Merge branch 'main' of github.com:MicrosoftDocs/azure-ai-docs-pr into sdg-fix-qs

Author: sdgilley

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

@@ -348,6 +348,15 @@ The Stability AI collection of image generation models include Stable Image Core
 | [Stable Image Core](https://ai.azure.com/explore/models/Stable-Image-Core/version/1/registry/azureml-stabilityai) | Image generation | - **Input:** text (1000 tokens)  <br /> - **Output:** 1 Image  <br />  - **Tool calling:** No <br /> - **Response formats:** Image (PNG and JPG) |
 | [Stable Image Ultra](https://ai.azure.com/explore/models/Stable-Image-Ultra/version/1/registry/azureml-stabilityai) | Image generation | - **Input:** text (1000 tokens)  <br /> - **Output:** 1 Image  <br />  - **Tool calling:** No <br /> - **Response formats:** Image (PNG and JPG) |
 
+### xAI
+
+xAI's Grok 3 and Grok 3 Mini models are designed to excel in various enterprise domains. Grok 3, a non-reasoning model pre-trained by the Colossus datacenter, is tailored for business use cases such as data extraction, coding, and text summarization, with exceptional instruction-following capabilities. It supports a 131,072 token context window, allowing it to handle extensive inputs while maintaining coherence and depth, and is particularly adept at drawing connections across domains and languages. On the other hand, Grok 3 Mini is a lightweight reasoning model trained to tackle agentic, coding, mathematical, and deep science problems with test-time compute. It also supports a 131,072 token context window for understanding codebases and enterprise documents, and excels at using tools to solve complex logical problems in novel environments, offering raw reasoning traces for user inspection with adjustable thinking budgets.
+
+| Model  | Type | Capabilities |
+| ------ | ---- | ------------ |
+| [grok-3](https://ai.azure.com/explore/models/grok-3/version/1/registry/azureml-xai) | chat-completion | - **Input:** text (131,072 tokens) <br /> - **Output:** text (131,072 tokens) <br /> - **Languages:** `en` <br />  - **Tool calling:** yes <br /> - **Response formats:** text |
+| [grok-3-mini](https://ai.azure.com/explore/models/grok-3-mini/version/1/registry/azureml-xai) | chat-completion |  - **Input:** text (131,072 tokens) <br /> - **Output:** text (131,072 tokens) <br /> - **Languages:** `en` <br />  - **Tool calling:** yes <br /> - **Response formats:** text |
+
 #### Inference examples: Stability AI
 
 Stability AI models deployed via standard deployment implement the Foundry Models API on the route `/image/generations`.
@@ -358,15 +367,6 @@ For examples of how to use Stability AI models, see the following examples:
 - [Use Requests library with Stable Diffusion 3.5 Large for image to image requests](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/stabilityai/Image_to_Image.ipynb)
 - [Example of a fully encoded image generation response](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/stabilityai/Sample_image_generation_response.txt)
 
-### xAI
-
-**Grok** is a family of models designed...
-
-| Model  | Type | Tier | Capabilities |
-| ------ | ---- | --- | ------------ |
-| [Grok]() |  | Global standard | - **Input:** text (0 tokens) <br /> - **Output:** text (0 tokens) <br /> - **Languages:**  <br />  - **Tool calling:**  <br /> - **Response formats:**  |
-| [grok-3-mini]() |  | Global standard | - **Input:** text (0 tokens) <br /> - **Output:** text (0 tokens) <br /> - **Languages:**  <br />  - **Tool calling:**  <br /> - **Response formats:**  |
-
 
 ## Related content
 

articles/ai-foundry/foundry-local/get-started.md

@@ -35,13 +35,18 @@ Also, ensure you have administrative privileges to install software on your devi
 
 Get started with Foundry Local quickly:
 
-1. [**Download Foundry Local Installer**](https://aka.ms/foundry-local-installer) and **install** by following the on-screen prompts. 
-    > [!TIP]
-    > If you're installing on Windows, you can also use `winget` to install Foundry Local. Open a terminal window and run the following command:
-    >
-    > ```powershell
-    > winget install Microsoft.FoundryLocal
-    > ```
+1. **Install Foundry Local** 
+    - **Windows**: Open a terminal and run the following command:
+        ```bash
+        winget install Microsoft.FoundryLocal
+        ```
+    - **macOS**: Open a terminal and run the following command:
+        ```bash
+        brew tap microsoft/foundrylocal
+        brew install foundrylocal
+        ```
+    Alternatively, you can download the installer from the [Foundry Local GitHub repository](https://aka.ms/foundry-local-installer).
+
 1. **Run your first model** Open a terminal window and run the following command to run a model: 
 
