🤖 Friday - AI Assistant

"Just like the AI from Iron Man, but with more attitude and better coding skills."

Friday is a sophisticated AI assistant built with LiveKit and Google's Gemini AI, offering seamless voice interactions, detailed analysis capabilities, and a personality inspired by Tony Stark's AI companion from Iron Man.

✨ Features

🎙️ Realtime Voice Interaction

• Seamless voice conversations using Google's Realtime API
• Natural language processing with "Aoede" voice
• Real-time response generation

🧠 Advanced AI Capabilities

• Dual AI Architecture: Combines realtime voice with detailed text analysis
• Coding Assistant: Comprehensive code examples, best practices, and debugging help
• Technical Analysis: In-depth explanations and multiple perspectives
• Smart Tool Integration: Weather, web search, email, and detailed analysis

🛠️ Built-in Tools

• 🌤️ Weather Information: Get current weather for any city
• 🔍 Web Search: DuckDuckGo integration for real-time information
• 📧 Email Sending: Gmail integration with secure authentication
• 💻 Code Analysis: Detailed programming help and explanations

🎭 Personality

• Classy butler demeanor with a touch of sarcasm
• Inspired by Iron Man's Friday AI
• Professional yet entertaining responses

🚀 Quick Start

Prerequisites

• Python 3.8 or higher
• A Google API key (for Gemini AI)
• LiveKit account and credentials
• Gmail account (for email functionality)

Installation

1. Clone the repository

   git clone https://github.com/Debanjan110d/Friday-An-AI-assistent.git
   cd Friday-An-AI-assistent

2. Install dependencies

   pip install -r requirements.txt

3. Download required files

   python agent.py download-files

4. Set up environment variables

   Create a .env file in the project root:

   # Google Gemini AI
   GOOGLE_API_KEY=your_google_api_key_here
   
   # LiveKit Configuration
   LIVEKIT_URL=wss://your-livekit-url.livekit.cloud
   LIVEKIT_API_KEY=your_livekit_api_key
   LIVEKIT_API_SECRET=your_livekit_api_secret
   
   # Gmail Configuration (Optional - for email functionality)
   GMAIL_USER=your_email@gmail.com
   GMAIL_APP_PASSWORD=your_gmail_app_password

5. Run the assistant

   # Development mode
   python agent.py dev
   
   # Console mode
   python agent.py console

🔧 Setup Guide

1. Getting Google API Key

1. Go to Google AI Studio
2. Create a new API key
3. Copy the key to your .env file as GOOGLE_API_KEY

2. LiveKit Setup

1. Sign up at LiveKit Cloud
2. Create a new project
3. Get your WebSocket URL, API Key, and API Secret
4. Add them to your .env file

3. Gmail Setup (Optional)

For email functionality:

1. Enable 2-Factor Authentication on your Gmail account
2. Generate an App Password:
   • Go to Google Account Settings
   • Security → 2-Step Verification → App Passwords
   • Generate password for "Mail"
3. Use this app password (not your regular password) in GMAIL_APP_PASSWORD

📋 Environment Variables

Variable	Required	Description
GOOGLE_API_KEY	✅ Yes	Google Gemini AI API key
LIVEKIT_URL	✅ Yes	LiveKit WebSocket URL
LIVEKIT_API_KEY	✅ Yes	LiveKit API key
LIVEKIT_API_SECRET	✅ Yes	LiveKit API secret
GMAIL_USER	❌ Optional	Gmail address for email functionality
GMAIL_APP_PASSWORD	❌ Optional	Gmail app password

🎯 Usage Examples

Voice Commands

"Hey Friday, what's the weather in New York?"
"Can you search the web for Python tutorials?"
"Send an email to john@example.com about the meeting"
"Help me write a MongoDB user schema"

Coding Assistance

User: "Write a simple MongoDB schema"
Friday: "Certainly, Sir. Let me provide you with detailed coding assistance."
[Returns comprehensive code examples with explanations]

🏗️ Architecture

┌─────────────────┐    ┌─────────────────┐    ┌─────────────────┐
│   Voice Input   │───▶│  RealtimeModel  │───▶│  Live Response  │
└─────────────────┘    └─────────────────┘    └─────────────────┘
                                │
                                ▼
┌─────────────────┐    ┌─────────────────┐    ┌─────────────────┐
│ Complex Queries │───▶│   Gemini Pro    │───▶│ Detailed Output │
└─────────────────┘    └─────────────────┘    └─────────────────┘
                                │
                                ▼
                    ┌─────────────────┐
                    │      Tools      │
                    │ • Weather       │
                    │ • Web Search    │
                    │ • Email         │
                    │ • Code Analysis │
                    └─────────────────┘

🛠️ Available Tools

Weather Tool

await get_weather(city="London")
# Returns: "London: ⛅️ +8°C"

Web Search Tool

await search_web(query="Python best practices")
# Returns: Comprehensive search results

Email Tool

await send_email(
    to_email="user@example.com",
    subject="Meeting Reminder",
    message="Don't forget about our meeting at 3 PM"
)

Detailed Analysis Tool

await get_detailed_analysis(
    query="Explain async/await in Python",
    context_info="For a beginner programmer"
)
# Returns: Comprehensive explanation with examples

🔍 Capabilities

What Friday Can Do:

✅ Voice Interactions

• Natural conversation in real-time
• Context-aware responses
• Personality-driven communication

✅ Coding Assistance

• Code generation and explanation
• Best practices recommendations
• Debugging help and error analysis
• Multiple programming languages support

✅ Information Retrieval

• Real-time weather data
• Web search capabilities
• Current events and facts

✅ Communication

• Email composition and sending
• Professional communication assistance

✅ Analysis & Reasoning

• Complex problem breakdown
• Multiple perspective analysis
• Technical documentation explanation

Current Limitations:

❌ Cannot access local files or systems ❌ Cannot execute code directly ❌ Cannot make phone calls or SMS ❌ Cannot access private databases

🧪 Development

Project Structure

Friday-An-AI-assistent/
├── agent.py              # Main agent logic
├── tools.py              # Tool implementations
├── prompts.py            # AI prompts and instructions
├── requirements.txt      # Python dependencies
├── .env                  # Environment variables
├── .gitignore           # Git ignore rules
├── README.md            # This file
├── LICENSE              # MIT License
└── KMS/                 # Key Management and logs
    └── logs/

Adding New Tools

1. Create a new function in tools.py:

@function_tool()
async def your_new_tool(
    context: RunContext,
    parameter: str
) -> str:
    """Your tool description"""
    # Implementation here
    return "Result"

2. Import and add to agent in agent.py:

from tools import get_weather, search_web, send_email, get_detailed_analysis, your_new_tool

# In Assistant class
tools=[
    get_weather,
    search_web,
    send_email,
    get_detailed_analysis,
    your_new_tool  # Add here
],

Running in Different Modes

# Development mode (with debugging)
python agent.py dev

# Console mode (text-based interaction)
python agent.py console

# Download required files
python agent.py download-files

🤝 Contributing

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

📝 License

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

🙏 Acknowledgments

• LiveKit for real-time communication infrastructure
• Google AI for Gemini AI capabilities
• Marvel Studios for the inspiration from Iron Man's Friday AI
• The open-source community for various tools and libraries

📞 Support

If you encounter any issues or have questions:

1. Check the Issues page
2. Create a new issue if your problem isn't already listed
3. Provide detailed information about your setup and the error

---

"Sometimes you gotta run before you can walk." - Tony Stark

Made with ❤️ and a lot of coffee ☕