https://github.com/tomasonjo/kg-rag
Supporting repository for the Essential GraphRAG book published by Manning
https://github.com/tomasonjo/kg-rag
chatbot graph llm neo4j openai rag
Last synced: 4 months ago
JSON representation
Supporting repository for the Essential GraphRAG book published by Manning
- Host: GitHub
- URL: https://github.com/tomasonjo/kg-rag
- Owner: tomasonjo
- Created: 2023-12-17T20:53:45.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2025-07-22T14:39:07.000Z (11 months ago)
- Last Synced: 2025-07-22T16:26:33.101Z (11 months ago)
- Topics: chatbot, graph, llm, neo4j, openai, rag
- Language: Jupyter Notebook
- Homepage: https://www.manning.com/books/knowledge-graph-enhanced-rag
- Size: 146 KB
- Stars: 29
- Watchers: 3
- Forks: 9
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Essential GraphRAG
A practical guide to building production-quality Retrieval Augmented Generation (RAG) systems using knowledge graphs for enhanced accuracy, traceability, and performance.
Link: [https://mng.bz/4Jy5](https://mng.bz/4Jy5)
## About
**Essential GraphRAG** demonstrates how to harness knowledge graphs to supercharge your RAG systems. While traditional RAG relies on vector similarity, GraphRAG leverages structured relationships in data to deliver more relevant and comprehensive context to LLMs.
## What You'll Learn
- Benefits of using Knowledge Graphs in RAG systems
- Implementing GraphRAG systems from scratch
- Building production-ready RAG pipelines
- Constructing knowledge graphs using LLMs
- Evaluating RAG pipeline performance
- Vector similarity-based retrieval approaches
- Working with semantic layers and agentic RAG
- Generating Cypher statements for graph queries
## Key Features
- **Practical Examples**: Vector similarity search tools, Agentic RAG applications, and performance evaluation
- **Production-Ready**: Learn to extract structured knowledge from text and deploy real-world systems
- **Hybrid Approach**: Combine vector-based and graph-based retrieval methods
- **Comprehensive**: From basic concepts to advanced implementation techniques
## Why GraphRAG?
Traditional RAG systems struggle with complex relationships and context. GraphRAG solves this by:
- Modeling data relationships explicitly in knowledge graphs
- Providing richer, more relevant prompts to LLMs
- Reducing hallucinations through structured context
- Enabling better traceability and explainability
## Target Audience
This book is perfect for developers, data scientists, and AI engineers looking to build sophisticated RAG systems that go beyond simple vector similarity search.
---
*Build RAG systems that truly understand your data's relationships and deliver accurate, contextual responses.*