     ```bash

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

@@ -114,13 +114,6 @@ TimeGEN-1  | [Microsoft Managed Countries/Regions](/partner-center/marketplace/t
 |---------|---------|---------|---------|
 tsuzumi-7b    | [Microsoft Managed Countries/Regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions) | East US 2 <br> South Central US <br> East US <br> West US 3 <br> West US <br> North Central US       |  East US 2 <br> East US <br> North Central US <br> South Central US <br> West US <br> West US 3      |
 
-### xAI
-
-| Model | Offer Availability Region  | Hub/Project Region for Deployment  | Hub/Project Region for Fine tuning  |
-|---------|---------|---------|---------|
-grok-3  | [Microsoft Managed Countries/Regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions)    |       |  Not available       |
-grok-3-mini  | [Microsoft Managed Countries/Regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions)    |       |  Not available       |
-
 
 ### Stability AI models
 

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

@@ -208,13 +208,12 @@ See [this model collection in Azure AI Foundry portal](https://ai.azure.com/expl
 
 ### xAI
 
-**Grok** is a family of models designed...
+xAI's Grok 3 and Grok 3 Mini models are designed to excel in various enterprise domains. Grok 3, a non-reasoning model pre-trained by the Colossus datacenter, is tailored for business use cases such as data extraction, coding, and text summarization, with exceptional instruction-following capabilities. It supports a 131,072 token context window, allowing it to handle extensive inputs while maintaining coherence and depth, and is particularly adept at drawing connections across domains and languages. On the other hand, Grok 3 Mini is a lightweight reasoning model trained to tackle agentic, coding, mathematical, and deep science problems with test-time compute. It also supports a 131,072 token context window for understanding codebases and enterprise documents, and excels at using tools to solve complex logical problems in novel environments, offering raw reasoning traces for user inspection with adjustable thinking budgets.
 
 | Model  | Type | Tier | Capabilities |
 | ------ | ---- | --- | ------------ |
-| [Grok]() |  | Global standard | - **Input:** text (0 tokens) <br /> - **Output:** text (0 tokens) <br /> - **Languages:**  <br />  - **Tool calling:**  <br /> - **Response formats:**  |
-| [grok-3-mini]() |  | Global standard | - **Input:** text (0 tokens) <br /> - **Output:** text (0 tokens) <br /> - **Languages:**  <br />  - **Tool calling:**  <br /> - **Response formats:**  |
-
+| [grok-3](https://ai.azure.com/explore/models/grok-3/version/1/registry/azureml-xai) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** text (131,072 tokens) <br /> - **Languages:** `en` <br />  - **Tool calling:** yes <br /> - **Response formats:** text |
+| [grok-3-mini](https://ai.azure.com/explore/models/grok-3-mini/version/1/registry/azureml-xai) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** text (131,072 tokens) <br /> - **Languages:** `en` <br />  - **Tool calling:** yes <br /> - **Response formats:** text |
 
