raphaelmansuy

Convert PDF documents to Markdown using Vision Language Models — CLI and library

28
3
100% credibility
Found Feb 20, 2026 at 22 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Rust
AI Summary

A command-line tool and library that converts PDF documents into structured Markdown by rendering pages as images and using vision language models from various AI providers.

How It Works

1
đź“° Find the PDF Magic Tool

You discover a handy helper that turns messy PDFs into neat, editable Markdown files.

2
📥 Get It Ready

Download the tool to your computer—it sets itself up quickly and easily.

3
đź§  Link Your AI Helper

Connect a smart AI service so the tool can read and understand your PDF pages like a person.

4
✨ Feed It a PDF

Give it a PDF from your files or a web link, pick pages if you want, and let it do its thing.

5
⚡ Watch It Work

It processes pages fast, showing progress as clean text appears.

âś… Perfect Markdown Ready

You now have beautifully structured, editable text—tables, headings, everything preserved perfectly.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 22 to 28 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is edgequake-pdf2md?

This Rust CLI tool and library converts PDF documents—local files or URLs—into clean, structured Markdown using vision language models like GPT-4o, Claude, or Gemini. It rasterizes pages into images for AI to read accurately, handling tables, math, and layouts that traditional extractors butcher. Run `pdf2md document.pdf -o output.md` for instant results, or integrate the async API for batch jobs; perfect for flipping scanned papers or reports into editable text before converting GitHub Markdown to PDF or feeding repos to LLMs.

Why is it gaining traction?

Zero-setup binaries bundle PDF rendering with no env vars or downloads, unlike Python alternatives that need manual deps. Concurrent page processing slashes time (10x speedup), multi-provider support (OpenAI, Ollama local) keeps costs low (~$0.02 for 50 pages), and post-processing fixes AI quirks like bad tables. Devs love the self-contained Rust speed over flaky OCR tools.

Who should use this?

Data engineers building RAG pipelines from research PDFs, needing convert PDF to docx/epub/word flows. Docs teams converting GitHub repo PDFs or readmes to LLM text. CLI powerusers batch-processing invoices or books to Markdown for GitHub/VSCode.

Verdict

Grab it for reliable PDF-to-Markdown if you're tired of garbled extracts—CLI shines for quick wins, library for apps. At 16 stars and 1.0% credibility, it's early (solid docs/tests but low adoption); test on your PDFs before production.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.