Graph Mastery to AI
summary
Argues that mastering graph tech is now imperative and shows concrete systems: Neo4j plus LangChain feeding a vector DB and GPT-based retriever, a web crawler that scrapes pages and PDFs into a graph index, and production use for contact tracing, fraud detection, recommendation and task scheduling. Describes algorithms used (BFS/DFS, shortest path, DAGs, cycle detection, topological sort), practical fixes (title/keyword indexing, grouping, sliding windows, reranking) and a jump from ~400 to ~1,000 chunks in practice that improves answers. Highlights Neo4j + vector DB hybrid retriever and assembled search that makes vector+keyword+graph+Q lookup.
AI-written summary · about
chapters (6)
- 0:00Introduction to graph AI
- 1:49Graph types and uses
- 8:19Graph databases and Neo4j
- 20:27Graph traversal algorithms
- 37:38Graph RAG and hybrid search
- 58:53Summary and key takeaways
related talks
27mWhen Vectors Aren’t Enough: Unlocking AI’s Hidden Connections with Graphs
26mGraph Databases will change your (freakin') life
49mModern Graph Databases
39mEnhancing RAG with Neo4j Knowledge Graph
01h 17mGraph Database and Retrieval Augmented Generation
30mAgentic RAG with Knowledge Graphs Explained
38mKnowledge Graphs : Adding a New Dimension to Vector Search and Generative AI
55mA Practical Guide to Graph Databases