Meet KAG: Supercharging RAG Systems with Advanced Reasoning

31 Dec 2024 · 15 min
14:40

LARRUZ walks through KAG, which extends RAG by using knowledge graphs to preserve entity relationships and enable multi-hop reasoning. The tutorial demos OpenSPG running locally with Neo4j and shows how to ingest PDFs, extract entities, build a knowledge graph, and run multi-step questions that decompose queries before answering.

Questions this video answers

Apache license

MS SQL Server, Neo4j graph store, and the OpenSPG server

DeepSeek with model name uhdiepsichat

BGE/BGEM embeddings (BGM3 referenced), hosted locally via OLAMA; vector dimension 1024

SPO retriever (specialized retriever developed in the project)

Chapters

More from LARRUZ

8:49
youtube.com

OpenAI’s New AI Is Doing Things We Barely Understand

3d ago
5:38
youtube.com

DeepSeek Solved AI’s Memory Problem

4d ago
33:17
youtube.com

DeepMind's New AI Just Cracked The Code Of Life

1w ago
3:43
youtube.com

The Billion Dollar AI Advantage Is Disappearing

1w ago
5:14
youtube.com

Claude Opus 5.5 AI: An Incredible Leap Forward

3w ago
5:16
youtube.com

Yes, Jev Is Insane, But There's A Catch

3w ago
5:11
youtube.com

DeepSeek’s Insane New Architecture

4w ago
4:16
youtube.com

Claude Is Now Leaving Invisible Fingerprints In Its Text

1mo ago
9:18
youtube.com

I Never Thought I’d See This Happen

1mo ago
5:22
youtube.com

GPT-6 Astra Changes Everything

1mo ago
4:55
youtube.com

Claude Fable AI Is Much Stranger Than The Headlines Suggest

1mo ago
See all content