FoodSnap AI

[Rahul-R79]

📝 Summary

I have successfully completed the full-stack implementation of the FoodSnap AI application. This project uses generative AI to simplify nutrition tracking. Users can simply SNAP a photo of their meal, and the app allows Google's Gemini AI to identify the food and estimate portion sizes. This is then cross-referenced with the Edamam API to fetch accurate nutritional breakdowns (Calories, Protein, Carbs, Fat).

✨ Key Features Implemented

• 📸 AI-Powered Analysis: Integrated Google Gemini flash 2.5 to accurately identify dishes and estimate quantities from user-uploaded images.
• 🥗 Detailed Nutrition: Seamless integration with Edamam API to retrieve precise calorie and macronutrient data based on the AI's analysis.
• 💾 History & Storage: Implemented MongoDB database to store analyzed food logs and potential caching for performance.
• 🎨 Modern & Responsive UI: Built a clean, mobile-first interface using React (Vite) and Tailwind CSS v4 for a premium user experience.
• 🚀 Production Ready: Fully deployed with optimized build scripts (Frontend on Vercel, Backend on Render).

🛠️ Tech Stack

• Frontend: React 19, Vite, Tailwind CSS, TypeScript, Axios
• Backend: Node.js, Express.js, TypeScript
• Database: MongoDB (Mongoose)
• AI & APIs: Google Gemini SDK, Edamam Nutrition API

[Rahul-R79]

@wecode-community