PDF Data Extractor

Upload any PDF — text or scanned — and extract structured data with a custom AI prompt.

Extraction Prompt

Tell the AI exactly what fields to pull and what to filter. The output will be a JSON array — each object becomes a row in the table below.

Large PDFs are split into chunks of this size and processed in parallel. Lower = more API calls but better coverage. Default: 30.

Drop PDFs here or click to browse

Text-based and scanned PDFs both supported · Multiple files accepted

No data extracted yet

Set your extraction prompt above, then upload a PDF