hello, I was trying to create a workflow that, starting from a paper in pdf, converts it into txt and separate it into different fields (abstract, introduction, etc.). Unfortunately, after months of attempts, I could not get the desired results, I’ve tried with various pdf2txt tools (including pdf paser+document data extractor node) and differtent splitting pattern; someone has some advice or knows some workflow that does something like that? thanks in advance, any suggestion will be greatly apreciated
Welcome to our forum!
Could you please share a screenshot of how it looks like now and describe then a bit more what would be your wish how it should look like?
Could you also share an example workflow with an example pdf? That would help a lot understanding how far you are now