Medical Record Parsing

Parse and extract structured data from digital medical record PDFs. Text-layer extraction — not for scanned documents.

Requires digital PDFs with embedded text. Rosetta does not perform OCR on scanned documents.

Use the Rosetta Extract API with a custom JSON schema to pull structured data from medical record parsing documents. PDF extraction API with native MCP support for Cursor and Claude.

curl -X POST https://rosettafolio.com/api/v2/extract \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "file=@document.pdf" \
  -F 'schema={"type":"object","properties":{...}}'