Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

KAG – Knowledge Graph RAG Framework

github.com

Post reply on HN
Print view View original

31–40 of 81 posts

Re: KAG – Knowledge Graph RAG Framework

#31

Post by washadjeffmad »

swyx wrote: post #19
kergonath wrote: post #12

Earlier quoted context omitted.

> 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. I have heard good things about Graphrag [1] (but what a stupid name). I did not have the time to try it properly, but it is supposed to build the knowledge graph itself somewhat transparently, using LLMs. This is a big stumbling block. At least vector stores are easy to understand and t…

why stupid? it uses a Graph in RAG. graphrag. if anything its too generic and multiple people who have the same idea now cannot use the name bc microsoft made the most noise about it.

It's the sound and Bobcat Goldthwait would have made if he'd voiced the Aflac duck.

Re: KAG – Knowledge Graph RAG Framework

#34

Post by dartos »

bkovacev wrote: post #28
isoprophlex wrote: post #7

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.

I have been building something like this for myself. Is there a room for a paid software, and would you be willing to pay for something like that?

IMO there is only a B2B market for this kind of thing.

I’ve heard of a few very large companies using glean (https://www.glean.com/)

This is the route I’d take if I wanted to make a business around rag.

Re: KAG – Knowledge Graph RAG Framework

#35

Post by dartos »

ankit219 wrote: post #27
trees101 wrote: post #6

Earlier quoted context omitted.

Can you expand on that? Where do big enterprise orgs products fit in, eg Microsoft, Google? What are the leading providers as you see them? As an outsider it is bewildering. First I hear that llama_index is good, then I hear that its overcomplicating slop. What sources or resources are reliable on this? How can we develop anything that will still stand in 12 months time?

> How can we develop anything that will still stand in 12 months time? The pace at which things are moving, likely none. You will have to keep making changes as and when you see newer things. One thing in your favor (arguably) is that every technique is very dependent on the dataset and problem you are solving. So, if you do not have the latest one implemented, you would be okay, as long as your evals and metrics are…

Well the rate of new LLMs keep coming out, but since they’re all trying to model language, they should all be fairly interchangeable and potentially will converge.

It’s not hard for a product to swap the underlying LLM for a given task.

Re: KAG – Knowledge Graph RAG Framework

#36

Post by dartos »

tessierashpool9 wrote: post #32
tessierashpool9 wrote: post #22

a quick look leaves me with the question: what exactly is being tokenized? RDS, OWL, Neo4j, ...? how is the knowledge graph serialized?

isn't this a key question? anybody here knowledgeable and care to reply?

I worked at a small company experimenting with RAG.

We used neo4j as the graph database and used the LLM to generate parts of the spark queries.

Re: KAG – Knowledge Graph RAG Framework

#37

Post by adeptima »

leobg wrote: post #13
rastierastie wrote: post #5

What do other HNers make out of this? Would you use this? Responsible for a legaltech startup here.

Fellow legal tech founder here. The first thing I look at in projects like this are the prompts: https://github.com/OpenSPG/KAG/blob/master/kag/builder/promp... All you’re doing here is “front loading” AI: Imstead of running slow and expensive LLMs at query time, you run them at index time. It’s a method for data augmentation or, in database lingo, index building. You use LLMs to add context to chunks that doesn’t ex…

This comment and an idea to work backwards deserve an article!

Just finished a call a few mins, and we came to conclusion we do natural query language, BM25 scoring with Tantivy based code first

https://github.com/quickwit-oss/tantivy

In meanwhile we collect all questions to ask LLM so we can be more consious at Hybrid Search implementation phase

Re: KAG – Knowledge Graph RAG Framework

#38

Post by tessierashpool9 »

dartos wrote: post #36
tessierashpool9 wrote: post #32

Earlier quoted context omitted.

isn't this a key question? anybody here knowledgeable and care to reply?

I worked at a small company experimenting with RAG. We used neo4j as the graph database and used the LLM to generate parts of the spark queries.

not sure if this is addressing my question. as i understand it the RAG augments the knowledge base by representing its content as a graph. but this graph representation needs to be linguistically represented such that an llm can digest it by tokenizing and embedding.

Re: KAG – Knowledge Graph RAG Framework

#39

Post by BOOSTERHIDROGEN »

djoldman wrote: post #29

"Whitepaper" is guarded behind this: https://survey.alipay.com/apps/zhiliao/n33nRj5OV > The white paper is only available for professional developers from different industries. We need to collect your name, contact information, email address, company name, industry type, position and your download purpose to verify your identity... That's new.

For industrial plant white papers, a common practice is to submit your company email address and name as part of the access process.

Re: KAG – Knowledge Graph RAG Framework

#40

Post by kergonath »

swyx wrote: post #19
kergonath wrote: post #12

Earlier quoted context omitted.

> 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. I have heard good things about Graphrag [1] (but what a stupid name). I did not have the time to try it properly, but it is supposed to build the knowledge graph itself somewhat transparently, using LLMs. This is a big stumbling block. At least vector stores are easy to understand and t…

why stupid? it uses a Graph in RAG. graphrag. if anything its too generic and multiple people who have the same idea now cannot use the name bc microsoft made the most noise about it.

> why stupid? it uses a Graph in RAG. graphrag.

It is trivial, completely devoid of any creativity, and most importantly quite difficult to google. It’s like they did not really think about it even for 5 seconds before uploading.

> if anything its too generic and multiple people who have the same idea now cannot use the name bc microsoft made the most noise about it.

Exactly! Anyway, I am not judging the software, which I have yet to try properly.

Post reply on HN