Extract text from PDF and image using Vertex AI (Gemini) into CSV

Go to Workflow
26,113 views
Built by Keith Rumjahn Keith Rumjahn
Created on June 05, 2026

Description


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.

Click here to watch Youtube tutorial

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 crendtials
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

Nodes Used (4)

Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm
Google Drive
n8n-nodes-base.googleDrive
Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini
HTTP Request
n8n-nodes-base.httpRequest