rag concepts

Author: laujan

articles/ai-services/content-understanding/concepts/retrieval-augmented-generation.md

@@ -1,26 +1,24 @@
 ---
-title: Azure AI Content Understanding Retrieval Augmented Generation Concept
+title: Azure AI Content Understanding retrieval-augmented generation Concept
 titleSuffix: Azure AI services
-description: Learn about Retrieval Augmented Generation
+description: Learn about retrieval-augmented generation
 author: laujan
 ms.author: tonyeiyalla
 manager: nitinme
 ms.service: azure-ai-content-understanding
 ms.topic: overview
-ms.date: 03/16/2025
-ms.custom: 2025-understanding-release
+ms.date: 04/23/2025
 ---
-# Creating a Multimodal Retrieval Augmented Generation Solution with Content Understanding
 
-# Introduction
+# Retrieval-augmented generation with Content Understanding
 
-Retrieval Augmented Generation (RAG) enhances Generative AI models by grounding their responses in external knowledge sources, significantly improving accuracy, relevance, and reliability. A key challenge in RAG is effectively extracting and preparing multimodal content – documents, images, audio, and video – so that it can be accurately retrieved and used to inform the LLM's responses. 
+retrieval-augmented generation (RAG) enhances Generative AI models by grounding their responses in external knowledge sources, significantly improving accuracy, relevance, and reliability. A key challenge in RAG is effectively extracting and preparing multimodal content – documents, images, audio, and video – so that it can be accurately retrieved and used to inform the LLM's responses. 
 
 Azure AI Content Understanding addresses these challenges by providing sophisticated extraction capabilities across all content modalities, preserving semantic integrity and contextual relationships that traditional extraction methods often lose. This unified approach eliminates the need to manage separate workflows and models for different content types, streamlining implementation while ensuring optimal representation for retrieval and generation.
 
 ## Why Does Multimodal Data Matter for RAG?
 
-In traditional content processing, simple text extraction was sufficient for many use cases. However, modern enterprise environments contain rich, diverse information spread across multiple formats—documents with complex layouts, images conveying visual insights, audio recordings of crucial conversations, and videos that combine all these elements. For truly comprehensive Retrieval Augmented Generation (RAG) systems, all of this content must be accurately processed and made available to generative AI models. This ensures that when users pose questions, the underlying RAG system can retrieve relevant information regardless of its original format—whether it's a complex table in a financial report, a technical diagram in a manual, insights from a recorded conference call, or explanations from a training video.
+In traditional content processing, simple text extraction was sufficient for many use cases. However, modern enterprise environments contain rich, diverse information spread across multiple formats—documents with complex layouts, images conveying visual insights, audio recordings of crucial conversations, and videos that combine all these elements. For truly comprehensive retrieval-augmented generation (RAG) systems, all of this content must be accurately processed and made available to generative AI models. This ensures that when users pose questions, the underlying RAG system can retrieve relevant information regardless of its original format—whether it's a complex table in a financial report, a technical diagram in a manual, insights from a recorded conference call, or explanations from a training video.
 
 ## Capabilities of Content Understanding for Multimodal RAG
 
@@ -50,7 +48,7 @@ A high level summary of RAG implementation pattern looks like this:
 3. Store embedded vectors in database or search index.  
 4. Use Generative AI chat models to query and generate responses from retrieval systems.
 
-Here’s an overview of the implementation process, beginning with data extraction using Azure AI Content Understanding as the foundation for transforming raw multimodal data into structured, searchable formats optimized for RAG workflows:
+Here's an overview of the implementation process, beginning with data extraction using Azure AI Content Understanding as the foundation for transforming raw multimodal data into structured, searchable formats optimized for RAG workflows:
 
