# PDF to Markdown

Recover readable Markdown, equations, and figures from a PDF for notes, review, or reuse.

PDF to Markdown pulls the useful reading material out of a fixed page. It is a good route for turning your own report into notes, preparing a document for a Markdown knowledge base, or recovering text that no longer has an editable source.

## Choose it when

Use Markdown when you want portable prose and simple structure. Choose [PDF to LaTeX](/docs/tools/pdf-to-latex/) when the destination is a typeset paper, or [PDF to Typst](/docs/tools/pdf-to-typst/) when you plan to continue in Typst.

Only convert documents you own or are allowed to reuse. Conversion does not change the source's copyright or license.

## Convert the PDF

1. Open **PDF to Markdown**, or run `/pdf-to-markdown`.
2. Choose a PDF up to 128 MB.
3. Start the conversion.
4. Save `converted.md` with any extracted files, or create a Markdown project.
5. Compare the result with the PDF.

For a PDF with selectable text, Oleafly reads the text layer, detects likely headings and columns, extracts figures, and carries math through the local conversion pipeline. If the document appears scanned, Oleafly can transcribe its pages with a compatible Ollama vision model.

## What to inspect

PDFs describe where marks sit on a page, so reading order must be inferred. Check multi-column pages, footnotes, tables, equations, captions, hyphenated line endings, and the reference list. Figure files are placed under `assets/` when extraction succeeds.

:::caution[Scans need a local model]
Scanned-PDF transcription requires Ollama with a vision-capable model and accepts up to 50 pages. Text-layer extraction does not require AI. Neither route uploads the PDF to a hosted service.
:::

Markdown cannot reproduce every page-layout decision. Treat the output as content to edit, not as a visual replica of the original PDF.