Automated Text Extraction from PDFs and Images to CSV

This n8n workflow automates the process of extracting text data from PDFs and images stored in Google Drive, then converting that data into structured CSV files and uploading them back to Google Drive. The workflow begins by monitoring a specific folder for new files. When a new file is detected, it routes the file based on its MIME type to either download and extract data from PDFs or process images using Vertex AI for optical character recognition (OCR). It then sends the extracted text to an AI model to convert the information into CSV format, which is finally uploaded into a designated Google Drive folder.

This workflow is particularly useful for automating the digitization of paper or PDF-based payment records, invoices, receipts, or any scanned documents where manual data entry is time-consuming. Businesses can use this setup to streamline records processing, improve data accuracy, and save significant time in data management tasks.

The key nodes involved include Google Drive triggers and download nodes, MIME type routing with switches, OCR services via Vertex AI for images, language model processing for text to CSV conversion, and Google Drive for uploading processed files. It leverages AI and cloud storage to create an efficient, automatic document data extraction pipeline.