@ items:
         href: ./how-to/configure-entra-id.md
       - name: Control model deployment with custom policies
         href: ./how-to/configure-deployment-policies.md
+      - name: Use virtual networks
+        href: ../../ai-services/cognitive-services-virtual-networks.md?context=/azure/ai-foundry/model-inference/context/context
   - name: Manage cost
     href: ./how-to/manage-costs.md
   - name: Quotas and limits
@@ -88,7 +90,7 @@ items:
           href: ./how-to/use-chat-completions.md
         - name: Work with reasoning models
           href: ./how-to/use-chat-reasoning.md
-        - name: Work with image and audio content
+        - name: Work with multimodal models
           href: ./how-to/use-chat-multi-modal.md
     - name: Develop with LangChain and LangGraph
       href: ../how-to/develop/langchain.md?context=/azure/ai-foundry/model-inference/context/context
@@ -113,4 +115,4 @@ items:
         - name: Get Image Embeddings
           href: /rest/api/aifoundry/model-inference/get-image-embeddings/get-image-embeddings
     - name: Azure OpenAI API
-      href: /azure/ai-services/openai/reference?context=/azure/ai-foundry/model-inference/context/context
+      href: /azure/ai-services/openai/reference

articles/ai-foundry/toc.yml

@@ -130,7 +130,7 @@ items:
           href: ../ai-foundry/model-inference/how-to/use-chat-completions.md?context=/azure/ai-foundry/context/context
         - name: Work with reasoning models
           href: ../ai-foundry/model-inference/how-to/use-chat-reasoning.md?context=/azure/ai-foundry/context/context
-        - name: Work with image and audio content
+        - name: Work with multimodal models
           href: ../ai-foundry/model-inference/how-to/use-chat-multi-modal.md?context=/azure/ai-foundry/context/context
 - name: Azure OpenAI and AI services
   items:
@@ -565,6 +565,8 @@ items:
   items:
   - name: Azure AI Projects SDK
     href: /python/api/overview/azure/ai-projects-readme
+  - name: Azure AI Evaluation SDK
+    href: /python/api/overview/azure/ai-evaluation-readme
   - name: Azure Machine Learning Python SDK
     href: /python/api/overview/azure/ai-ml-readme
   - name: Azure Machine Learning REST API

articles/ai-services/cognitive-services-data-loss-prevention.md

@@ -42,14 +42,14 @@ There are two parts to enable data loss prevention. First, the resource property
 
     ```azurecli-interactive
     az rest -m get \
-        -u /subscriptions/{subscription ID}/resourceGroups/{resource group}/providers/Microsoft.CognitiveServices/accounts/{account name}?api-version=2021-04-30 \
+        -u /subscriptions/{subscription ID}/resourceGroups/{resource group}/providers/Microsoft.CognitiveServices/accounts/{account name}?api-version=2024-10-01 \
     ```
 
 1. Configure the restrictOutboundNetworkAccess property and update the allowed FqdnList with the approved URLs
 
     ```azurecli-interactive
     az rest -m patch \
-        -u /subscriptions/{subscription ID}/resourceGroups/{resource group}/providers/Microsoft.CognitiveServices/accounts/{account name}?api-version=2021-04-30 \
+        -u /subscriptions/{subscription ID}/resourceGroups/{resource group}/providers/Microsoft.CognitiveServices/accounts/{account name}?api-version=2024-10-01 \
         -b '{"properties": { "restrictOutboundNetworkAccess": true, "allowedFqdnList": [ "microsoft.com" ] }}'
     ```
 
@@ -65,7 +65,7 @@ There are two parts to enable data loss prevention. First, the resource property
         ResourceProviderName = 'Microsoft.CognitiveServices'
         ResourceType = 'accounts'
         Name = 'myaccount'
-        ApiVersion = '2021-04-30'
+        ApiVersion = '2024-10-01'
         Method = 'GET'
     }
     Invoke-AzRestMethod @getParams
@@ -79,7 +79,7 @@ There are two parts to enable data loss prevention. First, the resource property
         ResourceProviderName = 'Microsoft.CognitiveServices'
         ResourceType = 'accounts'
         Name = 'myaccount'
-        ApiVersion = '2021-04-30'
+        ApiVersion = '2024-10-01'
         Payload = '{"properties": { "restrictOutboundNetworkAccess": true, "allowedFqdnList": [ "microsoft.com" ] }}'
         Method = 'PATCH'
     }

