|
|
|
|
|
by shafyy
887 days ago
|
|
This is cool. As you said, my recommendation would be to not use ChatGPT to get the nutrition data, but use one of the databases that have good APIs such as USDA's Food Data Central [1]. This is domain where there's structured data and it's important that the output is deterministic, so a LLM is not a good choice. I once started working on something similar, but the goal was to suggest a list of ingredients for me to buy for the week so that I had a good total nutritional values. I don't work on it anymore though. 1: https://fdc.nal.usda.gov/index.html |
|
Also, if it's going to give protein advice it should probably recognise meat - unless it's aimed solely at vegetarians & vegans. My receipt had a whole chicken, a lamb shoulder, and a couple of different kinds of fish - but it said I was getting 0 protein and recommended quinoa.