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

Show HN: OpenNutrition – A free, public nutrition database

opennutrition.app

Post reply on HN
Print view View original

101–110 of 160 posts

Re: Show HN: OpenNutrition – A free, public nutrition database

#101

Post by TechDebtDevin »

Cheer2171 wrote: post #87
joshdickson wrote: post #83

Earlier quoted context omitted.

I envisioned many lines of inquiry from HN but the idea that a compressed TSV of nutritional data is not a "dataset" (definition: a collection of related sets of information that is composed of separate elements but can be manipulated as a unit by a computer) was unexpected.

Your response is such a perfect example of why the "data science" movement is a cancer on actual science. So many graduate from programs and boot camps (or just read blog posts) that teach them all the technical mechanics of working with data, but nothing about actual science.

You sound like you're having a bad day. Go take a walk, its just someones side project on HN. They arent trying to destroy science for you, they were simply sharing something they enjoyed building. You dont have to use it or like it, but it has nothing to do with "science". Its not that deep bro.

Re: Show HN: OpenNutrition – A free, public nutrition database

#102

Post by joshdickson »

morgengold wrote: post #64

Well done! How do you create the food images?

Thank you! The images are created via Flux (Schnell, due to cost). An LLM (currently Gemini Flash) creates the prompt, Flux generates the images, a rembg lambda that I open-sourced trims the background out, and then a vision-based LLM (also currently Gemini Flash) grades the resulting output for prompt adherence, background removal artifacts, etc. A lot get thrown away but the cost is so low that even a 25-50% success rate is adequate.

Background removal lambda if you want to check that out: https://github.com/joshdickson/rembg-lambda

Re: Show HN: OpenNutrition – A free, public nutrition database

#103

Post by NewJazz »

hombre_fatal wrote: post #73
adamas wrote: post #35

What's the main difference between this and OpenFoodFacts really ?

The problem with OpenFoodFacts is that it just has nutrition label info for packaged goods. So, very little nutrient info beyond calories and protein. No info about micronutrients. No info about minerals, vitamins, amino acids, fatty acids. It's useless for nutrition tracking since if you're eating packaged food, then you already have that information yourself. It doesn't answer basic questions like "I ate 100g of ex…

You can add micro nutrients to those foods, they just don't always have them. Or so I thought.

Re: Show HN: OpenNutrition – A free, public nutrition database

#104

Post by kekub »

The Swiss Food Composition Database (https://naehrwertdaten.ch/en/) is an exceptional resource for detailed nutritional information on over 1,100 foods available in Switzerland but also around the world. It offers comprehensive data on macronutrients, micronutrients, and fat composition.

Maybe that would be a good source to challenge and validate the values provided by your LLM approach.

Re: Show HN: OpenNutrition – A free, public nutrition database

#105

Post by nelblu »

I am so glad there is another open data for nutrition. My favourite one so far is https://www.nutritionvalue.org/ which is awesome. As a fitness enthusiast/gym rat I really appreaciate having a pure facts only nutrition website (even if it is AI enhanced a bit), because these days if you ever google "Nutrition value of XXXX", you inevitably find useless search results giving "Benefits of eating XXXX". I have a feeling this might be true even if you substitute "XXXX" with "human poop". I hope this site doesn't start learning from those crappy articles.

Re: Show HN: OpenNutrition – A free, public nutrition database

#106

Post by joshdickson »

thi2 wrote: post #98
pmichaud wrote: post #79

Earlier quoted context omitted.

[flagged]

Tried it with unsweetened oat milk and the info was off in nearly every col. Not representable because I dont have US food but since its AI enhanced I cant compare my stuff with the stuff in the "dataset" and be sure thats an Us vs germany thing..

Would you mind posting/messaging me in some way (links in bio) what you expected it to show?

It looks like for unsweetened oat milk:

https://www.opennutrition.app/search/unsweetened-oat-milk-mt...

...it is leaning into a citation from the Australian Nutrient Database (e.g. Oat beverage, fluid, unfortified. Australian Nutrient Database. Public Food Key F006132. ), which is what I instructed it to do if it thought there was an exact match from a governmental database.

It's possible this is a poor general source for oat milk or that's not the beverage intended for the entry to stand for. I'll check it out, thank you for the report.

Re: Show HN: OpenNutrition – A free, public nutrition database

#107

Post by bl4ckm0r3 »

hombre_fatal wrote: post #29
bl4ckm0r3 wrote: post #12

this is great thanks a lot! on a similar theme...would anyone happen to know a public db like this but for workout exercises (with images/videos)?

https://github.com/wrkout/exercises.json

you are amazing thanks!

Re: Show HN: OpenNutrition – A free, public nutrition database

#108

Post by sodality2 »

I have to say, irrespective of any concerns about the LLM-generated content, the actual app alone (goal-setting, macro tracking, etc) is the best free iOS-based nutrition-tracking app I've ever used, at first use. It's actually shockingly hard to find good, free (or even one time payment!) ones that don't constantly nag you to upgrade and paywall. I would pay a lot (once) for a nutrition/weight tracking app as slick as this, with all of the goal setting, data graphs, etc, that uses the OpenFoodFacts database, not your own. (Soliciting suggestions!) Please consider making the AI features optional and instead using the OFF database as the primary source.

Also, looks like the Apple Health option in Settings actually opens the start-of-week settings modal.

Re: Show HN: OpenNutrition – A free, public nutrition database

#109

Post by joshdickson »

kekub wrote: post #104

The Swiss Food Composition Database ( https://naehrwertdaten.ch/en/ ) is an exceptional resource for detailed nutritional information on over 1,100 foods available in Switzerland but also around the world. It offers comprehensive data on macronutrients, micronutrients, and fat composition. Maybe that would be a good source to challenge and validate the values provided by your LLM approach.

Thank you for your feedback. This would be a great dataset to include -- my next priority is the Japanese government dataset which would expand food coverage for more traditional Asian diets, but this is a great resource.

https://www.mext.go.jp/en/policy/science_technology/policy/t...

Re: Show HN: OpenNutrition – A free, public nutrition database

#110

Post by thi2 »

joshdickson wrote: post #106
thi2 wrote: post #98

Earlier quoted context omitted.

Tried it with unsweetened oat milk and the info was off in nearly every col. Not representable because I dont have US food but since its AI enhanced I cant compare my stuff with the stuff in the "dataset" and be sure thats an Us vs germany thing..

Would you mind posting/messaging me in some way (links in bio) what you expected it to show? It looks like for unsweetened oat milk: https://www.opennutrition.app/search/unsweetened-oat-milk-mt... ...it is leaning into a citation from the Australian Nutrient Database (e.g. Oat beverage, fluid, unfortified. Australian Nutrient Database. Public Food Key F006132. ), which is what I instructed it to do if it thought ther…

I'll check it later to give more constructive feedback, also it seems like you are hammering a backend request with each keystroke (?), cant verify it on mobile but you might consider debouncing the user input a bit to ease off the load
Post reply on HN