PDF to Markdown for AI & RAG (Tables + OCR)
Pricing
from $1.00 / 1,000 text pages
PDF to Markdown for AI & RAG (Tables + OCR)
Convert PDFs to clean Markdown or text for LLMs and RAG: headings, paragraphs, Markdown tables, OCR for scanned pages, page ranges, metadata and ready-made chunks.
Pricing
from $1.00 / 1,000 text pages
Rating
0.0
(0)
Developer
Scot C
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
a day ago
Last modified
Categories
Share
Turn PDFs into clean, LLM-ready Markdown, with no layout junk and no broken words. Paste links, and get back Markdown you can feed directly into ChatGPT, Claude, embeddings or a RAG pipeline.
What you get, per PDF
- Clean Markdown: headings detected from font sizes, wrapped lines merged into proper paragraphs, rotated margin text removed.
- Tables as Markdown tables: ruled tables become
| col | col |tables you can read and query. - OCR for scanned pages: pages with no text layer are read automatically with OCR. Choose from 7 languages.
- Page ranges: process only the pages you need (
1-5,9,12-). - Page markers:
<!-- page N -->comments, so your AI answers can cite page numbers. - RAG chunks: optional chunking on paragraph boundaries, with overlap, ready for embedding.
- Metadata: title, author, creation date, producer.
- A .md file per document, plus a structured JSON row with page, OCR and table counts.
Who it's for
- AI and RAG builders: ingest manuals, reports, papers and contracts into a vector database.
- Automation workflows (Make, Zapier, n8n, LangChain): turn a PDF link into text in one API call.
- Researchers and analysts: pull readable text out of papers, filings and scanned archives.
Input
| Field | Example |
|---|---|
| PDF URLs | https://arxiv.org/pdf/1706.03762 |
| Pages | 1-5,9 (empty = all) |
| OCR for scanned pages | Auto, Always or Off |
| RAG chunk size | 2000 characters (0 = off) |
Example output (excerpt)
From "Attention Is All You Need" (arXiv), page 1:
Each result row also includes: pages, textPages, ocrPages, tables, characters, metadata, chunks (optional) and markdownFile.
Pricing
Pay per event, and only for pages you actually process:
- Text page: a fraction of a cent per page.
- OCR page (scanned pages only): a small per-page fee.
Failed downloads are never charged. You can cap spend per run with Apify's maximum-charge setting, and the Actor stops cleanly when the cap is reached.
Notes and limits
- PDFs up to 100 MB each. Use "Max pages per document" to control cost on very large files.
- Table detection works on tables with ruling lines. Borderless tables come out as text.
- OCR uses Tesseract, which works well on clean scans. Handwriting and very low-quality scans give weaker results.
- Password-protected PDFs aren't supported.
- Only process documents you have the right to use.
