Remix.run Logo
niklasd 7 days ago

We found that for extracting tables, OpenAIs LLMs aren't great. What is working well for us is Docling (https://github.com/DS4SD/docling/)

emmanueloga_ 7 days ago | parent | next [-]

Haven't seen Docling before, it looks great! Thanks for sharing.

soci 7 days ago | parent | prev [-]

agreed, extracting tables in pdfs using any of the available openAI models has been a waste of prompting time here too.