This workflow transforms n8n into an API endpoint for extracting structured data from images using Google Gemini AI. By sending an image URL and defining the required fields, the workflow processes the image, extracts relevant details, and returns clean JSON output.
It’s perfect for OCR-based automation tasks such as processing identity documents, invoices, receipts, or business cards.
Features
- 📥 Webhook API Endpoint – Accepts image URLs and extraction requirements
- 🖼 Image Handling – Fetches the image and converts it into base64 format for processing
- 🤖 AI-Powered Extraction – Leverages Gemini Flash Lite for advanced image-to-text analysis
- 🎯 Customizable Output – Define your own properties (e.g., Name, Date of Birth, PAN Number, Validity)
- 📝 Structured JSON Response – Returns clean, schema-driven JSON results
- ⚡ Ready-to-Use API – Integrates easily with applications for automated data entry and workflows
- 🔧 Flexible Use Cases – Supports document OCR, form digitization, text extraction, and more
