Making OSS AI Real with Knowledge Graphs
summary
Clear claim: combining Knowledge Graphs with retrieval (the GraphRAG pattern) gives grounded, long‑range context that pure vector RAG misses. Concrete tools and artifacts shown: Neo4j integration, LangChain and LlamaIndex connectors, the open‑source LM Graph Builder, SEC/EDGAR notebooks and a Graph Academy course. Surprising data point: an open‑source component reportedly hit 1.5 billion machines were updated. Emphasis on human‑validated facts and demos that build and query graphs, not just slides about theory.
AI-written summary · about
chapters (8)
- 0:00Knowledge graphs and OSS AI
- 7:08What are knowledge graphs
- 10:19Graph RAG vs vector RAG
- 13:27Open Source Science KG
- 18:47Financial forums graph RAG
- 24:08OSS ecosystem for graph RAG
- 32:13Resources for KG development
- 35:29Q&A
related talks
53mPractical GraphRAG - Making LLMs smarter with Knowledge Graphs
26mPractical GraphRAG Making LLMs smarter with Knowledge Graphs
36mAgentic GraphRAG: AI’s Logical Edge
27mLies, Damn Lies, and AIs
20mBeyond RAG: Building the AI Corporate Brain with Knowledge Graphs and Virtue Ethics
38mLeveraging Knowledge Graphs for RAG: A Smarter Approach to Contextual AI Applications
32mGraphRAG: Powering Up LLMs with Knowledge Graphs
20mPractical GraphRAG: Making LLMs smarter with Knowledge Graphs