 ## Open and protected models
 

articles/ai-services/agents/concepts/agent-catalog.md

@@ -5,7 +5,7 @@ description: This article provides instructions on how to use the AI agent catal
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 04/29/2025
+ms.date: 05/18/2025
 ms.author: aahi
 author: aahill
 ---
@@ -59,25 +59,22 @@ A full list of agent samples in the catalog can be found on the Azure AI Foundry
 | [AI Red Teaming Agent](https://github.com/microsoft/agent-catalog/tree/main/semantic-kernel-blueprints/ai-red-teaming-agent) | Facilitates the development of a copilot to accelerate your AI red teaming process: through multi-agent system that automates the generation, transformation, and execution of harmful prompts against target generative AI models or applications for AI red teaming purposes. Useful for streamlining safety testing workflows, surfacing guardrail bypasses, and guiding risk mitigation planning. | Microsoft | Multi-agent | Semantic Kernel | Advanced | N/A |
 | [Saifr Communication Compliance Agent](https://aka.ms/saifr-communication-agent) | The Saifr Communication Compliance Agent identifies potentially noncompliant text and generates a more compliant, fair, and balanced version, helping end users better adhere to relevant regulatory guidelines | Saifr from Fidelity Labs | Single-agent | Agent AI Agent Service | Intermediate | OpenAPI Specified Tool |
 | [Auquan Due Diligence Risk Analyst](https://aka.ms/due-diligence-risk-analyst-agent) | Helps create agents that assess risks across financial, operational, regulatory, and ESG domains | Auquan | Single-agent | Agent AI Agent Service | Intermediate | OpenAPI Specified Tool |
-| [Healthcare Multi-agent Orchestrator](https://aka.ms/healthcare-multi-agent) | Facilitates the development and testing of  modular specialized agents that coordinate across diverse data types and tools like M365 and Teams to assist multi-disciplinary healthcare workflows—such as cancer care. | Microsoft | Multi-agent | Semantic Kernel | Advanced |  |
+| [Healthcare Agent Orchestrator](https://aka.ms/healthcare-multi-agent) | Facilitates the development and testing of  modular specialized agents that coordinate across diverse data types and tools like M365 and Teams to assist multi-disciplinary healthcare workflows—such as cancer care. | Microsoft | Multi-agent | Semantic Kernel | Advanced |  |
 | [ResearchFlow Agent](https://aka.ms/research-flow) | Helps create agents that execute complex, multi-step research workflows and solve open-ended tasks | Microsoft | Multi-agent | Agent AI Agent Service | Advanced |  |
 | [Magentic-One Agent](https://aka.ms/magnetic-one) | A generalist, autonomous multi-agent system that performs deep research and problem-solving by orchestrating web search, code generation, and code execution agents. Helpful for tackling open-ended analytical or technical tasks. | Microsoft | Multi-agent | Agent AI Agent Service | Advanced |  |
 | [SightMachine Filler Optimization Agent](https://aka.ms/sight-machine-filler-optimization-agent) | The SightMachine Filler Optimization Agent supports building agents that analyze manufacturing data to reduce bottlenecks and improve throughput via predictive insights | SightMachine | Single-agent | Agent AI Agent Service | Intermediate | Azure Functions |
 | [Marquee Insights AI News Agent](https://aka.ms/ai-news-agent) | Enables creating an agent that retrieves and summarize news focused on Microsoft, healthcare, and legal sectors | Marquee Insights | Single-agent | Agent AI Agent Service | Intermediate |  |
-| [MiHCM HR Assist Agent](https://aka.ms/ hr-agent) | Supports agent development for HR scenarios by enabling employees to navigate HR-related records like leave balances, HR requests and work activities using MiHCM's HR APIs | MiHCM | Single-agent | Agent AI Agent Service | Intermediate | OpenAPI Specified Tool |
-| [Claim Concierge](https://aka.ms/claim-concierge) | Helps create agents for multi-lingual claim navigation | Microsoft | Multi-agent | Agent AI Agent Service | Beginner | Connected Agents, File Search, Grounding with Bing, Code Interpreter |
+| [MiHCM HR Assist Agent](https://aka.ms/hr-agent) | Supports agent development for HR scenarios by enabling employees to navigate HR-related records like leave balances, HR requests and work activities using MiHCM's HR APIs | MiHCM | Single-agent | Agent AI Agent Service | Intermediate | OpenAPI Specified Tool |
 | [Portfolio Navigator](https://aka.ms/trusty-link) | Supports agent creation for exploring financial topics from Morningstar data and Grounding with Bing | Microsoft | Single-agent | Agent AI Agent Service | Beginner | Morningstar, Grounding with Bing |
 | [Travel Planner](https://aka.ms/travel-planner) | Enables agent creation for travel scenarios | Microsoft | Single-agent | Agent AI Agent Service | Beginner | File Search, Code Interpreter, Tripadvisor, OpenAPI Specified Tool |
 | [Home Loan Guide](https://aka.ms/home-loan-guide) | Enables agent creation to provide users with helpful information about mortgage applications at a fictitious company, Contoso Bank. | Microsoft | Single-agent | Agent AI Agent Service | Beginner | Connected Agents, File Search, Code Interpreter, Grounding with Bing |
 | [Sales Analyst Agent](https://aka.ms/sales-analyst) | Supports building agents that analyze sales data | Microsoft | Single-agent | Agent AI Agent Service | Beginner | File Search, Code Interpreter |
 | [Customer Service Agent](https://aka.ms/customer-service) | Helps create a multi-agent system that manages full-cycle support resolution —from authentication to escalation to resolution | Microsoft | Multi-agent | Agent AI Agent Service | Advanced |  |
 | [Warranty Claim Processing Agent](https://aka.ms/warranty-claim-processing) | Facilitates the development of agents for processing warranty claims | Microsoft | Single-agent | Semantic Kernel | Intermediate | OpenAPI Specified Tool |
 | [Voice Live Agent](https://aka.ms/voice-live-agent) | Enables agent development for real-time, voice-based interactions using Azure AI Voice Live API. | Microsoft | Single-agent | Agent AI Agent Service  | Intermediate |  |
-| [Meeting Prep Agent](https://aka.ms/meeting-prep-agent) | Helps build an agent that helps with meetings by researching attendees and generating contextual summaries | Microsoft | Single-agent | Agent AI Agent Service | Intermediate | Grounding with Bing, Azure Logic Apps |
-| [CommsPilot](https://aka.ms/comms-pilot) | Enables agent creation for personalized outbound sales emails and outreach logging | Microsoft | Single-agent | Agent AI Agent Service | Intermediate | File Search, Grounding with Bing, Azure Logic Apps |
 | [Text Translation Agent](https://aka.ms/translation-agent) | Helps create agents that handle multilingual text processing, including dynamic language detection and bidirectional translation using Azure AI Translator service | Microsoft | Single-agent | Agent AI Agent Service | Beginner | OpenAPI Specified Tool |
 | [Video Translation Agent](https://aka.ms/video-translation-agent) | Supports building agents for multilingual video localization with translation, subtitles, and speech generation | Microsoft | Single-agent | Semantic Kernel | Beginner | N/A |
 | [Intent Routing Agent](https://aka.ms/intent-routing) | Helps create agents that detect user intent and provide exact answering. Perfect for deterministically intent routing and exact question answering with human controls. | Microsoft | Single-agent | Agent AI Agent Service | Beginner | OpenAPI Specified Tool |
 | [Exact Question Answering Agent](https://aka.ms/exact-question-answering) | Supports building agents that answer predefined, high-value questions to ensure consistent and accurate responses. | Microsoft | Single-agent | Agent AI Agent Service | Beginner | OpenAPI Specified Tool |
 | [Contract Analysis Agent](https://aka.ms/contract-analysis-agent) | Enables creating agents that compare contract versions, extract key clauses, highlight differences, and generate review-ready reports. | Microsoft | Single-agent | Semantic Kernel | Intermediate | File Search, OpenAPI Specified Tool |
-| [SOP Forge Agent](https://aka.ms/sop-forge-agent) | Helps create an agent that converts instructional videos into a fully formatted Standard Operating Procedure (SOP). | Microsoft | Single-agent | Semantic Kernel | Intermediate | File Search, OpenAPI Specified Tool |
+| [SOP Forge Agent](https://aka.ms/sop-forge-agent) | Helps create an agent that converts instructional videos into a fully formatted Standard Operating Procedure (SOP). | Microsoft | Single-agent | Semantic Kernel | Intermediate | File Search, OpenAPI Specified Tool |

