Use “Summarize scanned PDF with OCRmyPDF” in Recued. Create a searchable PDF from a scanned document, extract its text through Poppler pdftotext, and produce preview-first notes from the extracted text file ref.

How it works 16 steps

Inspect the data fetches, transforms, gates, and output this recipe runs.

Process (16 steps)

◆ ocr recued-core.ocrmypdf.pdf.ocr_searchable

Ocr searchable pdf on ocrmypdf

◆ keep_pdf core.storage.file.persist

Persist storage file

◆ text recued-core.pdftotext.pdf.to_text

To text pdf on pdftotext

■ text_ref default

Apply default

■ has_text compare

Check if text ref has data

✦ summarize core.ai.summarize

AI generates a concise summary

skip: step.has_text not_equal true

■ defaults defaults

Apply defaults

■ key_points_count count

Count items in key points

■ key_points_text join

Join items with " "

■ now date_add

Add 0 days to

■ skip_write any

Check if any of the conditions are true

◆ keep_text core.storage.file.persist

Persist storage file

skip: step.skip_write equal true

■ row_key replace

Replace text in keep pdf cas ref

◆ stage_row core.storage.shared.write

Write storage shared

skip: step.skip_write equal true

■ staged not

Apply not

■ card to_summary

Format results as a summary card

▼

Output

summary card

Settings 7 configurable

Configurable at install. Defaults shown — change them anytime in Recued.

focus setting = important facts, decisions, dates, obligations, and follow-up actions

title setting =

source setting = [object Object]

language setting = eng

max length setting = 300

write mode setting = preview

staging prefix setting = scanned_documents_staging