more updates

Author: HeidiSteen

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

@@ -28,12 +28,14 @@ The decision about which information retrieval system to use is critical because
 
 + Integration with embedding models for indexing, and chat models or language understanding models for retrieval.
 
-Azure AI Search is a [proven solution for information retrieval](https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/README.md) in a RAG architecture. It provides indexing and query capabilities, with the infrastructure and security of the Azure cloud. Through code and other components, you can design a comprehensive RAG solution that includes all of the elements for generative AI over your proprietary content. 
+Azure AI Search is a [proven solution for information retrieval](https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/README.md) in a RAG architecture. It provides indexing and query capabilities, with the infrastructure and security of the Azure cloud. Through code and other components, you can design a comprehensive RAG solution that includes all of the elements for generative AI over your proprietary content.
+
+You can choose between two approaches for RAG workloads: agentic retrieval, or the original query architecture for classic RAG.
 
 > [!NOTE]
 > New to copilot and RAG concepts? Watch [Vector search and state of the art retrieval for Generative AI apps](https://www.youtube.com/watch?v=lSzc1MJktAo).
 
-## Modern RAG with Agentic Retrieval
+## Option 1: Modern RAG with Agentic Retrieval
 
 Azure AI Search now provides **agentic retrieval**, a specialized pipeline designed specifically for RAG patterns. This approach uses large language models to intelligently break down complex user queries into focused subqueries, executes them in parallel, and returns structured responses optimized for chat completion models.
 
@@ -49,7 +51,7 @@ You need new objects for this pipeline: one or more knowledge sources, a knowled
 
 For new RAG implementations, we recommend starting with [agentic retrieval](agentic-retrieval-overview.md). For existing solutions, consider migrating to take advantage of improved accuracy and context understanding.
 
-## Classic RAG pattern for Azure AI Search
+## Option 2: Classic RAG pattern for Azure AI Search
 
 A RAG solution can be implemented on Azure AI Search using the original query execution environment. This approach is faster and simpler with fewer components, and depending on your application requirements it can be the best choice. There's no LLM query planning or LLM integration in the query pipeline. Your application sends a single query request to Azure AI Search, the search engine executes the query and returns search results. There's no query execution details in the response, and citations are built into the response only if you have fields in your index that provide a parent document name or page.
 
@@ -79,14 +81,6 @@ The information retrieval system provides the searchable index, query logic, and
 
 The LLM receives the original prompt, plus the results from Azure AI Search. The LLM analyzes the results and formulates a response. If the LLM is ChatGPT, the user interaction might consist of multiple conversation turns. An Azure solution most likely uses Azure OpenAI, but there's no hard dependency on this specific service.
 
-## Choosing between agentic retrieval and classic RAG
-
-Try a few quickstarts using your own data to understand the development effort and compare outcomes:
-
-+ [Quickstart: Agentic search](search-get-started-agentic-retrieval.md)
-
-+ [Quickstart: Classic RAG using grounding data from Azure AI Seach](search-get-started-rag.md)
-
 ## Searchable content in Azure AI Search
 
 In Azure AI Search, all searchable content is stored in a search index that's hosted on your search service. A search index is designed for fast queries with millisecond response times, so its internal data structures exist to support that objective. To that end, a search index stores *indexed content*, and not whole content files like entire PDFs or images. Internally, the data structures include inverted indexes of [tokenized text](https://lucene.apache.org/core/7_5_0/test-framework/org/apache/lucene/analysis/Token.html), vector indexes for embeddings, and unaltered plain text for cases where verbatim matching is required (for example, in filters, fuzzy search, regular expression queries).
@@ -233,6 +227,12 @@ We recommend the [Azure OpenAI demo](https://github.com/Azure-Samples/azure-sear
 
 There are many ways to get started, including code-first solutions and demos.
 
+For help with choosing between agentic retrieval and classic RAG, try a few quickstarts using your own data to understand the development effort and compare outcomes:
+
++ [Quickstart: Agentic search](search-get-started-agentic-retrieval.md)
+
++ [Quickstart: Classic RAG using grounding data from Azure AI Seach](search-get-started-rag.md)
+
 ### [**Docs**](#tab/docs)
 
 + [Try this agentic retrieval quickstart](search-get-started-rag.md) to walk through the new and recommended approach for RAG.

articles/search/search-get-started-rag.md

@@ -8,14 +8,17 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2024
 ms.topic: quickstart
-ms.date: 07/09/2025
+ms.date: 10/15/2025
 zone_pivot_groups: programming-languages-ai-search-rag-qs
 ---
 
 # Quickstart: Classic generative search (RAG) using grounding data from Azure AI Search
 
 In this quickstart, you send queries to a chat completion model for a conversational search experience over your indexed content on Azure AI Search. After setting up Azure OpenAI and Azure AI Search resources in the Azure portal, you run code to call the APIs.
 
+> [!NOTE]
+> We now recommend [agentic retrieval](search-get-started-agentic-retrieval.md) for RAG workflows, but classic RAG is simpler. If it meets your application requirements, it's still a good choice.
+
 ::: zone pivot="csharp"
 
 [!INCLUDE [.NET quickstart](includes/quickstarts/search-get-started-rag-dotnet.md)]

articles/search/toc.yml

@@ -152,9 +152,9 @@ items:
       href: tutorial-document-extraction-image-verbalization.md
     - name: Verbalize images from a structured document layout
       href: tutorial-document-layout-image-verbalization.md
-  - name: RAG tutorials
+  - name: Classic RAG tutorials
     items:
-    - name: Build a RAG solution
+    - name: Build a classic RAG solution
       href: tutorial-rag-build-solution.md
     - name: Choose models
       href: tutorial-rag-build-solution-models.md