Wisdom-Driven Knowledge Augmented Generation at Scale
summary
Claims that a Wisdom-Driven Knowledge Graph boosts quantitative Knowledge-Augmented Generation vs vector RAG, implemented as a graph DB + Cypher backend with n8n orchestration and a multi-agent wisdom agent that can call OpenAI Anthropic or on‑prem models. Builds a competitive-analysis chatbot that pulls market data, runs multihop queries, executes function calls for precise numbers and uses a hybrid extraction + human pruning pipeline. Benchmarks report 91% accuracy and 85% flexibility; system runs from a Docker LLM-graph-stack.
AI-written summary · about
chapters (11)
- 0:00Introduction to Patho AI and KAG
- 1:09Defining Knowledge and Knowledge Graphs
- 1:56KAG vs. RAG
- 2:37The Wisdom-Decision Making-Situation Diagram
- 6:26Practical Application: Competitive Analysis Chatbot
- 8:37Implementation with N8n and Multi-Agent System
- 11:37Why Use Knowledge Graphs over RAG
- 14:01Challenges with Vector RAG and Numerical Reasoning
- 15:34Building KAG Systems and Hybrid Models
- 16:45Graph Extraction and Benchmarks
- 17:42Conclusion and Resources
related talks
42mMaking OSS AI Real with Knowledge Graphs
12mAgentic GraphRAG: Autonomous Knowledge Graph Construction and Adaptive Retrieval
21mAgentic GraphRAG: Autonomous Knowledge Graph Construction and Adaptive Retrieval
29mKnowledge graph based chatbots
27mLies, Damn Lies, and AIs
28mAgentic GraphRAG: Multi-Agent Knowledge Graph
32mMulti-Agent Query Generation w/ LLMs on Complex Knowledge Graphs
28mBuilding Knowledge Graph-Based Agents with Structured Text Generation