LDXhub icon

LDXhub

Work with the LDXhub AI-powered document processing platform

Actions5

ExtractDoc → Run Conversion Job

AI-generated

Summary

Upload a document from the configured binary field to LDXhub, run an ExtractDoc conversion with the selected engine and output format, then poll until the job finishes and download the result. The operation is described as extracting plain text or JSONL from PDF, DOCX, XLSX, or PPTX without AI or OCR.

Inputs

  • Input Binary Field (required) — Binary property containing the file to process; defaults to data.
  • Engine Name or ID (required) — ExtractDoc engine to use. Select an available engine or provide its ID or an expression.
  • Output Format Name or ID (required) — Output format supported by the selected engine; choose a listed format or provide its ID or an expression.
  • Polling Settings — Optional job polling controls: maximum attempts defaults to 180, and server wait seconds defaults to 10 (allowed range 1–10). The defaults allow about 30 minutes of polling.

Output shape

One output item per input item, with JSON job metadata and the downloaded result in binary data.

JSON includes job_id, status, and output_file_id. The result binary uses the same property name as the input field. The downloaded filename is used when available; otherwise the node names it output.txt for text, output.jsonl for jsonl, or output.<format> for another format. Errors stop execution unless Continue On Fail is enabled, in which case the item contains its original JSON and an error.

Links

Discussion