AI Mentor — Full Stack AI Learning App (MVP)

An AI-powered learning assistant that helps users ask questions, get explanations, and track learning progress.

---

About This Project

This project marks my transition from building AI experiments in Google Colab to developing a real full-stack application with a proper backend, frontend, and database.

Previously, I worked mainly with:

• Jupyter / Google Colab notebooks
• Isolated AI scripts

With this project, I focused on:

• Structuring code into backend + frontend
• Building APIs using FastAPI
• Connecting a real database (Supabase)
• Creating a usable UI with Next.js

👉 This is my first complete attempt at turning AI ideas into a real product (MVP).

---

✨ Features

• Ask questions using natural language
• AI-generated responses (Groq LLaMA 3.1)
• Automatically saves learning topics to database
• Displays last 3 interactions (chat history)
• Fast and minimal UI
• Real-time backend communication

---

🛠 Tech Stack

Frontend

• Next.js (App Router)
• Tailwind CSS

Backend

• FastAPI
• Groq API (LLaMA 3.1)

Database

• Supabase (PostgreSQL via REST API)

🏗 Architecture

Frontend (Next.js)
      ↓
Backend API (FastAPI)
      ↓
AI Model (Groq)
      ↓
Database (Supabase)

---

How to Run Locally

1️. Clone Repository

git clone https://github.com/YOUR_USERNAME/ai-mentor.git
cd ai-mentor

2️. Backend Setup

cd backend
python -m venv venv
venv\Scripts\activate

pip install -r requirements.txt

Create .env file:

GROQ_API_KEY=your_api_key
SUPABASE_URL=your_supabase_url
SUPABASE_KEY=your_supabase_key

Run backend:

uvicorn main:app --reload

3️. Frontend Setup

cd frontend
npm install
npm run dev

---

🌐 Access

• Frontend → http://localhost:3000
• Backend → http://127.0.0.1:8000

---

Key Learnings

• Moving from notebooks to structured applications
• Understanding API-based architecture
• Handling frontend-backend communication
• Managing environment variables and configs
• Debugging real-world issues (CORS, dependencies, etc.)

🚧 Limitations (MVP)

• No user authentication (single test user)
• Basic UI (focused on functionality)
• No advanced analytics/dashboard yet

---

Future Improvements

• User authentication (Supabase Auth)
• Learning dashboard with insights
• Improved UI/UX
• Chat history persistence
• Deployment (Vercel + Railway)

---

inal Note

This project is a learning milestone for me — moving beyond isolated AI experiments into building real, usable AI-powered applications.

⭐ If you like this project

Feel free to star ⭐ the repo or connect with me!