Intro to GraphRAG
summary
Hands-on introduction that builds a talent graph in Neo4j from a CSV and two sample résumés, creates uniqueness constraints, loads ~154 nodes, stores 1536-dim embeddings, runs Leiden community detection to cluster skills, and materializes both semantic-similarity and hard-overlap relationships. Queries use Cypher plus vector indexes to count shared skills and compute a weighted similarity score. A small Langraph agent exposes four tools (retrieve person skills, find similar skills, person similarity, find people by skills) and successfully answers demo queries. Neo4j + Cypher and Langraph agent run end-to-end.
AI-written summary · about
chapters (7)
- 0:00Introduction and setup
- 9:00What is GraphRAG
- 16:46Building the skills graph
- 35:59Graph analytics and community detection
- 55:18Extracting skills from unstructured data
- 1:01:03LangGraph agent with retrieval tools
- 1:16:35Resources and Q&A
related talks
24mEmpowering Lifelong Learning: Transforming Data into Insights With GraphRAG
24mGraph-Powered Job Matcher: From SQL Tables to Neo4j RAG in Production
36mGraphRAG Explained 🔥 Building Smarter LLMs
01h 17mGraph Database and Retrieval Augmented Generation
39mEnhancing RAG with Neo4j Knowledge Graph
23mConnecting the Dots With Context Graphs
30mPerformant GraphRAG Improving Neo4j to Drive Autonomous AI ...
27mAdaptive Knowledge Graphs for Dynamic RAG Systems