n8n Workflow: Extract PDF Form Fields to Google Sheets

Turn PDF form fields into a Google Sheets row automatically

This n8n workflow watches a Google Drive folder for new PDF forms, runs Mistral OCR + Mistral Chat to extract structured form fields, and appends each result to Google Sheets—so your form data lands ready for reporting and operations.

What this workflow does

• Triggers when a new file is created in a specified Google Drive folder (or you can run it manually to list and process PDFs already in the folder).
• Filters to PDFs only, then downloads each PDF from Google Drive.
• Uploads the PDF to Mistral Files, requests a signed document URL, and sends that URL to Mistral OCR to extract the form text.
• Combines OCR output pages into a single text block and builds a fixed JSON schema containing the required fields plus Google Drive file metadata.
• Uses Mistral Chat Completions with strict JSON output rules to extract the requested form fields from the OCR text.
• Parses the returned JSON, maps values into the target Turkish-labeled Google Sheets columns, and appends a new row including the source file name.
• When processing in bulk, it waits briefly between items to pace requests and continues until all PDFs are processed.

Use cases

• Automatically capture data from PDF application / registration forms stored in Google Drive.
• Convert scanned or image-based PDFs into structured records for CRM-like tracking in Google Sheets.
• Batch-process historical PDF forms by running the workflow manually and writing all results to a sheet.

Technical details

• n8n nodes: Code, Wait, Filter, Sticky Note, Google Drive, HTTP Request
• Integrations: Google Drive OAuth2, Google Sheets OAuth2, Mistral Cloud API key (Mistral Files, Mistral OCR, Mistral Chat Completions)
• Configured with a Google Drive folder ID, plus Google Sheets document ID and target sheet tab.

Ideal for n8n users, automation engineers, and SaaS operators who need reliable PDF-to-structured-data extraction and Google Sheets automation.