←back to thread

KAG – Knowledge Graph RAG Framework

(github.com)
230 points taikon | 2 comments | 30 Dec 24 02:55 UTC | HN request time: 0s | source
Show context
isoprophlex ◴[30 Dec 24 06:49 UTC] No.42547133[source]▶
Fancy, I think, but again no word on the actual work of turning a few bazillion csv files and pdf's into a knowledge graph.

I see a lot of these KG tools pop up, but they never solve the first problem I have, which is actually constructing the KG itself.

replies(11): >>42547488 #>>42547556 #>>42547743 #>>42548481 #>>42549416 #>>42549856 #>>42549911 #>>42550327 #>>42551738 #>>42552272 #>>42562692 #
roseway4 ◴[30 Dec 24 15:01 UTC] No.42549856[source]▶
You may want to take a look at Graphiti, which accepts plaintext or JSON input and automatically constructs a KG. While it’s primarily designed to enable temporal use cases (where data changes over time), it works just as well with static content.

https://github.com/getzep/graphiti

I’m one of the authors. Happy to answer any questions.

replies(3): >>42549922 #>>42555303 #>>42555979 #
1. ganeshkrishnan ◴[31 Dec 24 00:51 UTC] No.42555303[source]▶
>uses OpenAI for LLM inference and embedding

This becomes a cyclical hallucination problem. The LLM hallucinates and create incorrect graph which in turn creates even more incorrect knowledge.

We are working on this issue of reducing hallucination in knowledge graphs and using LLM is not at all the right way.

replies(1): >>42585953 #
2. sc077y ◴[03 Jan 25 14:34 UTC] No.42585953[source]▶
Actually the rate of hallucination is not constant across the board. For one you're doing a sort of synthesis, not intense reasoning or retrieval with the llm. Second, the problem is segmented into sub problems much like how gpt-o1 or o3 does using CoT. Thus, the risk of hallucinations is significantly lower compared to a zero-shot raw LLM or even a naive RAG approach.