# PDF to Markdown

Turn a text PDF into clean Markdown: headings from letter size, joined paragraphs, lists and simple tables.

Reads the text layer of a PDF and rebuilds its structure: lines are joined back into paragraphs, words split at line ends are mended, larger letters become headings, bullets and numbers become lists, and short cells that line up become tables. Made for giving a PDF to a language model.

- Endpoint: `POST https://setget.net/v1/tools/pdf-to-markdown` with JSON `{"input": {...}}` (add `"wait": 30` to hold the reply until the job finishes)
- MCP: `run_tool` with `slug` = `pdf-to-markdown`
- Page: https://setget.net/tools/pdf-to-markdown

## Files in, files out

This is a file tool. Its file inputs take file references, not file contents and not web addresses.

- Get a reference by uploading: `curl -T FILE https://setget.net/drop/` prints a line `ref  <id>/f1`. Or `POST https://setget.net/v1/drops` with `{"files":[{"name","size"}]}`, PUT the bytes to the returned `upload.url` with the listed headers, and use the file's `ref`. Over MCP use the `drop` tool. A file under about 700 KB can also be sent in place as a `data:<type>;base64,<content>` URI.
- Uploads are at most 100 MB per file, are readable by anyone with the link, and expire (one hour by default). Programs are refused.
- The tool runs as a job. The reply is `{"tool", "ms", "result", "files", "job"}`: `result` is JSON, and every result file comes back in `files` as `{"name", "size", "content_type", "kind", "url", "ref"}`. Download it from `url`, or pass `ref` as the input of another file tool.
- A job still running when the wait ends answers 202 with `job`. Follow it with `GET https://setget.net/v1/jobs/<id>?wait=30`, or stream progress from `GET https://setget.net/v1/jobs/<id>/events` (over MCP: the `job` tool). A person can watch it at `job.url`.

## Inputs

- `file` (required, file, a file reference such as `DROP_ID/f1`, accepts pdf, binary, text): The PDF to convert. It needs real text in it, not only scanned pages.
- `pages` (optional, string): Pages to convert, such as 1-3, 7, 10-. Leave empty for all pages.
- `page_breaks` (optional, boolean, default `false`): Mark where each page starts with a line such as <!-- page 2 --> and a rule between pages.

## Example 1: A three-page PDF as Markdown

Upload first. Each placeholder below stands for the reference of one upload: `DROP_ID/f1` = [sample.pdf](https://setget.net/static/samples/sample.pdf).

```json
{"input":{"file":"DROP_ID/f1"},"wait":30}
```

## Example 2: Two pages, with page marks

Upload first. Each placeholder below stands for the reference of one upload: `DROP_ID/f1` = [sample.pdf](https://setget.net/static/samples/sample.pdf).

```json
{"input":{"file":"DROP_ID/f1","pages":"1-2","page_breaks":true},"wait":30}
```

**How does it find headings?** By letter size. The most common size is taken as body text; larger sizes become headings, the largest as #, the next as ## and so on. Bold and italic words are kept.

**Why did I get an error about no text?** The PDF is a scan: its pages are pictures. Use the ocr-pdf tool, which reads text from pictures.

**Does it keep tables?** Simple ones, where short cells line up in rows and columns. Tables with long or wrapped cells come out as lines of text. Check tables that matter against the original.

**What is left out?** Pictures, and lines that repeat at the top or bottom of most pages such as running titles and page numbers. The result says how many of each.

**What are the limits?** Up to 1,000 pages in one run. For a longer PDF, set "pages" to a range and run it again for the rest. Password-protected PDFs must be unlocked first.

**Where is the Markdown?** In a file named after your upload, ending in .md. The result also holds the Markdown itself in "markdown" when it is up to 200,000 characters; "truncated" is true when only the start fits there.

**Does it fetch anything from the internet?** No. Links and picture addresses found in the file are copied as text. Nothing they point to is opened or downloaded.
