AI Snack Suggester banner

AI Snack Suggester

Created by: ajk216212
2 devlogs
29m 26s

Developed a full-stack AI application that provides mood-based snack recommendations using a locally hosted ONNX-optimized large language model. The backend is implemented in Node.js with Express, integrating Hugging Face Transformers.js for text …

Developed a full-stack AI application that provides mood-based snack recommendations using a locally hosted ONNX-optimized large language model. The backend is implemented in Node.js with Express, integrating Hugging Face Transformers.js for text generation, while the frontend offers a simple, responsive UI for user interaction. The system ensures clean, production-ready outputs without chain-of-thought leakage and supports fast inference on CPU hardware.

Repository

README

Loading README...
ajk216212
ajk216212 worked on AI Snack Suggester
2 months ago
0h 29m logged

I built a full-stack AI Snack Suggester that recommends snacks based on a user’s mood. The frontend collects the mood and sends it to a Node.js + Express backend, which uses an ONNX-optimized instruction-tuned LLM (Qwen2.5-0.5B-Instruct) via Hugging Face Transformers.js to generate a clean, human-like response. The model runs locally for fast and private inference without exposing internal reasoning. Through this project, I learned how to integrate LLMs into real applications, handle model compatibility and generation tuning, and design a simple API-driven AI system suitable for production use.

Attachment
0
ajk216212
ajk216212 worked on AI Snack Suggester
2 months ago

I’m working on my first project! This is so exciting. I can’t wait to share more updates as I build.

Attachment
0