What it does
An n8n workflow that shows five ways to analyze images and PDFs with Google Gemini. It covers a single image, several images with set prompts, item by item processing, and direct API calls for PDFs and images. Each approach suits a different volume and level of control.
Use cases
- 01Describe or classify a single image
- 02Extract text from a PDF through the Gemini API
- 03Run different prompts across several images
Connects
HTTP Request · AI Agent · Google Gemini Chat Model