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

Show HN: Knowledge graph of restaurants and chefs, built using LLMs

theophilecantelob.re

Post reply on HN
Print view View original

31–40 of 45 posts

Re: Show HN: Knowledge graph of restaurants and chefs, built using LLMs

#31

Post by Rooster61 »

theophilec wrote: post #11
Rooster61 wrote: post #3

Earlier quoted context omitted.

Me too. Title might need a bit of adjusting. Neat concept though! I do wish it expanded out past French cuisine. It has its place, but I am very much tired of French cooking being held above other locales/styles

The graph contains restaurants in France and Belgium but all cuisines are represented. It's completely possible to expand the graph to other parts of the world. What source of reviews/info do you have in mind?

My apologies, only gave it a cursory glance. Should have dug a bit deeper

Re: Show HN: Knowledge graph of restaurants and chefs, built using LLMs

#32

Post by nluken »

theophilec wrote: post #26
nluken wrote: post #24

Given the structured nature of the data, how does this compare to running a specialized classification model that looks for specific words in a review and uses those to assign Chefs to Restaurants? With some fine tuning, you might get more consistent results than feeding the reviews into a generative model.

The data is initially not at all structured, and the critics talk about a chef's CV in passing. For instance, take this example: > At Grenat, Antoine Joannier and Neil Mahatsry are bathed in an ardent red glow, much like the pomegranate-toned walls of their space. After working together at La Brasserie Communale, where they first met, the duo is now firing on all cylinders in the heart of Marseille, where Antoine ten…

Nice breakdown. Cheers!

Re: Show HN: Knowledge graph of restaurants and chefs, built using LLMs

#33

Post by dylan604 »

moandcompany wrote: post #6

Very cool work. It's worth mentionion that the Graph browser using "Retina" is a project from Ouestware ( https://www.ouestware.com/en/ ) which is also contributor to the GraphCommons and GephiLite projects.

I was clicking around with the embed, and eventually hit the "home/house" icon. That takes me to a Retnia credit/loading screen with no way to back out of it that I could see. Was forced to hard refresh the page. If there is a close button, it could be made more obvious

Re: Show HN: Knowledge graph of restaurants and chefs, built using LLMs

#35

Post by fads_go »

arnath wrote: post #21

This is a super cool idea! I've sort of mused about an idea for general web search that's very similar to this concept, where you start with a set of trusted entities and then branch out from there, but choosing how you establish trust is really important. But this is a really clever application, well done!

so you mean how academics search for relevant publications on a topic, which is the direct inspiration for the original Google ranking algorithm, back in the happy days when the web was young and had not optimized itself around short-term money making.

Re: Show HN: Knowledge graph of restaurants and chefs, built using LLMs

#36

Post by theophilec »

bevan wrote: post #34

This was inspiring, what a cool idea. Just curious—-for 4o mini isn’t there a json mode that reliably produces structured output? Was that what you were referring to / ended up using?

Yes I ended up using that. Libraries like outlines give that functionality to open models.

Re: Show HN: Knowledge graph of restaurants and chefs, built using LLMs

#37

Post by drabbiticus »

Very interesting. A small tweak and it seems like this could be applied to the problem of identifying degree of separation from political dissidents or other targets with the right data source. Lots of tools already exist that do that, but it's kind of wild how accessible and scalable certain techniques have become.

Re: Show HN: Knowledge graph of restaurants and chefs, built using LLMs

#39

Post by theophilec »

theophilec wrote: post #14
tantalor wrote: post #12

The embedding is kind of weird. Like, there's no reason a "degree: 1" node should be so far away from its sibling. Example: https://imgur.com/a/7Cktyzp This makes the graph look more random/noisy/disorganized than it actually is.

I agree the spatialization could be better. I used one of the algorithms in Gephi-lite directly. Do you have a favorite spatialization algorithm to recommend?

FYI I updated the visualization. Credit goes to @jacomyal from @ouestware on GitHub who helped me out.

Re: Show HN: Knowledge graph of restaurants and chefs, built using LLMs

#40

Post by tantalor »

theophilec wrote: post #39
theophilec wrote: post #14

Earlier quoted context omitted.

I agree the spatialization could be better. I used one of the algorithms in Gephi-lite directly. Do you have a favorite spatialization algorithm to recommend?

FYI I updated the visualization. Credit goes to @jacomyal from @ouestware on GitHub who helped me out.

The "Chloé Woestelandt" test is still just as bad
Post reply on HN