articles/ai-services/computer-vision/how-to/video-retrieval.md

@@ -16,6 +16,8 @@ ms.author: pafarley
 
 # Do video retrieval using vectorization (version 4.0 preview)
 
+[!INCLUDE [video-retrieval-deprecation](../includes/video-retrieval-deprecation.md)]
+
 Azure AI Video Retrieval APIs are part of Azure AI Vision and enable developers to create a media index, add documents (videos and images) to it, and search it with natural language. Developers can define metadata schemas for each index and ingest metadata to the service to help with retrieval. Developers can also specify which features to extract from the index (vision, speech) and filter their search based on features.
 
 ## Prerequisites

articles/ai-services/computer-vision/includes/video-retrieval-deprecation.md

@@ -0,0 +1,44 @@
+---
+title: Video retrieval deprecation notice
+titleSuffix: Azure AI services
+#services: cognitive-services
+author: PatrickFarley
+manager: nitinme
+ms.service: azure-ai-vision
+ms.topic: include
+ms.date: 03/21/2025
+ms.collection: "ce-skilling-fresh-tier2, ce-skilling-ai-copilot"
+ms.author: pafarley
+---
+
+> [!IMPORTANT]
+> On 30 June 2025, Azure AI Vision Video Retrieval will be retired. The decision to retire this feature is part of our ongoing effort to improve and simplify and improve the features offered for video processing. Migrate to Azure AI Content Understanding and Azure AI Search to benefit from their additional capabilities.
+>
+> **Video processing: Video Retrieval vs Azure AI Content Understanding**
+>
+>|Feature |	Video Retrieval for video description |	Azure AI Content Understanding|
+>|---|---|---|
+Video Length Supported|Optimized for short videos, up to ~3 minutes|Supports short & long videos, up to 4 hours|
+>|Frame Processing|Up to 20 frames|Batch processing, sampling shot-by-shot sampled across entire video|
+>|Content Extraction Pre-Processing|Transcription|Transcription, Shot identification, Face grouping|
+>|Structured Output Support|Not supported|Supports schema-conforming structured outputs|
+>|Data types|Video supported|Video, images, documents, and speech supported|
+>|Pricing|Variable Token-based|Fixed cost per minute of video processed|
+> 
+> To migrate to Content Understanding for video summaries and descriptions, we'd recommend reviewing the [Azure AI Content Understanding](/azure/ai-services/content-understanding/video/overview) documentation.
+>
+>
+> **Video Search: Video Retrieval vs. Azure AI Search and Content Understanding**
+>
+>|Feature |	Video Retrieval for video search |	Azure AI Search and Content Understanding|
+>|---|---|---|
+|Visual Embedding type|Frame-based Image Embeddings|Video description text embeddings|
+|Content Extraction Pre-Processing|Transcription, OCR|Transcription, Shot identification, Face grouping|
+|People & Object search support|Strong support|Strong support|
+|Action and Event support|Limited|Strong support|
+|Customization|None|Content Understanding analyzer can be customized to focus using the fields and field descriptions|
+>
+> To start building the search use case with Content Understanding, we recommend starting with this [sample](https://aka.ms/Content-Understanding-Video-Search) which shows how to use Azure AI Search to search videos.
+>
+> To avoid service disruptions, migrate by 30 June 2025.
+

articles/ai-services/computer-vision/intro-to-spatial-analysis-public-preview.md

@@ -53,6 +53,8 @@ Spatial Analysis can also be configured to detect if a person is wearing a prote
 
 ## Video Retrieval
 
+[!INCLUDE [video-retrieval-deprecation](includes/video-retrieval-deprecation.md)]
+
 Video Retrieval is a service that lets you create a search index, add documents (videos and images) to it, and search with natural language. Developers can define metadata schemas for each index and ingest metadata to the service to help with retrieval. Developers can also specify what features to extract from the index (vision, speech) and filter their search based on features.
 
 > [!div class="nextstepaction"]

articles/ai-services/computer-vision/reference-video-search.md

@@ -16,6 +16,8 @@ ms.author: pafarley
 
 # Video Retrieval API reference
 
+[!INCLUDE [video-retrieval-deprecation](includes/video-retrieval-deprecation.md)]
+
 ## Authentication
 
 Include the following headers when making a call to any API in this document.