filepdf.ruPDF tools in the browser

PDF → Markdown

Convert PDF to Markdown, JSON, or HTML. Extract structured text with headings, tables, and lists — ready for AI/LLM pipelines.

  1. 1Files
  2. 2Settings
  3. 3Run
  4. 4Result

1. Files

Source file

Accepted formats: .pdf

2. Settings

3. Run

Attach a file to continue

How it works

  1. 1Upload the PDF you want to turn into structured text.
  2. 2Choose a format: Markdown (.md), JSON with coordinates, or HTML.
  3. 3Run the conversion and download the result for RAG, GPT, or a knowledge base.

Frequently asked questions

Which format for RAG?
Markdown: split the result into chunks at second-level headings (##) — the standard LangChain and LlamaIndex splitter.
Why JSON with bounding boxes?
It stores on-page coordinates of elements — for answers with precise citation links.
What about scans?
Run OCR first, then the recognized text will be marked up correctly.

Read the full guide: How to Convert a PDF to Markdown for AI and LLM Pipelines →