Automated Thai Document OCR and Data Extraction to Google Sheets

This n8n workflow automates the process of extracting structured information from Thai PDF documents and storing it in Google Sheets. It begins with a manual trigger for testing, then loads PDF files from a specific folder. The PDFs are processed through Typhoon OCR to extract text, which is then sent to a language model to structure the data into JSON format. A custom script parses the JSON, extracting fields such as document ID, date, subject, sender, attachments, details, signatories, contacts, and download links. Finally, the structured data is appended to a designated Google Sheet for record-keeping or further analysis. This workflow is ideal for organizations that handle a large volume of official Thai documents, streamlining data entry and reducing manual effort.