{"id":8976,"date":"2025-07-24T08:00:53","date_gmt":"2025-07-24T08:00:53","guid":{"rendered":"https:\/\/www.process.st\/help\/?post_type=ht_kb&p=8976"},"modified":"2026-06-02T09:00:43","modified_gmt":"2026-06-02T09:00:43","slug":"extract-text-file-uploads","status":"publish","type":"ht_kb","link":"https:\/\/www.process.st\/help\/docs\/extract-text-file-uploads\/","title":{"rendered":"Extract Text From File Uploads"},"content":{"rendered":"

Extract plain text from files uploaded to File Upload<\/strong> form fields \u2014 PDFs, Word documents, spreadsheets, images, and scanned documents. The extracted text becomes a variable you can pass directly into AI Tasks<\/a> for processing, summarization, or data extraction. Uploaded files with extracted text are also searchable in the global search box<\/a>.<\/p>\n

Users:<\/em><\/strong> Only Administrators or a Builder<\/a> with ‘edit’<\/a> permission can enable text extraction on form fields.<\/em><\/p>\n

Enable text extraction<\/h2>\n
    \n
  1. Open the workflow in the editor and add (or select) a File Upload<\/strong> form field<\/a>.<\/li>\n
  2. Click the meatball menu (three dots) next to the File Upload form field and select Settings<\/strong>.<\/li>\n
  3. Switch the Extract text<\/strong> toggle to the “on” position.<\/li>\n
  4. Click Apply<\/strong>.<\/li>\n<\/ol>\n

    \"Toggle<\/p>\n

    When a file is uploaded during a workflow run, the system extracts up to 512KB of plain text from it automatically.<\/p>\n

    OCR for images and scanned PDFs<\/h2>\n

    OCR (optical character recognition) automatically extracts text from images and scanned documents. No additional setup is required \u2014 OCR activates automatically when text extraction is enabled.<\/p>\n

    OCR works with:<\/p>\n