🤖 AI Assistant

A dual-mode AI assistant with Mentor Mode for interactive learning and Concept Mirror for understanding analysis — powered by Gemini & Groq.

Demo Link:-Concept_mirror

Features • Demo • Quick Start • API Reference • Deployment • Contributing

---

✨ Features

🎓 Mentor Mode

Your personal AI tutor that adapts to your learning pace.

• Multi-turn conversations — context-aware follow-ups for deeper understanding
• Syntax-highlighted code — beautiful code examples with language detection
• Topic-scoped sessions — focused learning on Python, DSA, Web Dev, and more
• Smart fallbacks — graceful demo responses when API keys aren't configured

🪞 Concept Mirror

Reflect on what you think you know — and discover what you're missing.

• Understanding analysis — breaks down what you got right, wrong, and missed
• Gap detection — surfaces blind spots in your mental models
• Structured feedback — organized into Understood, Missing, Incorrect, and Assumptions
• Actionable insights — clear summary with next steps for improvement

⚡ Additional Highlights

Feature	Description
🔄 Dual AI Providers	Switch between Google Gemini and Groq (LLaMA/Mixtral) with one env variable
🎭 Demo Mode	Full functionality without API keys for testing and development
🌐 REST API	Clean Flask API — use it headless or integrate with any frontend
📱 Responsive UI	Modern React interface that works on desktop and mobile

---

🎬 Demo

Demo mode is built in — just run the app without API keys and it works out of the box with mock responses.

---

📁 Project Structure

AI-ASSISTANT/
├── backend/                  # Python Flask API server
│   ├── api.py                # REST endpoints (/mentor, /analyze, /generate)
│   ├── ai_client.py          # AI provider factory & client
│   ├── base.py               # Abstract base class for providers
│   ├── config.py             # Environment configuration loader
│   ├── prompts.py            # System prompts for each mode
│   ├── demo.py               # Fallback mock responses
│   ├── run.py                # Server entry point
│   ├── requirements.txt      # Python dependencies
│   ├── .env.example          # Environment template
│   ├── gemini_provider/      # Google Gemini integration
│   └── groq_provider/        # Groq (LLaMA/Mixtral) integration
│
├── frontend/                 # React + Vite SPA
│   ├── src/
│   │   ├── App.jsx           # Main app with mode switching
│   │   ├── components/
│   │   │   ├── MentorMode.jsx        # Interactive tutor chat
│   │   │   ├── ConceptMirrorMode.jsx # Understanding analyzer
│   │   │   ├── ModeSelector.jsx      # Mode toggle UI
│   │   │   ├── Header.jsx            # App header with settings
│   │   │   └── ApiKeyModal.jsx       # API key configuration
│   │   └── services/
│   │       └── geminiService.js      # Backend API client
│   ├── index.html
│   ├── package.json
│   └── vite.config.js
│
├── vercel.json               # Vercel deployment config
└── README.md

---

🚀 Quick Start

Prerequisites

• Python 3.10+ and pip
• Node.js 18+ and npm
• API key from Google AI Studio or Groq Console (optional — demo mode works without keys)

1. Clone the Repository

git clone https://github.com/tech-akash010/AI-ASSISTANT.git
cd AI-ASSISTANT

2. Backend Setup

cd backend

# Create virtual environment (recommended)
python -m venv .venv
source .venv/bin/activate    # Linux/macOS
.venv\Scripts\activate       # Windows

# Install dependencies
pip install -r requirements.txt

# Configure environment
cp .env.example .env
# Edit .env with your API keys (or leave defaults for demo mode)

# Start the API server
python run.py

The backend will start at http://localhost:5000.

3. Frontend Setup

cd frontend
npm install
npm run dev

Open http://localhost:5173 in your browser. 🎉

---

🔑 API Configuration

Environment Variables

Variable	Default	Description
ACTIVE_PROVIDER	gemini	AI provider to use (gemini or groq)
ACTIVE_MODEL	(auto)	Override model (e.g., gemini-2.0-flash, llama-3.3-70b-versatile)
GOOGLE_API_KEY	—	Your Google Gemini API key
GROQ_API_KEY	—	Your Groq API key
FLASK_HOST	127.0.0.1	Server bind address
FLASK_PORT	5000	Server port
FLASK_DEBUG	True	Enable Flask debug mode
DEMO_MODE	False	Force demo mode (mock responses)

Supported Models

Google Gemini Models

Model	Best For
gemini-2.0-flash	Fast responses, general use
gemini-1.5-flash	Balanced speed & quality
gemini-1.5-pro	Complex reasoning tasks

Groq Models

Model	Best For
llama-3.3-70b-versatile	High quality, versatile
llama-3.1-8b-instant	Ultra-fast responses
mixtral-8x7b-32768	Long context, balanced

---

📡 API Reference

GET /health

Health check endpoint.

{
  "status": "healthy",
  "provider": "gemini",
  "model": "gemini-2.0-flash",
  "has_api_key": true,
  "demo_mode": false
}

POST /mentor

Multi-turn Mentor Mode chat.

// Request
{
  "messages": [
    { "role": "user", "content": "Explain recursion with an example" }
  ],
  "topic": "Python"
}

// Response
{
  "response": "Recursion is when a function calls itself...",
  "provider": "gemini",
  "model": "gemini-2.0-flash"
}

POST /analyze

Concept Mirror analysis.

// Request
{
  "concept": "Binary Search",
  "explanation": "Binary search divides the array in half each time..."
}

// Response
{
  "understood": ["Divide and conquer approach", "Halving the search space"],
  "missing": ["Sorted array prerequisite", "Time complexity analysis"],
  "incorrect": [],
  "assumptions": ["Works on any array"],
  "summary": "Good grasp of the core idea, but missing key prerequisites..."
}

POST /generate

Simple text generation.

// Request
{ "prompt": "Explain DSA in simple terms" }

// Response
{
  "response": "Data Structures and Algorithms (DSA)...",
  "provider": "gemini"
}

---

🚢 Deployment

Frontend and backend are deployed separately on Vercel (each has its own vercel.json).

Deploy Backend

1. On vercel.com, click Add New → Project
2. Import your GitHub repo
3. Set Root Directory to backend
4. Add Environment Variables in the Vercel dashboard:

   Variable	Value
   ACTIVE_PROVIDER	gemini or groq
   GOOGLE_API_KEY	Your Gemini key
   GROQ_API_KEY	Your Groq key (if using Groq)
   DEMO_MODE	False

5. Deploy — note your backend URL (e.g., https://your-backend.vercel.app)

Deploy Frontend

1. Create a second Vercel project from the same repo
2. Set Root Directory to frontend
3. Add Environment Variables:

   Variable	Value
   VITE_API_URL	Your backend URL from above (e.g., https://your-backend.vercel.app)

4. Deploy — your frontend will connect to the backend automatically

---

🛠️ Tech Stack

Frontend	Backend	AI Providers
React 19 Vite 7 react-markdown react-syntax-highlighter	Python 3.10+ Flask 3 Flask-CORS python-dotenv	Google Gemini Groq (LLaMA 3.3, Mixtral)

---

🤝 Contributing

Contributions are welcome! Here's how to get started:

1. Fork the repository
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Commit your changes: git commit -m 'Add amazing feature'
4. Push to the branch: git push origin feature/amazing-feature
5. Open a Pull Request

Made by tech-akash010 Also by Ayon-coder