 ### 1. Content Extraction: The Foundation for RAG with Content Understanding
 
@@ -337,16 +335,16 @@ Below is an example showcasing the results of content and field extraction using
             "valueString": "Maria Smith contacted Contoso to inquire about her current point balance. Agent John Doe confirmed her identity and informed her that she has 599 points. Maria did not require any further information and the call ended on a positive note."
           },
           "TrainingTopics": {
-						"type": "array",
-						"valueArray": [
-							{
-								"type": "string",
-								"valueString": "Compliance"
-							},
-							{
-								"type": "string",
-								"valueString": "Risk mitigation"
-							},]
+                        "type": "array",
+                        "valueArray": [
+                            {
+                                "type": "string",
+                                "valueString": "Compliance"
+                            },
+                            {
+                                "type": "string",
+                                "valueString": "Risk mitigation"
+                            },]
           },
           "People": {
             "type": "array",
@@ -416,16 +414,16 @@ Below is an example showcasing the results of content and field extraction using
             "valueString": "The video begins with a view from a glass floor, showing a person's feet in white sneakers standing on it. The scene captures a downward view of a structure, possibly a tower, with a grid pattern on the floor and a clear view of the ground below. The lighting is bright, suggesting a sunny day, and the colors are dominated by the orange of the structure and the gray of the floor."
           },
           "KeyTopics": {
-						"type": "array",
-						"valueArray": [
-							{
-								"type": "string",
-								"valueString": "Flight delay"
-							},
-							{
-								"type": "string",
-								"valueString": "Customer service"
-							},
+                        "type": "array",
+                        "valueArray": [
+                            {
+                                "type": "string",
+                                "valueString": "Flight delay"
+                            },
+                            {
+                                "type": "string",
+                                "valueString": "Customer service"
+                            },
             ]
           }
         },

articles/ai-services/content-understanding/overview.md

@@ -41,7 +41,7 @@ Content Understanding offers a streamlined process to reason over large amounts
 
 * **Automation**. Content Understanding supports automation scenarios by converting unstructured content into structured data, which can be integrated into various workflows and applications. Confidence scores minimize human review and lower costs. For example, automate procurement and payment processes by extracting fields from invoices.
 
-* **Search and retrieval augmented generation (RAG)**. Content Understanding enables ingestion of content of any modality into the search index. The structured output representation improves the relevance for RAG scenarios.
+* **Search and retrieval-augmented generation (RAG)**. Content Understanding enables ingestion of content of any modality into the search index. The structured output representation improves the relevance for RAG scenarios.
 
 * **Analytics and reporting**: Content Understanding's extracted field outputs enhance analytics and reporting, allowing businesses to gain valuable insights, conduct deeper analysis, and make informed decisions based on accurate reports.
 

articles/ai-services/content-understanding/toc.yml

@@ -65,13 +65,14 @@ items:
     - name: Accuracy and confidence
       displayName: accuracy, confidence, analyzers, optimization, fields, scores
       href: concepts/accuracy-confidence.md
-    - name: Retrieval Augmented Generation (RAG)
+    - name: Retrieval-augmented generation (RAG)
       displayName: RAG, retrieval, augmented, generation, knowledge, base, search, index, vector
       href: concepts/retrieval-augmented-generation.md
 - name: Tutorials
   items:
-    - name: Retrieval Augmented Generation Tutorial
-      href: tutorial/RAG-tutorial.md
+    - name: Build a retrieval-augmented solution
+      displayName: RAG, retrieval, augmented, generation, knowledge, base, search, index, vector
+      href: tutorial/rag-tutorial.md
 - name: Responsible AI
   items:
     - name: Transparency note

articles/ai-services/content-understanding/tutorial/RAG-tutorial.md renamed to articles/ai-services/content-understanding/tutorial/retrieval-augmented-generation.md

@@ -1,7 +1,7 @@
 ---
-title: Azure AI Content Understanding Retrieval Augmented Generation Tutorial
+title: Azure AI Content Understanding retrieval-augmented generation Tutorial
 titleSuffix: Azure AI services
-description: Learn about Retrieval Augmented Generation
+description: Learn about retrieval-augmented generation
 author: laujan
 ms.author: tonyeiyalla
 manager: nitinme
@@ -11,9 +11,9 @@ ms.date: 04/05/2025
 ms.custom: 2025-understanding-release
 ---
 
-# Tutorial: Building a Multimodal Retrieval Augmented Generation (RAG) Solution with Content Understanding
+# Tutorial: Building a Multimodal retrieval-augmented generation (RAG) Solution with Content Understanding
 
