←back to thread

KAG – Knowledge Graph RAG Framework

(github.com)
230 points taikon | 1 comments | 30 Dec 24 02:55 UTC | HN request time: 0.203s | source
Show context
dcreater ◴[30 Dec 24 06:01 UTC] No.42546890[source]▶
Yet another RAG/knowledge graph implementation.

At this point, the onus is on the developer to prove it's value through AB comparisons versus traditional RAG. No person/team has the bandwidth to try out this (n + 1) solution.

replies(2): >>42546979 #>>42550357 #
1. TrueDuality ◴[30 Dec 24 15:51 UTC] No.42550357[source]▶
This is actually the first project I've seen that is actually doing any kind of knowledge graph generation. Most are just precomputing similarity scores as edges between document snippets that act as their nodes. People have basically been calling their vector databases with an index a knowledge graph.

This is actually attempting fact extraction into an ontology so you can reason over this instead of reasoning in the LLM.