Hand this to your AI agent. It does the boring part.

Scanned invoices in n8n: local OCR first, then a checked LLM extract

Scanned or photographed invoices have no text, so an LLM given them may invent values.

1. 1Lay out the folders›

   Who this is for (audience: both): people who already run self-hosted n8n for invoice or receipt data entry, and AI agents that build or maintain that workflow for them. You should know Docker and n8n basics. This isn't a beginner guide. Create ~/invoices/scans-in (input), ~/.n8n-files/ocr-out (OCR output, which n8n can read) and ~/invoices/scans-done (archived originals). Plus a Google Sheet with tabs Invoice, Review (same headers as the invoice playbook) and Processed (file_name, processed_at). Plus 5 to 10 scanned invoices whose correct values you know. Keep the output and archive folders outside the input folder. OCRmyPDF's watcher refuses to start if they overlap, because output written inside the input folder would be OCR'd again endlessly.
2. 2Run the OCRmyPDF watcher container›

   Read scanned invoices in n8n: local OCR first, then a checked LLM extract. Add a local OCRmyPDF step that turns scans into searchable PDFs, then let n8n extract fields and send anything that doesn't match the OCR text to a person. Use the watcher that ships in the official Docker image (documented in the OCRmyPDF batch docs; it runs as uid 1000 by default, so set --user to your uid:gid). skip_text leaves pages that already have text alone, for example when your scanner already makes searchable PDFs. Check the option names against ocrmypdf --help for your version. v17 also has a --mode skip form. Add language packs such as eng+deu if your vendors need them.
3. 3Test the OCR aloneyou check›

   Drop one known scan into scans-in. Confirm a PDF appears in ocr-out. Run pdftotext ocr-out/<file>.pdf - and check by eye that the invoice number and total are readable. If text is garbled, rescan at 300 dpi or higher, or try --deskew/--clean. The "OCR node, then LLM, then sheet" pattern comes from Vinay's template 7634 (Tesseract.js community node + Gemini + Airtable), WeblineIndia's template 7239 (Tesseract for images, PDF parser for PDFs, Gemini, Sheets), and Bart Slodyczka's video walkthrough, which shows a Tesseract node reading an invoice PNG. This playbook moves OCR out of n8n into an OCRmyPDF container, so no community node or Execute Command node is needed, and it adds source-text validation and human checkpoints.
4. 4Mount the output into n8n›

   n8n 2.x limits disk access to ~/.n8n-files by default (N8N_RESTRICT_FILE_ACCESS_TO). Mount the host ~/.n8n-files/ocr-out to /home/node/.n8n-files/ocr-out in the n8n container. Leave the Execute Command and Local File Trigger nodes disabled (their n8n 2.0 default). This design doesn't need them. n8n Cloud is paid and can't read a local OCR output folder (Read/Write Files on Cloud is limited to an ephemeral /home/node/).
5. 5Trigger on a schedule and skip files already done›

   Add a Schedule Trigger (every 5 to 15 minutes), then Read/Write Files from Disk → Read File(s) with the selector /home/node/.n8n-files/ocr-out/*.pdf. Look up each file name in the Processed tab. Drop matches. n8n can't move or delete files without Execute Command, so the Processed tab is the memory. Clean ocr-out by hand or with a host cron job. PDF Scrubber box: strip names and other personal data from invoice PDFs before sending them to a cloud AI tool.
6. 6Extract the text and the fields›

   CrimsonBot's live playbook Turn emailed invoices into a checked spreadsheet (invoice-inbox-to-spreadsheet) sends every PDF with no text layer (scans, phone photos) to a Review tab, because an LLM given an empty page may make up values. This playbook clears that pile. Use Extract From File → PDF. If the text is under about 50 non-space characters, send the file to Review with review_reason set to "OCR found no text" and don't call the LLM. Use the prompt below with a structured output parser. Attach the Ollama Chat Model node for a fully local run. The OCR text is the source of truth the validator checks against. If OCR misreads 140.40 as 14O.40 and the model "corrects" it, the value no longer matches the source and a person sees it. That is the intended behavior.
7. 7Validate against the OCR text›

   Add a Code node ("Run Once for Each Item") with the validator below. It checks required fields, numeric amounts, subtotal + tax = total within 0.01, YYYY-MM-DD dates, model confidence, and that the invoice number and total appear in the OCR text (commas stripped first). Failures go to Review with every reason. Look up invoice_number + vendor_name in the Invoice tab. If they match, send to Review as "possible duplicate". Otherwise append to Invoice with status = New. In both cases add the file name to Processed.
8. 8Compare known scans before you activateyou check›

   Compare every cell with the paper invoice. Only then activate the schedule. Clear the Review tab daily or weekly. A person decides anything that touches payment.