@GithubProjects Have you tried docling? It does a better job at converting PDFs to Markdown and supports more file formats. I even released a lightweight and easily scalable backend for it. You can check it out here github.com/drmingler/docl…
@GithubProjects I have created a prompt-to-PDF tool. I think with some improvements, it could be useful for people 🥲 prompt2pdf.vercel.app
@GithubProjects @OliverSorock This can be useful for you bro
@GithubProjects Is there any reverse DeOCR Tool? I need it so my professor cannot copy my assignment and check for plagiarism
@GithubProjects has anyone done OCR for non-savable excel / sheets?
@GithubProjects Great tool but isnt everyone using llms for text extraction?
@GithubProjects Looking for project, where I can upload my confidential pdfs, then I can search and ask questions.
@GithubProjects Oh did something on Tessact , is this the same ? Open source?