🔮 AI Text Archaeologist

Reconstructing the forgotten voices of the early internet, one fragment at a time, using AI and contextual web research

📖 Overview

Project Chronos is an intelligent system that reconstructs fragmented internet messages (slang, acronyms, and incomplete phrases from 2000s-2010s internet culture) into coherent, modern English sentences. It uses advanced AI to understand context, expand slang, and provide relevant historical sources.

✨ Key Features

• 🤖 AI-Powered Reconstruction - Leverages Google Gemini 2.5 Flash to intelligently reconstruct fragmented messages
• 🔍 Contextual Research - Automatically searches and retrieves relevant sources explaining cultural references
• 🌐 Web Interface - Clean React frontend for easy interaction
• 📚 Historical Context - Provides links to definitions and explanations of internet slang and cultural phenomena
• ⚡ Fast Processing - Efficient API design with Flask backend

🛠️ Technology Stack

Frontend:

• React + Vite
• Modern JavaScript (ES6+)

Backend:

• Python 3.x
• Flask (REST API)
• Google Generative AI (Gemini)
• Serper API (Web Search)

🚀 Getting Started

Prerequisites

• Node.js (v16 or higher)
• Python 3.8+
• Google Gemini API Key
• Serper API Key

Obtaining API Keys

Google Gemini API Key

1. Visit Google AI Studio
2. Sign in with your Google account
3. Click on "Get API Key" or "Create API Key"
4. Create a new API key or use an existing one
5. Copy your API key (it starts with AIza...)

Important: Keep this key secure and never commit it to version control

Serper API Key

1. Go to Serper.dev
2. Click "Sign Up" or "Get Started"
3. Sign up using your Google account or email
4. After logging in, navigate to your Dashboard
5. Copy your API key from the dashboard

Note: Serper offers 2,500 free searches, perfect for testing and development

Installation

1. Clone the repository

   git clone https://github.com/LazyHusky26/SOTY_Hackathon.git
   cd SOTY_Hackathon

2. Install Python dependencies

   pip install -r requirements.txt

3. Install Node dependencies (install nodejs first)

   npm install

4. Configure environment variables

   Copy .env.example to .env and add your API keys:

   cp .env.example .env

   Edit .env with your credentials:

   GEMINI_API_KEY=your_gemini_api_key_here
   SERPER_API_KEY=your_serper_api_key_here

   ⚠️ Important:

• Never commit your .env file (it's already in .gitignore)
• Get your Gemini API key from ai.google.dev
• Get your Serper API key from serper.dev
• Download nodejs from nodejs.org
• After running npm run dev, wait a few seconds for all the components to start up.

Running the Application

npm run dev

💡 Usage

1. Enter a fragmented message (e.g., "smh Top 8 drama g2g")
2. Click "Reconstruct"
3. View the AI-reconstructed message in modern English
4. Explore contextual sources explaining cultural references

Example

Input:

smh Top 8 drama g2g

Output:

Shaking my head at the drama surrounding MySpace Top 8 rankings; I've got to go.

Sources Provided:

• Urban Dictionary: "smh" definition
• Know Your Meme: MySpace Top 8 culture
• Wikipedia: Early social networking history

📁 Project Structure

SOTY_Hackathon/
├── src/                    # React frontend source
│   └── main.jsx           # React entry point
├── imgs/                   # Project images and assets
├── api.py                  # Flask REST API server
├── main.py                 # Core reconstruction logic
├── index.html              # HTML entry point
├── package.json            # Node dependencies
├── requirements.txt        # Python dependencies
├── .env.example           # Environment template
└── README.md              # Documentation

🔌 API Endpoints

POST /api/reconstruct

Reconstructs fragmented text and retrieves contextual sources.

Request:

{
  "fragment": "smh g2g brb"
}

Response:

{
  "original": "smh g2g brb",
  "reconstructed": "Shaking my head, I've got to go, but I'll be right back.",
  "sources": [
    {
      "link": "https://www.urbandictionary.com/define.php?term=smh",
      "description": "Internet slang meaning 'shaking my head'..."
    }
  ]
}

📞 Support

If you encounter any issues or have questions, please open an issue.

🙏 Members

• Aarnav Tandava - SE22UARI002
• Meet Sangani – SE24UARI184
• Devi Gottumukkala – SE24UARI081
• Varshika Sriya – SE24UARI146
• Pushpashree Ramgopal – SE24UCSE048

---

Built with ❤️ for SOTY Hackathon