Document to Markdown & RAG Chunks (PDF, DOCX, PPTX, XLSX, OCR)

Turn PDF, Word (DOCX), PowerPoint (PPTX), Excel (XLSX), HTML, TXT/CSV and images into clean, LLM-ready Markdown and heading-aware chunks for RAG, vector databases, AI agents and search — in one call.

• Tables preserved as Markdown tables (Word, Excel, HTML).
• Smart OCR for scanned PDFs and images (English, Portuguese, Spanish). In Auto mode only pages that are really scanned are OCR'd — you never pay OCR prices for normal text pages.
• RAG-ready chunks split on headings, with the heading path (["Contract", "Clause 3"]) and configurable size and overlap.
• Page markers (<!-- page 3 -->) in PDF output, so answers can cite pages.
• Fair billing: if no text can be extracted (e.g. a logo image), the document is not charged.
• Fail-safe batches: a broken link or unsupported file is reported in the dataset and the run continues.
• Works great from AI agents via the Apify MCP server, LangChain, LlamaIndex, n8n, Make and Zapier.

Input

Field	Description	Default
startUrls	Public URLs of documents	—
outputFormat	both, markdown or chunks	both
ocr	auto (scanned pages only), always, never	auto
chunkSize	Max characters per chunk (~4 chars per token)	4000
chunkOverlap	Characters repeated between chunks	400
maxPagesPerDocument	Skip longer documents to protect your budget	500

{
  "startUrls": [{ "url": "https://example.com/report.pdf" }],
  "outputFormat": "both",
  "ocr": "auto",
  "chunkSize": 4000,
  "chunkOverlap": 400
}

Output (one item per document)

{
  "url": "https://example.com/report.pdf",
  "fileName": "report.pdf",
  "kind": "pdf",
  "pages": 12,
  "ocrPages": 2,
  "chars": 31540,
  "markdown": "<!-- page 1 -->\n\n# Annual Report\n\n...",
  "chunks": [
    { "index": 0, "text": "# Annual Report\n\n...", "headings": ["Annual Report"], "chars": 3980 }
  ]
}

Failed items contain url and error. Items with no extractable text contain warning and are not charged.

Pricing (pay per event)

• Page — each PDF page, image, or 3,000 characters of text from other formats.
• OCR page — a page that needed OCR (scanned PDF page or image).

You only pay for documents that produced text. Use maxPagesPerDocument and the run's maximum cost to stay in budget.

Supported formats

PDF · DOCX · PPTX · XLSX · HTML/HTM · TXT · MD · CSV · PNG · JPG/JPEG · WEBP · TIFF · BMP · GIF

Files up to 50 MB. Password-protected PDFs are not supported.

Use cases

• Build a RAG knowledge base from company PDFs, manuals and policies.
• Feed AI agents with documents found on the web.
• Convert scanned invoices, receipts and contracts to text.
• Migrate Office documents to Markdown for docs sites and wikis.

Notes

Only process documents you have the right to use. Text is extracted as-is; complex layouts (multi-column magazines, forms) may need review.