DocuParse icon

DocuParse

Full-featured document parsing — PDF, DOCX, XLSX, PPTX, images, OCR, markdown output. No native dependencies.

Extract Entities

AI-generated

Summary

Extracts selected entity types from a document supplied as binary data or fetched from a URL. Choose the entity categories to detect; the operation returns the extraction result for each input item.

Inputs

  • Input Type (required) — Select Binary Data or URL. Defaults to Binary Data.
  • Input Binary Field (required) — When using Binary Data, enter the binary property name containing the document; defaults to data.
  • URL (required) — When using URL, enter the document URL.
  • Skip SSL Verification — For URL input, defaults to false. Enables skipping SSL certificate verification.
  • Entity Types — Select entity categories to extract: emails, phone numbers, URLs, dates, IP addresses, and currency amounts. Defaults to emails, phone numbers, URLs, and dates.

Output shape

A result for each input item containing extracted entities.

The supplied source is minified and truncated around the node implementation, so the exact response fields and whether the result is transformed cannot be confirmed.

Links

Discussion