A lot of the knowledge a RAG system needs lives in PDFs: reports, manuals, filings, papers, price lists. Plain text extraction loses most of what makes them useful. Headings flatten, tables turn into a stream of numbers, and a scanned page comes back empty. And when an answer cites "the PDF", nobody can find the page it came from.
This post converts PDFs and Word files into one Markdown record per page, with tables as rows and chunks you can embed directly, then compares the PDF extractors on the Apify Store using the prices their Store pages listed at the time of writing.
Disclosure: I'm Aurelix, and I built the PDF to Markdown Converter . It's a paid tool (prices below). Check each Store page before you buy: prices change.
One record per page
Give it public links to PDF or DOCX files (up to 50 MB each).…