Practical GraphRAG Making LLMs smarter with Knowledge Graphs
summary
Shows how GraphRAG combines vector search with a knowledge graph and live demos using Neo4j Workspace and the LLM Graph Builder, ingesting web pages, PDFs and CSVs. Demonstrates building a Vermont special-education graph, importing 523 rows to produce 72 nodes, 431 documents and ~319 relationships, and generating entity-chunk links for RAG and explainability. Mentions Microsoft Research GraphRAG concepts, LangChain/python integration and that query latency is usually dominated by LLM API calls rather than graph traversal.
AI-written summary · about
chapters (12)
- 0:00Introduction to GraphRAG
- 1:01Understanding RAG and Graphs
- 3:08Graph Database Components
- 5:12Advantages of GraphRAG
- 7:52GraphRAG Patterns and Usage
- 9:36Getting Started Tips
- 11:15Modeling Data with Arrows
- 13:14Using the LLM Graph Builder
- 15:46Live Demo: Importing Data
- 20:42Exploring the Generated Graph
- 24:06Tools and Resources
- 25:11Integrating Microsoft GraphRAG
related talks
53mPractical GraphRAG - Making LLMs smarter with Knowledge Graphs
20mPractical GraphRAG: Making LLMs smarter with Knowledge Graphs
32mGraphRAG: Powering Up LLMs with Knowledge Graphs
49mPower up LLMs to be Factual Ninjas using GraphRAG
36mGraphRAG Explained 🔥 Building Smarter LLMs
28mEnhancing LLMs with Graph Technology
36mAgentic GraphRAG: AI’s Logical Edge
27mLies, Damn Lies, and AIs