Radhika

banner

RADHIKA - Adaptive Reasoning & Intelligence Assistant

A sophisticated AI-powered assistant built with Next.js and powered by multiple LLM providers including Groq, Gemini, OpenAI, and Claude. RADHIKA adapts to different modes of interaction, providing specialized assistance for productivity, wellness, learning, creative tasks, and even acts as your GenZ bestie!

🎬 Project Showcase

Preview Description
YouTube Demo 🎬 YouTube Demo
Click the image to watch the full demo.
Blog Post 📝 Blog Post
Read the blog for in-depth explanation.

✨ Features

🎯 Multi-Mode Intelligence

🤖 Multi-Provider AI Support

🚀 Advanced Chat Interface

🎤 Voice Integration

⚡ Quick Actions & Smart Features

🎨 Dynamic AI Visualization

📊 Activity Analytics

🛠️ Tech Stack

Frontend

AI & Backend

Development

💃 Smart Model Selection

RADHIKA automatically selects the best model based on your query complexity:

// Determine which model to use based on conversation context
let modelType = "fast"; // llama-3.1-8b-instant for quick responses

// Use reasoning model for complex analytical tasks
if (query.includes("analyze", "compare", "plan", "strategy", "decision", "problem")) {
  modelType = "reasoning"; // llama-3.3-70b-versatile
}

// Use creative model for artistic and innovative tasks
if (query.includes("creative", "brainstorm", "idea", "write", "design", "story")) {
  modelType = "creative"; // qwen/qwen3-32b
}

🚀 Getting Started

Prerequisites

Installation

  1. Clone the repository 
    git clone https://github.com/RS-labhub/radhika.git
cd radhika
  2. Install dependencies 
    npm install
# or
bun install
  3. Set up environment variables (check .env.example) 
    touch .env

    Add your API keys (optional for full functionality):

    # Required for Groq (free tier available)
GROQ_API_KEY=your_groq_api_key_here
   
# Required for Gemini (free tier available)
GOOGLE_GENERATIVE_AI_API_KEY=your_gemini_api_key_here
   
# Optional: Add via UI for OpenAI/Claude
# OPENAI_API_KEY=your_openai_api_key_here
# ANTHROPIC_API_KEY=your_claude_api_key_here
  4. Run the development server 
    npm run dev
# or
bun run dev
  5. Open your browser Navigate to http://localhost:3000

🎮 Usage Guide

Selecting AI Modes

Click on any of the six mode buttons to switch RADHIKA’s personality and expertise:

AI Provider Selection

Choose from multiple AI providers in the bottom-right corner:

Voice Features

Quick Actions

Each mode provides quick action buttons with pre-defined prompts:

Chat Management

Themes & Customization

🏗️ Project Structure

radhika/
├── app/
│   ├── api/chat/route.ts          # Multi-provider chat API endpoint
│   ├── globals.css                # Global styles and theme variables
│   ├── layout.tsx                 # Root layout with metadata
│   └── page.tsx                   # Main application orchestrator
├── components/
│   ├── ui/                        # shadcn/ui base components
│   ├── chat-header.tsx            # Header with controls and mode display
│   ├── chat-sidebar.tsx           # Mode selection and quick actions
│   ├── chat-messages.tsx          # Message display and formatting
│   ├── chat-input.tsx             # Input field with voice controls
│   ├── chat-container.tsx         # Chat logic and state management
│   ├── ai-visualization.tsx       # 3D particle system visualization
│   └── activity-matrix.tsx        # Real-time analytics dashboard
├── hooks/
│   └── use-speech.ts              # Speech recognition and synthesis
├── types/
│   └── speech.d.ts                # TypeScript definitions for speech APIs
└── lib/
    └── utils.ts                   # Utility functions and helpers

🔧 Configuration

System Prompts

Each mode has a carefully crafted system prompt in app/api/chat/route.ts:

Model Configuration

Customize model selection in the API route:

const MODELS = {
  groq: {
    fast: "llama-3.1-8b-instant",
    reasoning: "llama-3.3-70b-versatile", 
    creative: "qwen/qwen3-32b"
  },
  gemini: { default: "gemini-2.0-flash" },
  openai: { default: "gpt-4o" },
  claude: { default: "claude-3-5-sonnet-20241022" }
}

Customization Options

🌟 Key Features Explained

Adaptive Model Selection

RADHIKA intelligently chooses the best model for your query:

Persistent Chat History

Advanced Voice Integration

Real-time Analytics

Responsive Design

🤝 Contributing

We welcome contributions! Here’s how to get started:

  1. Fork the repository
  2. Create a feature branch 
    git checkout -b feature/amazing-feature
  3. Make your changes
    • Follow TypeScript best practices
    • Add tests for new functionality
    • Update documentation as needed
  4. Commit your changes 
    git commit -m 'Add amazing feature'
  5. Push to your branch 
    git push origin feature/amazing-feature
  6. Open a Pull Request

Development Guidelines

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

📞 Support & Community

🔮 Roadmap

Upcoming Features

Performance Improvements

Meet the Author

Author

**Built with ❤️ by [RS-labhub](https://github.com/RS-labhub)** *RADHIKA - Your Adaptive AI Companion for Every Need* [⭐ Star this repo](https://github.com/RS-labhub/radhika) • [🐛 Report Bug • 💡 Request Feature](https://github.com/RS-labhub/radhika/issues)
This site is open source. Improve this page.