PDF to Markdown icon

PDF to Markdown

Convert a PDF (binary) to semantic Markdown in-process via @opendocsg/pdf2md. No external API.

PDF to Markdown

AI-generated

Summary

Convert each input item’s PDF binary to Markdown and write it to a JSON field. If Markdown extraction fails or returns empty output, fall back to plain-text extraction; optionally demote headings by one level.

Inputs

  • inputField (required) — Binary property containing the PDF; defaults to data. Missing binary data raises an item error.
  • outputField — JSON field for the extracted content; defaults to markdown.
  • demote — When enabled, shifts ATX headings down one level, capping at H6; defaults to false.

Output shape

One output item per input item, each retaining its JSON fields and binary data, with the extracted content in the configured output field and a pdfExtraction field.

pdfExtraction is pdf2md for semantic Markdown extraction or text-fallback when plain-text extraction is used. With Continue On Fail enabled, errors are returned in an error JSON field and the original binary is preserved.

Links

Discussion