Grounded Intelligence Boosting LLMs with Real-Time Graph Context
summary
Claims that combining live graph queries with LLMs cuts hallucinations and raises answer precision by adding relationship-aware context; implementation uses Neo4j as the graph store, the open-source Neo4j Knowledge Graph Builder to ingest PDFs/CSV/APIs, LLMs (OpenAI/SageMaker/Vertex) for entity extraction, a retriever that runs vector similarity plus Cypher graph traversals, a prompt constructor, and a GraphRAG Python package for orchestration; eBay-style production usage since 2016 and two years of Neo4j in production are cited as working evidence.
AI-written summary · about
chapters (13)
- 0:00Introduction to Graph RAG
- 1:51Limitations of traditional RAG
- 4:45What is a knowledge graph
- 8:22How Graph RAG works
- 12:21Graph RAG architecture
- 15:43Pros of Graph RAG over vector RAG
- 18:41Implementing Graph RAG
- 20:29Demo of Knowledge Graph Builder
- 21:56Graph RAG Python package
- 23:19Comparison with vector RAG
- 24:04Case study eBay
- 25:31Getting started resources
- 26:36Closing and next steps
related talks
41mEnhancing LLMs with Graph Technology
52mGive Your LLMs a Left Brain
44mGive Your LLMs a Left Brain
20mPractical GraphRAG: Making LLMs smarter with Knowledge Graphs
23mKnowledge Graphs and LLMs in Action
26mPractical GraphRAG Making LLMs smarter with Knowledge Graphs
53mPractical GraphRAG - Making LLMs smarter with Knowledge Graphs
49mPower up LLMs to be Factual Ninjas using GraphRAG