A ChatGPT-style web application that explains source code snippets using a locally hosted Large Language Model (LLM) powered by Ollama.
Built with Next.js (TypeScript) on the frontend and FastAPI on the backend.
- Accepts code snippets from the user
- Automatically detects the programming language
- Explains the code in a clear, beginner-friendly way
- Uses a local LLM (no OpenAI / external APIs)
- ChatGPT-style conversational UI focused only on code explanation
This project demonstrates:
- Local AI / LLM integration using Ollama
- Prompt engineering for concise, fast responses
- Full-stack AI application architecture
- Understanding of deployment constraints for LLMs
- Clean Git hygiene and project structure
Browser (Next.js + TypeScript)
|
| HTTP (JSON)
v
Backend API (FastAPI)
|
| Local inference
v
Ollama (gemma3 model)