DocCrush
Convert any document into clean Markdown for AI.
14 followers
Convert any document into clean Markdown for AI.
14 followers
DocCrush converts PDFs, Word, PowerPoint, Excel, images and more into clean, structured Markdown. Built for developers, AI applications and RAG pipelines. • PDF → Markdown • Word → Markdown • OCR for scanned PDFs • Tables preserved • Images extracted • Batch processing • AI-ready output
One thing that would be great is preserving footnotes and endnotes properly in the Markdown output, since they often get flattened or dropped during conversion. Also, if you could add a CLI flag for choosing heading levels (like forcing h2 instead of h3 for detected sections), that would make the output much more consistent for downstream RAG pipelines.
@metenzts Thanks for the great suggestions! 🙌
You’re absolutely right — preserving things like footnotes, endnotes, and heading hierarchy makes a big difference when Markdown is used for RAG pipelines.
A CLI flag for controlling heading levels is a great idea as well. We’ll look into adding more output customization options.
Appreciate the feedback!