Get documents ready for AI — without handing them over
AI tools read clean text best, have hard limits on what they accept, and bill by the token. These tools handle the preparation: turning PDFs into structured Markdown, splitting what is too long, and measuring what you are about to send. All of it runs in your browser, so the document goes to the AI of your choice and nowhere else.
- PDF to MarkdownClean Markdown from any PDF, with OCR for scanned pages.
- PDF to ObsidianA PDF as an Obsidian note: properties, page markers, embedded images.
- Split PDF for AICut a PDF into parts NotebookLM, ChatGPT or Claude will accept.
- Token CounterExact OpenAI token counts for text, PDFs and Word files.
- Markdown Chunker for RAGSplit documents into token-sized chunks that respect headings.
Which one do you need?
- The AI misreads your PDF. PDF to Markdown gives it headings, lists and tables instead of broken lines — and OCRs scanned pages it would otherwise skip.
- The file is refused as too large. Split PDF for AI cuts it to the limits of NotebookLM, ChatGPT, Claude or Gemini, at chapter boundaries.
- You need to know if it fits. The token counter gives exact OpenAI counts for text, PDFs and Word files.
- You are building a RAG pipeline. The Markdown chunker splits documents into token-sized chunks at headings and exports JSONL.
Why prepare documents at all?
Because the answer can only be as good as what the model read. A PDF uploaded as-is may be partly skipped, its tables flattened, its scanned pages ignored — and the answer comes back confident anyway. The guide to AI upload limits covers what each tool accepts and what happens beyond it.
Guides
- ChatGPT, Claude, NotebookLM & Gemini File Upload Limits (2026)ChatGPT, Claude, NotebookLM and Gemini upload limits by plan - file size, files per chat, per 3 hours and per project. Checked against vendor docs.
- Why LLMs Read Markdown Better Than PDF (ChatGPT & Claude)PDF extraction throws away the structure your model needs. See what breaks, and why Markdown gets better answers out of ChatGPT and Claude.
- PDF to Markdown for RAG Pipelines (Practical Guide)Why clean Markdown improves RAG retrieval quality. Covers chunking strategies, metadata, common PDF extraction pitfalls, and where browser tools fit.
- PDF to Markdown for NotebookLM — Free, No Upload, With OCRCan NotebookLM read scanned PDFs or .md files? Why its PDF extraction is hit-or-miss, and how to convert to clean Markdown with OCR first, free.