articles/search/index.yml

@@ -1,10 +1,10 @@
 ### YamlMime:Landing
 
 title: Azure AI Search documentation # < 60 chars
-summary: Information retrieval at scale for agentic RAG, with vector and text content in traditional or generative search scenarios.
+summary: Information retrieval at scale for agentic retrieval, with vector and text content in traditional or generative search scenarios.
 metadata:
   title: Azure AI Search documentation
-  description: Information retrieval at scale for agentic RAG, with vector and text content in traditional or generative search scenarios.
+  description: Information retrieval at scale for agentic retrieval, with vector and text content in traditional or generative search scenarios.
   ms.service: azure-ai-search
   ms.custom:
     - ignite-2023
@@ -43,13 +43,13 @@ landingContent:
             url: vector-search-how-to-query.md
 
   # Card
-  - title: Agentic RAG
+  - title: Agentic retrieval and vectors
     linkLists:
       - linkListType: concept
         links:
           - text: Retrieval Augmented Generation (RAG)
             url: retrieval-augmented-generation-overview.md
-          - text: Agentic RAG
+          - text: Agentic retrieval
             url: search-agentic-retrieval-concept.md        
           - text: Vector search
             url: vector-search-overview.md

articles/search/retrieval-augmented-generation-overview.md

@@ -58,7 +58,7 @@ A high-level summary of the pattern looks like this:
 + Send it to Azure AI Search to find relevant information.
 + Return the top ranked search results to an LLM.
 + Use the natural language understanding and reasoning capabilities of the LLM to generate a response to the initial prompt.
-+ Optionally, use agentic RAG where an agent evaluates an answer and finds a better one if the original answer is incomplete or low quality.
++ Optionally, use agentic retrieval where an agent evaluates an answer and finds a better one if the original answer is incomplete or low quality.
 
 Azure AI Search provides inputs to the LLM prompt, but doesn't train the model. In RAG architecture, there's no extra training. The LLM is pretrained using public data, but it generates responses that are augmented by information from the retriever, in this case, Azure AI Search.