Extract Text from PDF/Image to CSV using Vertex AI (Gemini)

n8n Data Extraction AI Productivity

Contributed by Sabrina Ramonov 🍄. From the community directory at agents.sabrina.dev, republished with permission and full credit.

Case Study

I'm too lazy to record every transaction for my expense tracking. Since all my expenses are digital, I just extract the transactions from bank PDF statements and screenshots into CSV to import into my budgeting software.

What this workflow does

Upload your PDF or screenshots into Google Drive. It then passes the PDF/image to Vertex Gemini to do some A.I. image recognition. It then sends the transactions as CSV and stores it into another Google Drive folder.

Setup

Set up 2 Google Drive folders: 1 for uploading and 1 for the output.

Input your Google Drive credentials.

Input your Vertex Gemini credentials.

How to adjust it to your needs

You can upload other types of documents for information extraction.

You can extract any text data from any image or PDF.

You can adjust the A.I. prompt to do different things.

Tools used: Vertex AI, Google Drive, AI Agent

Download the workflow template (JSON)

Original tutorial

Want this running in your business? KOBA42 builds and operates automations like this one.