Merge pull request #5445 from MicrosoftDocs/main

6/9/2025 PM Publish

Author: Taojunshen

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

@@ -150,6 +150,7 @@ DeepSeek family of models includes DeepSeek-R1, which excels at reasoning tasks
 
 | Model  | Type | Capabilities | 
 | ------ | ---- | --- | 
+| [DeepSeek-R1-0528](https://ai.azure.com/explore/models/DeepSeek-R1-0528/version/1/registry/azureml-deepseek) <br /> | [chat-completion with reasoning content](../model-inference/how-to/use-chat-reasoning.md?context=/azure/ai-foundry/context/context) | - **Input:** text (163,840 tokens) <br /> - **Output:** text (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** No  <br /> - **Response formats:** Text |
 | [DeekSeek-V3-0324](https://ai.azure.com/explore/models/deepseek-v3-0324/version/1/registry/azureml-deepseek) | [chat-completion](../model-inference/how-to/use-chat-completions.md?context=/azure/ai-foundry/context/context) | - **Input:** text (131,072 tokens) <br /> - **Output:** (131,072 tokens) <br /> - **Tool calling:** No <br /> - **Response formats:** Text, JSON |
 | [DeepSeek-V3](https://ai.azure.com/explore/models/deepseek-v3/version/1/registry/azureml-deepseek) <br />(Legacy) | [chat-completion](../model-inference/how-to/use-chat-completions.md?context=/azure/ai-foundry/context/context) | - **Input:** text (131,072 tokens) <br /> - **Output:** text (131,072 tokens) <br />  - **Tool calling:** No <br /> - **Response formats:** Text, JSON |
 | [DeepSeek-R1](https://ai.azure.com/explore/models/deepseek-r1/version/1/registry/azureml-deepseek) | [chat-completion with reasoning content](../model-inference/how-to/use-chat-reasoning.md?context=/azure/ai-foundry/context/context) | - **Input:** text (163,840 tokens) <br /> - **Output:** text (163,840 tokens) <br />  - **Tool calling:** No <br /> - **Response formats:** Text. |

articles/ai-foundry/concepts/retrieval-augmented-generation.md

@@ -8,7 +8,7 @@ ms.custom:
   - ignite-2023
   - build-2024
 ms.topic: concept-article
-ms.date: 04/03/2025
+ms.date: 06/09/2025
 ms.reviewer: sgilley
 ms.author: sgilley
 author: sdgilley
@@ -20,7 +20,7 @@ This article talks about the importance and need for Retrieval Augmented Generat
 
 ## What is RAG?
 
-Some basics first. Large language models (LLMs) like ChatGPT are trained on public internet data that was available at the point in time when they were trained. They can answer questions related to the data they were trained on. This public data might not be sufficient to meet all your needs. You might want questions answered based on your private data. Or, the public data might simply be out of date. The solution to this problem is Retrieval Augmented Generation (RAG), a pattern used in AI that uses an LLM to generate answers with your own data.
+Some basics first. Large language models (LLMs) like ChatGPT are trained on public internet data that was available at the point in time when they were trained. They can answer questions related to the data they were trained on. The public data might not be sufficient to meet all your needs. You might want questions answered based on your private data. Or, the public data might just be out of date. The solution to this problem is Retrieval Augmented Generation (RAG), a pattern used in AI that uses an LLM to generate answers with your own data.
 
 ## How does RAG work?
 
@@ -31,11 +31,19 @@ RAG is a pattern that uses your data with an LLM to generate answers specific to
 
 ## What is an index and why do I need it?
 
-RAG uses your data to generate answers to the user question. For RAG to work well, we need to find a way to search and send your data in an easy and cost efficient manner to the LLMs. This is achieved by using an index. An index is a data store that allows you to search data efficiently. This index is very useful in RAG. An index can be optimized for LLMs by creating vectors (text data converted to number sequences using an embedding model). A good index usually has efficient search capabilities like keyword searches, semantic searches, vector searches, or a combination of these. This optimized RAG pattern can be illustrated as follows.
+RAG uses your data to generate answers to the user question. For RAG to work well, we need to find a way to search and send your data in an easy and cost efficient manner to the LLMs. An index solves this problem. An index is a data store that allows you to search data efficiently. This index is very useful in RAG. An index can be optimized for LLMs by creating vectors (text data converted to number sequences using an embedding model). A good index usually has efficient search capabilities like keyword searches, semantic searches, vector searches, or a combination of these features. This optimized RAG pattern can be illustrated as follows.
 
