Connecting the Dots with Context Graphs
summary
Asserts that retrieval-only RAG loses decision provenance and shows concrete results: a Neo4j agent memory package backed context graph plus OpenAI embeddings and vector search lets the system traverse links to reveal a patient’s smoking history and prior operation for emphysema care and to surface a loan’s previous rejection surfaced along with related margin trades and fraud patterns; demo stack uses Neo4j, graph RAG, and a Next.js UI and the examples run and explain the model’s reasoning.
AI-written summary · about
chapters (7)
- 0:00Context graphs and AI revolution
- 2:22Escaping AI control matrix
- 6:13Storing memory in knowledge graphs
- 10:01Demo: Podcast knowledge graph
- 11:48Context graphs for business problems
- 13:09Demo: Loan approval system
- 16:00Conclusion
related talks
56mConnecting the Dots with Context Graphs
23mConnecting the Dots With Context Graphs
24mUnlocking AI's Hidden Connections With Graphs
36mAgentic GraphRAG: AI’s Logical Edge
24mAgentic GraphRAG: AI’s Logical Edge
30mAgentic RAG with Knowledge Graphs Explained
35mGraphRag in Action: Revolutionizing Fraud Detection Techniques
39mEnhancing RAG with Neo4j Knowledge Graph