PDF to Markdown

Convert a PDF into clean Markdown - headings, lists, tables and images detected automatically, with an optional two-column reading-order fix and RAG-ready chunking.

Multi-file input
Long-running / async
PDF to Markdown workspace

This tool extracts a PDF's text, tables and images into Markdown, using font-size and layout heuristics to detect headings, lists and code blocks, a common two-column reading order, and running headers/footers/watermarks - not a full document-structure model, so review the result rather than trusting it blindly on a complex layout. It only reads the file; nothing is changed.

Simple workflow

How it works

1
Add PDFs

Add one or more PDFs to the list, and pick an extraction mode.
2
Convert

Convert a file and review its detected structure page by page.
3
Download

Download the Markdown, extracted images, or a ZIP bundle.

Frequently asked questions

Will the Markdown output exactly match the PDF's layout?

No. Headings, lists, code blocks and reading order are detected by font-size and layout heuristics, not a true document-structure model - review the result, especially on complex or unusually formatted pages, rather than trusting it blindly.

What does the AI alt-text toggle actually generate?

A plain, rule-based placeholder such as "Image on page 3" - not an image-captioning model. A real captioning model is out of scope for this tool.

What is RAG-optimized mode for?

It splits the converted Markdown into fixed-token-size chunks with overlap, each with optional YAML frontmatter naming the source file, page range and chunk index - ready to feed into a retrieval pipeline. Token counts use the same tokenizer family as common modern LLMs.

Stay ahead of your document work

New tools and thoughtful product updates, delivered occasionally. No noise, no spam.