-This tutorial provides a comprehensive guide to building a Retrieval Augmented Generation (RAG) solution using Azure AI Content Understanding. It explains the essential components required to design and implement a robust RAG system, highlights best practices for optimizing relevance and accuracy, and outlines the integration points with other Azure services. By the end of this tutorial, you will have a clear understanding of how to leverage Content Understanding to process multimodal data, enhance retrieval precision, and enable generative AI models to deliver contextually rich and accurate responses.
+This tutorial provides a comprehensive guide to building a retrieval-augmented generation (RAG) solution using Azure AI Content Understanding. It explains the essential components required to design and implement a robust RAG system, highlights best practices for optimizing relevance and accuracy, and outlines the integration points with other Azure services. By the end of this tutorial, you will have a clear understanding of how to leverage Content Understanding to process multimodal data, enhance retrieval precision, and enable generative AI models to deliver contextually rich and accurate responses.
 
 ## Exercises Covered in This Tutorial
 

articles/ai-services/document-intelligence/concept/analyze-document-response.md

@@ -167,7 +167,7 @@ When *output=figures* is specified during the initial `Analyze` operation, the s
 
 #### Sections
 
-Hierarchical document structure analysis is pivotal in organizing, comprehending, and processing extensive documents. This approach is vital for semantically segmenting long documents to boost comprehension, facilitate navigation, and improve information retrieval. The advent of [Retrieval Augmented Generation (RAG)](../concept/retrieval-augmented-generation.md) in document generative AI underscores the significance of hierarchical document structure analysis. The Layout model supports sections and subsections in the output, which identifies the relationship of sections and object within each section. The hierarchical structure is maintained in `elements` of each section.
+Hierarchical document structure analysis is pivotal in organizing, comprehending, and processing extensive documents. This approach is vital for semantically segmenting long documents to boost comprehension, facilitate navigation, and improve information retrieval. The advent of [retrieval-augmented generation (RAG)](../concept/retrieval-augmented-generation.md) in document generative AI underscores the significance of hierarchical document structure analysis. The Layout model supports sections and subsections in the output, which identifies the relationship of sections and object within each section. The hierarchical structure is maintained in `elements` of each section.
 
 ```json
 {

articles/ai-services/document-intelligence/faq.yml

@@ -56,7 +56,7 @@ sections:
 
           - With Azure AI Document Intelligence and Azure OpenAI combined, you can build an enterprise application to seamlessly interact with your documents using natural language. You can easily find answers, gain valuable insights, and generate new and engaging content from existing documents.
 
-          - You can find more details on the [retrieval augmented generation pattern here](concept/retrieval-augmented-generation.md).
+          - You can find more details on the [retrieval-augmented generation pattern here](concept/retrieval-augmented-generation.md).
 
       - question: |
          Can Document Intelligence help with semantic chunking within documents for retrieval-augmented generation?

articles/ai-services/document-intelligence/prebuilt/layout.md

@@ -526,7 +526,7 @@ if result.figures:
 
 ### Sections
 
-Hierarchical document structure analysis is pivotal in organizing, comprehending, and processing extensive documents. This approach is vital for semantically segmenting long documents to boost comprehension, facilitate navigation, and improve information retrieval. The advent of [Retrieval Augmented Generation (RAG)](../concept/retrieval-augmented-generation.md) in document generative AI underscores the significance of hierarchical document structure analysis. The Layout model supports sections and subsections in the output, which identifies the relationship of sections and object within each section. The hierarchical structure is maintained in `elements` of each section. You can use [output response to markdown format](#output-response-to-markdown-format) to easily get the sections and subsections in markdown.
+Hierarchical document structure analysis is pivotal in organizing, comprehending, and processing extensive documents. This approach is vital for semantically segmenting long documents to boost comprehension, facilitate navigation, and improve information retrieval. The advent of [retrieval-augmented generation (RAG)](../concept/retrieval-augmented-generation.md) in document generative AI underscores the significance of hierarchical document structure analysis. The Layout model supports sections and subsections in the output, which identifies the relationship of sections and object within each section. The hierarchical structure is maintained in `elements` of each section. You can use [output response to markdown format](#output-response-to-markdown-format) to easily get the sections and subsections in markdown.
 
 #### [Sample code](#tab/sample-code)