Advanced Retrieval-Augmented Generation

Bridging Large Language Models and Knowledge Graphs
1. Auflage 2026
ISBN: 978-1-394-37468-7
Verlag: John Wiley & Sons Inc

Buch, Englisch, 560 Seiten

Build Accurate, Grounded, and Trustworthy AI Systems with Retrieval-Augmented Generation

Large language models are powerful—but they hallucinate. Advanced Retrieval-Augmented Generation offers a complete guide from the foundations of information retrieval (IR) to the cutting-edge frontiers of RAG. Bridging large language models (LLMs) and knowledge graphs (KGs), this book provides the theoretical principles, practical techniques, and hands-on frameworks needed to build reliable AI systems that minimize hallucinations and improve factual correctness. The book covers core concepts of Graph-RAG with applications across search, recommendation, and enterprise AI. Practical chapters demonstrate implementations using LlamaIndex, Neo4j, and leading Graph-RAG frameworks.

Readers will learn: - IR and LLM fundamentals — model paradigms, transformer architecture, model families, training techniques, prompt engineering, applications, and limitations
- RAG pipeline engineering — chunking, indexing, retrieval, ranking, and generation
- KG construction and analytics — schema design, extraction techniques, graph algorithms, embeddings, and GNNs
- Graph-RAG architectures and evaluation — graph-based retrieval, graph-assisted generation, hybrid LLM–KG workflows, frameworks, benchmarks, and metrics
- Emerging directions — multimodal KGs, dynamic graphs, explainable RAG, RL-based traversal, and enterprise-scale implementations

With extensive hands-on examples and production-ready patterns, Advanced Retrieval-Augmented Generation is an indispensable resource for AI practitioners, ML engineers, researchers, and architects building the next generation of reliable, knowledge-grounded AI systems.

Autoren/Hrsg.

Wei, Wendy Ran

Wu, Huijun

Fachgebiete

• Mathematik | Informatik EDV | Informatik EDV & Informatik Allgemein
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz
• Mathematik | Informatik EDV | Informatik Daten / Datenbanken

Inhaltsverzeichnis

Foreword xiii
Preface xv
Acknowledgments xix
Introduction xxi

Part I From Traditional Information Retrieval to Modern RAG 1

1 Information Retrieval 3
1.1 Definition and Historical Evolution 3
1.2 Information Retrieval Components 14
1.3 Information Retrieval Applications 34
1.4 Challenges with IR Systems 45
1.5 Summary 46

2 Large Language Models 49
2.1 LLMs Overview 49
2.2 LLM Use Case in Information Retrieval 91
2.3 Challenges of LLMs for Information Retrieval 108
2.4 Summary 119

3 Retrieval-augmented Generation 123
3.1 RAG Overview 123
3.2 Data Preparation and Indexing 126
3.3 Retrieval Approaches 139
3.4 Generation 148
3.5 Summary 153

4 Practice: RAG Implementation 157
4.1 Overview of LangChain and LlamaIndex 157
4.2 Implementing RAG Pipelines with LlamaIndex 159
4.3 Example: Implementing RAG on the WANDS Dataset 175
4.4 Implementing Agentic RAG 189
4.5 Summary 195

Part II Graphs and Knowledge Graphs 197

5 Graphs and Graph Databases 199
5.1 Introduction to Graphs 199
5.2 Graph Databases: Comparison and Analysis 217
5.3 Introduction to Neo4j and Cypher 221
5.4 Practice: Flight Network Analysis and Optimization 228
5.5 Summary 244

6 Knowledge Graphs 247
6.1 Understanding KGs 247
6.2 Construction and Management of KGs 261
6.3 KGs Analytics and Enrichment 268
6.4 LLMs and KGs 287
6.5 Practice: Constructing KG from the WANDS Dataset 293
6.6 Practice: Construct KG from Unstructured Data 301
6.7 Summary 303

Part III Integrate RAG with Graph 307

7 Graph-based Retrieval-augmented Generation 309
7.1 Introduction to Graph-RAG 309
7.2 Architecture and Components of Graph-RAG 315
7.3 Applications 337
7.4 Summary 340

8 Practice: Graph-RAG Implementations 345
8.1 Graph-RAG on WANDS Dataset with LlamaIndex 345
8.2 Graph-RAG on Wiki and Kaggle Data with LangChain 352
8.3 Summary 364

9 Graph-RAG Evaluations 367
9.1 Performance Metrics Framework 367
9.2 Quality Assessment Methodologies 382
9.3 Benchmarking Frameworks 392
9.4 Tools and Platforms for Graph-RAG Evaluations 396
9.5 Practice: Evaluating RAG Pipelines Using Ragas 400
9.6 Summary 402

Part IV Advanced Implementations and Frontiers 405

10 Graph-RAG Frameworks for Enhanced Information Retrieval 407
10.1 Overview of Graph-RAG Frameworks for Search and Recommendations 407
10.2 Graph-RAG Tools and Softwares Overview 421
10.3 Practice: Run Graph-RAG Frameworks 424
10.4 Summary 453

11 Frontiers of Graph-RAG 455
11.1 Emerging Trends in Graph-RAG 455
11.2 Ethical Considerations and Bias Mitigation 478
11.3 Future Research Directions 482
11.4 Summary 490
11.5 Conclusion and Final Thoughts 491

A Set Up Experiment Servers 495
A.1 Two Models Hosted by vLLM 497
A.2 LLM Gateway 499
A.3 UI for LLM Models 500
A.4 Vector Store 500
A.5 Graph Database 501

B Prepare Synthetic Recommendation Data from WANDS 503
B.1 Step 1: Download the WANDS Dataset 503
B.2 Step 2: Load the Dataset 503
B.3 Step 3: Prepare the Data for Recommendation Tasks 504
B.4 Step 4: Generate Synthetic Recommendation Data 504
B.5 Step 5: Dataset Statistics and Sample Entries 509

Index 511

Über Autor(innen)

Wendy Ran Wei, PhD, is an expert in AI, ML, and LLMs, specializing in search and recommendation systems. She is a Machine Learning Engineer at Airbnb, where she develops retrieval and ranking models and brings LLM technologies into production. She previously held engineering roles at Meta, Pinterest, and Twitter, building large-scale search and recommendation solutions. Dr. Wei received her PhD in Statistics from The Ohio State University.

Huijun Wu, PhD, is an Engineer at Samsung Research America with expertise in large-scale distributed systems and data processing. He received his PhD in Computer Science from Arizona State University.