Sure, but the API itself is the easy part, especially with LLM help. The problem is the data source is a total trash fire, so in order for it to be worth it the API cost would either be exorbitant or not worth it.
You know what's pretty good at cleaning up data that's a total trash fire? _More_ LLM. :-)
I run a web service whose primary purpose is cleaning up messy, SEO-enshittified data from Google, eBay, etc. After years of fine-tuning my own heuristics, I threw a super-cheap LLM at it and it massively out-performed my custom code. It's slower, but the results are well worth it.
I run a web service whose primary purpose is cleaning up messy, SEO-enshittified data from Google, eBay, etc. After years of fine-tuning my own heuristics, I threw a super-cheap LLM at it and it massively out-performed my custom code. It's slower, but the results are well worth it.