anyone knows some robust open source library for extracting tables from pdf , even ocr library is fine
P.S- i have already tried tabula ,camelot , ing2table, unstructured.io and most of the document loader in langchain , none of them are even 95% robust
nougat by Facebook is your best bet.
thanks will check it out . have you tried it ?
Yup, it’s the best I’ve tried for tables and math formulas.