 :::image type="content" source="../media/index-retrieve/rag-pattern-with-index.png" alt-text="Screenshot of the RAG pattern with index." lightbox="../media/index-retrieve/rag-pattern-with-index.png":::
 
-Azure AI provides an index asset to use with RAG pattern. The index asset contains important information like where is your index stored, how to access your index, what are the modes in which your index can be searched, does your index have vectors, what is the embedding model used for vectors etc. The Azure AI index uses [Azure AI Search](/azure/search/search-what-is-azure-search) as the primary and recommended index store. Azure AI Search is an Azure resource that supports information retrieval over your vector and textual data stored in search indexes.
+Azure AI provides an index asset to use with RAG pattern. The index asset contains important information such as:
+
+* Where is your index stored?
+* How to access your index?
+* What are the modes in which your index can be searched?
+* Does your index have vectors?
+* What is the embedding model used for vectors?
+
+The Azure AI index uses [Azure AI Search](/azure/search/search-what-is-azure-search) as the primary and recommended index store. Azure AI Search is an Azure resource that supports information retrieval over your vector and textual data stored in search indexes.
 
 ## Next steps
 

articles/ai-foundry/faq.yml

@@ -8,7 +8,7 @@ metadata:
   ms.custom:
     - build-2024
   ms.topic: faq
-  ms.date: 01/17/2025
+  ms.date: 06/09/2025
   ms.reviewer: sgilley
   ms.author: sgilley
   author: sdgilley

articles/ai-foundry/includes/region-availability-maas.md

@@ -49,11 +49,11 @@ Cohere Embed v3 -  Multilingual    |  [Microsoft Managed Countries/Regions](/par
 
 | Model | Offer Availability Region  | Hub/Project Region for Deployment  | Hub/Project Region for Fine tuning  |
 |---------|---------|---------|---------|
+DeepSeek-R1-0528                  | 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       |
 DeepSeek-V3-0324                  | 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       |
 DeepSeek-V3                       | 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       |
 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       |
 
-
 ### Gretel models
 
 |Model  |Offer Availability Region  | Hub/Project Region for Deployment  | Hub/Project Region for Fine tuning  |

articles/ai-foundry/model-inference/concepts/models.md

@@ -59,6 +59,7 @@ DeepSeek family of models includes DeepSeek-R1, which excels at reasoning tasks
 
 | Model  | Type | Tier | Capabilities |
 | ------ | ---- | ---- | ------------ |
+| [DeepSeek-R1-0528]() <br /> | chat-completion | Global standard | - **Input:** text (163,840 tokens) <br /> - **Output:** text (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** No  <br /> - **Response formats:** Text  |
 | [DeepSeek-V3-0324](https://ai.azure.com/explore/models/deepseek-v3-0324/version/1/registry/azureml-deepseek) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:**  (131,072 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
 | [DeepSeek-R1](https://ai.azure.com/explore/models/deepseek-r1/version/1/registry/azureml-deepseek) | chat-completion <br /> [(with reasoning content)](../how-to/use-chat-reasoning.md) | Global standard | - **Input:** text (163,840 tokens) <br /> - **Output:**  (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** No <br /> - **Response formats:** Text. |
 | [DeepSeek-V3](https://ai.azure.com/explore/models/deepseek-v3/version/1/registry/azureml-deepseek) <br />(Legacy) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:**  (131,072 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** No <br /> - **Response formats:** Text, JSON |

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

@@ -1,5 +1,5 @@
 ---
-title: Video retrieval deprecation notice
+title: Video Retrieval deprecation notice
 titleSuffix: Azure AI services
 author: PatrickFarley
 manager: nitinme

articles/ai-services/computer-vision/index.yml

@@ -90,14 +90,6 @@ conceptualContent:
       footerLink:
         text: More
         url: overview-identity.md
-    - title: Video Analysis
-      links:
-        - itemType: overview
-          text: About Video Analysis
-          url: intro-to-spatial-analysis-public-preview.md
-        - itemType: how-to-guide
-          text: Call the Video Retrieval APIs
-          url: how-to/video-retrieval.md
     - title: Optical character recognition (legacy)
       links:
         - itemType: overview

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

@@ -1,59 +1,19 @@
 ---
-title: What is Video Analysis?
+title: What is Video Retrieval?
 titleSuffix: Azure AI services
-description: Learn about the basic concepts and features of Azure AI Vision Spatial Analysis and Video Retrieval.
+description: Learn about the basic concepts and features of Azure AI Vision Video Retrieval.
 author: PatrickFarley
 manager: nitinme
 ms.collection: "ce-skilling-fresh-tier2, ce-skilling-ai-copilot"
 ms.update-cycle: 365-days
 ms.author: pafarley
 ms.service: azure-ai-vision
 ms.topic: overview
-ms.date: 04/04/2025
+ms.date: 05/22/2025
 ms.custom: contperf-fy22q2, ignite-2022
 ---
 
