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

n8n template #2614

Summary

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

How to set it up

Open template #2614 on n8n.io and click Use for free, or copy the template JSON and paste it onto an empty canvas in n8n.
Create 2 credentials under Credentials → Add credential: Google Drive, Google Gemini Chat Model. Then open each of those nodes and pick the credential.
Check the model in the Google Gemini Chat Model node. The template may point at a model your account can't use; swap it for one you have access to.
Click Execute workflow and step through each node's output to confirm the data looks right.
Toggle the workflow to Active so its trigger runs on its own.

Hand off to your agent

Prompt

Help me set up the n8n workflow "Extract text from PDF and image using Vertex AI (Gemini) into CSV" (https://n8n.io/workflows/2614). It uses: HTTP Request, Google Drive, Basic LLM Chain, Google Gemini Chat Model. Import the template JSON into my n8n instance, list every credential I need to create, and walk me through testing it.

Paste into Claude Code and it will do the rest.

Apps and nodes

HTTP Request Google Drive Basic LLM Chain Google Gemini Chat Model

Questions

Yes. Keith Rumjahn published it free on n8n.io as a verified creator, and it has 26K views. It runs on n8n Cloud or a self-hosted n8n instance.

Google Drive, Google Gemini Chat Model. The other 2 nodes are built into n8n.

Similar workflows

NameViews