Essential GraphRAG: Knowledge Graph-Enhanced RAG

by Tomaz Bratanic, Oscar hane

Upgrade your RAG applications with the power of knowledge graphs.

Retrieval Augmented Generation (RAG) is a great way to harness the power of generative AI for information not contained in a LLM’s training data and to avoid depending on LLM for factual information. However, RAG only works when you can quickly identify and supply the most relevant context to your LLM. Essential GraphRAG shows you how to use knowledge graphs to model your RAG data and deliver better performance, accuracy, traceability, and completeness.

Inside Essential GraphRAG you’ll

• The benefits of using Knowledge Graphs in a RAG system
• How to implement a GraphRAG system from scratch
• The process of building a fully working production RAG system
• Constructing knowledge graphs using LLMs
• Evaluating performance of a RAG pipeline

Essential GraphRAG is a practical guide to empowering LLMs with RAG. You’ll learn to deliver vector similarity-based approaches to find relevant information, as well as work with semantic layers, deliver agentic RAG, and generate Cypher statements to retrieve data from a knowledge graph.

About the technology

A Retrieval Augmented Generation (RAG) system automatically selects and supplies domain-specific context to an LLM, radically improving its ability to generate accurate, hallucination-free responses. The GraphRAG pattern employs a knowledge graph to structure the RAG’s input, taking advantage of existing relationships in the data to generate rich, relevant prompts.

About the book

Essential GraphRAG shows you how to build and deploy a production-quality GraphRAG system. You’ll learn to extract structured knowledge from text and how to combine vector-based and graph-based retrieval methods. The book is rich in practical examples, from building a vector similarity search retrieval tool and an Agentic RAG application, to evaluating performance and accuracy, and more.

What's inside

• Embeddings, vector similarity search, and hybrid search
• Turning natural language into Cypher database queries
• Microsoft’s GraphRAG pipeline
• Agentic RAG

About the reader

For readers with intermediate Python skills and some experience with a graph database like Neo4j.

About the author

The author of Manning’s Graph Algorithms for Data Science and a contributor to LangChain and LlamaIndex, Tomaž Bratanic has extensive experience with graphs, machine learning, and generative AI. Oskar Hane leads the Generative AI engineering team at Neo4j.

Table of Contents

1 Improving LLM accuracy
2 Vector similarity search and hybrid search
3 Advanced vector retrieval strategies
4 Generating Cypher queries from natural language questions
5 Agentic RAG
6 Constructing knowledge graphs with LLMs
7 Microsoft’s GraphRAG implementation
8 RAG application evaluation
A The Neo4j environment

176 pages, Paperback

Published September 2, 2025

Reviews

[Tony Holdroyd · Rating 5 out of 5]

To effectively utilise GenAI with new data, various methods have emerged; however, a leading contender is RAG (Retrieval Augmented Generation). Extra factual information is supplied to the model. This data needs to be supplied in a way that the model can use accurately and efficiently. Enter GraphRAG. If you want to harness this power, then the Manning publication ‘Essential GraphRAG’ by Tomaž Bratanič and Oskar Hane is the resource you should seriously consider. This excellent and highly practical book demonstrates, and will teach you, all you need to know about exploiting the concepts and techniques of RAG and GraphRAG in your own applications. It comprehensively covers all the essential ground from improving accuracy by retrieving external data using RAG through search and retrieval techniques, query rewriting, the use of data structured into knowledge graphs and onward to agentic systems and evaluation methods. If you are working in this area or want to get into it, then this fine book should be at the top of your reading list.
https://mng.bz/eoZJ

[Adail Retamal · Rating 5 out of 5]

Retrieval-Augmented Generation (RAG) has evolved from a cutting-edge innovation into a cornerstone method for enhancing large language model (LLM) outputs. Yet, depending solely on vector-based similarity falls short when it comes to achieving sophisticated levels of information retrieval and response generation. Enter knowledge graphs (KGs)—the next frontier—and in "Essential RAG", the authors masterfully trace their evolution while providing clear, actionable guidance on integrating KGs to elevate the reliability and precision of our AI companions.

What sets this book apart are its practical examples: insightful, hands-on, and ready to adapt as prototypes for your own projects. A must-read for anyone pushing the boundaries of LLM applications.

[Pete Aven · Rating 5 out of 5]

Excellent! So useful. It's a practitioners guide to using LLMs for knowledge graph creation as well as interrogation and information retrieval. Python workbooks walk you through the practical application and implementation hands-on. A great primer that demonstrates the concepts and their utility in action, giving you the start you need to make use of your own data and start getting results from it quickly. Incredibly useful.

[Hung Pham · Rating 5 out of 5]

- LLMs is pretty unreliable, so often additional facts need providing to make the response useful.
- Start from the basic of RAG - chunk splitting, vector search, hybrid search to complete production pipeline with query rewriting.
- Go over the basic of Neo4j and Cypher language to represent knowledge in the form of graph.

[Harpal · Rating 4 out of 5]

A good book for an introduction to RAG pipelines using graphs. Heavily based on neo4j but concepts can be applied widely.

[Kiana · Rating 5 out of 5]

متن روون، جزئیات به اندازه.