Document to Markdown & RAG Chunks

Turn PDF, Word (DOCX), Excel (XLSX), PowerPoint (PPTX), HTML, CSV/TSV, TXT, Markdown and JSON files into clean Markdown plus ready-to-embed chunks for RAG pipelines, vector databases and LLM prompts. Paste file URLs, get structured output. No API key, no setup.

What you get per document

Field	Description
url, finalUrl	Input URL and URL after redirects
status	ok or failed (failed documents are not charged)
format	Detected from file content (works for links without extensions)
title	Document title (metadata, <title>, or first heading)
pages	PDF pages / PPTX slides converted
billablePages	Pages billed (see pricing)
chars, approxTokens	Size of the Markdown (token estimate ≈ 4 chars/token, 1 per CJK character)
markdown	Full Markdown: headings, lists, tables (DOCX/XLSX/HTML/CSV), page/slide markers
chunks[]	{index, headings, text, chars, approxTokens}; heading-aware, configurable size and overlap
warnings[]	e.g. truncated PDF, likely scanned PDF

Real example (RFC 8461 as plain text, trimmed): listing/output-example.json.

Pricing (pay per event)

Event	Price
Document converted	$0.003
Page converted	$0.0005
Actor start (Apify standard, once per run)	$0.0003

Pages = PDF pages or PPTX slides; for other formats, one page per 3,000 characters of output (minimum 1). Example: a 10-page PDF costs $0.008; a 200-page PDF $0.103; a 1-page web page $0.0035 (plus $0.0003 per run). Failed downloads and unsupported files are free. Set a maximum charge per run in the run options and the Actor stops cleanly when it is reached.

Limits

• No OCR. Scanned/image-only PDFs produce little text; the Actor warns you (likely scanned PDF).
• Max file size and max PDF pages are configurable (defaults 50 MB, 500 pages).
• Excel sheets are capped at 5,000 rows per sheet in Markdown output.
• Complex layouts (multi-column PDFs, nested tables, footnotes) can come out in the wrong order or flattened.
• Default memory 512 MB. Our test run (one 59 kB text file) peaked at 55 MB; very large PDFs or spreadsheets may need more memory.

Data and credit

Your files are processed inside your run with open-source libraries (see requirements.txt). Nothing is sent to third-party services.

Responsible use

• Only submit files you have the right to process (your own files, open data, public documents whose terms allow it).
• The Actor respects robots.txt by default (user agent DocumentToMarkdownActor), downloads each URL once, and refuses private/internal network addresses.
• Personal metadata (author, last-modified-by) is dropped from output. The Actor does not store your documents beyond your run's own storage.

Integrations

The output is plain JSON, so you can feed the chunks to your own embedding/vector-store code or to Apify integrations (we have not tested specific vector-database connectors). Call it from the Apify API:

curl -X POST "https://api.apify.com/v2/acts/<username>~document-to-markdown/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
  -H 'Content-Type: application/json' -d '{"fileUrls":["https://www.rfc-editor.org/rfc/rfc9309.pdf"]}'

No warranty

Provided as is, without warranty of any kind. Results are automated and can be incomplete or wrong; check anything important against the original source before relying on it.