Foudinge
Data
knowledge graph
SHOW HN2025
How HN took it
6 positive, 9 neutral or asking, 0 mixed, 6 critical, out of 21 comments about the project. Thread score +0.05.
Design: 1 for, 3 againstPerformance: 1 for, 2 againstIdea: 1 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Cool application of graph search and LLM extraction
From 2 comments
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…
arnath on HNThis looks great! I was just looking for a good web knowledge graph visualizer.
jonnycoder on HN
Positive reception of the updated visualization
From 1 comment
Yes! This looks amazing. Thanks! I made a mistake; I had checked the other link in your post ("You can explore the visualization here: [Interactive Culinary Network]") instead of…
tantalor on HN
Objections
Node layout looks random and disorganized
From 2 comments
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…
tantalor on HNThe "Chloé Woestelandt" test is still just as bad
tantalor on HN
Local models hallucinated more than gpt4o-mini
From 1 comment
Local models hallucinated a lot more that gpt4o-mini, so I stayed with OpenAI. On top of that, I paid around 14€ for inference on ~200 examples on OVH and inference was much…
theophilec on HN
Requests
Use a better layout algorithm such as UMAP, tSNE or hiveplot
From 2 comments
Yeah, they should have used UMAP or tSNE to cluster the data a bit
visarga on HNSince you did the hard work of parsing rich metadata already, it would be even cooler if your network visualization oriented nodes by some of this information. Here the…
peppery on HN
Try multimodal models
From 1 comment
Looks interesting, have you tried utilizing a multimodal model?
repsiace on HN
Support for other review datasets beyond LeFooding
From 1 comment
Do you think this will work as effectively with Google or Social Media review and rating datasets? As every country may not have a LeFooding.com Would like to here everyone's…
pranavm27 on HN
Questions
How does it compare to a specialized classification model versus a generative LLM
From 1 comment
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…
nluken on HN
Whether JSON mode was used for structured output with gpt4o-mini
From 1 comment
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…
bevan on HN
Alternatives named
Named entity recognition models such as spaCy
From 2 comments
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…
theophilec on HNLLMs have without a doubt replaced NER models and libraries like SpaCy. At least for my use-cases, creating ontologies and populating knowledge graphs.
varelaseb on HN