-# What is Video Analysis?
-
-Video Analysis includes video-related features like Spatial Analysis and Video Retrieval.
-
-## Spatial Analysis
-
-[!INCLUDE [spatial-analysis-deprecation](includes/spatial-analysis-deprecation.md)]
-
-<!--
-You can use Azure AI Vision Spatial Analysis to detect the presence and movements of people in video. Ingest video streams from cameras, extract insights, and generate events to be used by other systems. The service can do things like count the number of people entering a space or measure compliance with face mask and social distancing guidelines. By processing video streams from physical spaces, you can learn how people use them and maximize the space's value to your organization.
-
-Try out the capabilities of Spatial Analysis quickly and easily in your browser by using Azure AI Vision Studio.
-
-> [!div class="nextstepaction"]
-> [Try Vision Studio](https://portal.vision.cognitive.azure.com/)
-
-
-### People counting
-
-This operation counts the number of people in a specific zone over time using the *PersonCount* operation. It generates an independent count for each frame processed without attempting to track people across frames. This operation can be used to estimate the number of people in a space or generate an alert when a person appears.
-
-:::image type="content" source="https://user-images.githubusercontent.com/11428131/139924111-58637f2e-f2f6-42d8-8812-ab42fece92b4.gif" alt-text="Animation showing how Spatial Analysis counts the number of people in the cameras field of view.":::
-
-### Entrance Counting
-
-This feature monitors how long people stay in an area or when they enter through a doorway. This monitoring can be done using the PersonCrossingPolygon or PersonCrossingLine operations. In retail scenarios, these operations can be used to measure wait times for a checkout line or engagement at a display. Also, these operations could measure foot traffic in a lobby or a specific floor in other commercial building scenarios.
-
-:::image type="content" source="https://user-images.githubusercontent.com/11428131/137016574-0d180d9b-fb9a-42a9-94b7-fbc0dbc18560.gif" alt-text="Animation showing frames of people moving in and out of a bordered space, with rectangles drawn around them.":::
-
-### Social distancing and face mask detection
-
-This feature analyzes how well people follow social distancing requirements in a space. The system uses the *PersonDistance* operation to automatically calibrate itself as people walk around in the space. Then it identifies when people violate a specific distance threshold (6 ft. or 10 ft.).
-
-:::image type="content" source="https://user-images.githubusercontent.com/11428131/139924062-b5e10c0f-3cf8-4ff1-bb58-478571c022d7.gif" alt-text="Animation showing how Spatial Analysis visualizes social distance violation events showing lines between people showing the distance.":::
-
-Spatial Analysis can also be configured to detect if a person is wearing a protective face covering such as a mask. A mask classifier can be enabled for the PersonCount, PersonCrossingLine, and PersonCrossingPolygon operations by configuring the `ENABLE_FACE_MASK_CLASSIFIER` parameter.
-
-:::image type="content" source="https://user-images.githubusercontent.com/11428131/137015842-ce524f52-3ac4-4e42-9067-25d19b395803.png" alt-text="Photograph showing how Spatial Analysis classifies whether people have facemasks in an elevator.":::
--->
-
-## Video Retrieval
+# What is Video Retrieval?
 
 [!INCLUDE [video-retrieval-deprecation](includes/video-retrieval-deprecation.md)]
 

articles/ai-services/computer-vision/overview.md

@@ -26,7 +26,7 @@ The Azure AI Vision service gives you access to advanced algorithms that process
 | [Optical Character Recognition (OCR)](overview-ocr.md)|The Optical Character Recognition (OCR) service extracts text from images. You can use the Read API to extract printed and handwritten text from photos and documents. It uses deep-learning-based models and works with text on various surfaces and backgrounds. These include business documents, invoices, receipts, posters, business cards, letters, and whiteboards. The OCR APIs support extracting printed text in [several languages](./language-support.md). Follow the [OCR quickstart](quickstarts-sdk/client-library.md) to get started.|
 |[Image Analysis](overview-image-analysis.md)| The Image Analysis service extracts many visual features from images, such as objects, faces, adult content, and auto-generated text descriptions. Follow the [Image Analysis quickstart](quickstarts-sdk/image-analysis-client-library-40.md) to get started.|
 | [Face](overview-identity.md) | The Face service provides AI algorithms that detect, recognize, and analyze human faces in images. Facial recognition software is important in many different scenarios, such as identification, touchless access control, and face blurring for privacy. Follow the [Face quickstart](quickstarts-sdk/identity-client-library.md) to get started. |
-| [Video Analysis](intro-to-spatial-analysis-public-preview.md)| Video Analysis includes video-related features like Video Retrieval. [Video Retrieval](/azure/ai-services/computer-vision/how-to/video-retrieval) lets you create an index of videos that you can search with natural language.|
+| [Video Retrieval](intro-to-spatial-analysis-public-preview.md)| Video Retrieval lets you create an index of videos that you can search with natural language. Follow the [how-to guide](/azure/ai-services/computer-vision/how-to/video-retrieval).|
 
 ## Azure AI Vision for digital asset management
 

articles/ai-services/computer-vision/toc.yml

@@ -312,9 +312,9 @@ items:
         href: https://aka.ms/azure-ai-vision-face-liveness-client-sdk-web-api-reference
       - name: Understand the liveness versions
         href: sdk/understand-the-liveness-sdk-versions.md
-- name: Video Analysis
+- name: Video Retrieval
   items:
-  - name: Video Analysis overview
+  - name: Video Retrieval overview
     href: intro-to-spatial-analysis-public-preview.md
   - name: Responsible use of AI
     items: