Markdown

🚀 Team CS on Top - TechSprint GDG MUJ

A Next-Gen GenAI solution built for the TechSprint GDG MUJ hackathon.

---

📖 About

This project leverages the power of Pathway's real-time data processing engine combined with Generative AI to solve complex problems with live data contexts.

The system is designed to ingest streaming data, process it dynamically using Pathway, and provide intelligent, context-aware insights via a user-friendly Streamlit interface. By simulating real-time data environments, we demonstrate how GenAI can react and adapt to changing information instantaneously.

Key Features:

• ⚡ Real-time Data Processing: Utilizing Pathway for low-latency stream handling.
• 🧠 GenAI Integration: LLM-powered insights on live data.
• 🔄 Live Simulation: Includes a data simulator to mimic real-world streaming scenarios.
• 📊 Interactive UI: A clean Streamlit dashboard for visualization and interaction.

---

🛠️ Technology Stack

We used a modern tech stack focused on speed, scalability, and AI capabilities:

• Core Engine: Pathway (Data Processing & RAG)
• Language: Python
• Frontend: Streamlit
• AI/LLM: OpenAI GPT / Gemini (via API)
• Data Simulation: Custom Python Simulator

---

📂 Repo Structure

IIT-MADRAS/
├── backend.py          # Main Pathway backend logic (RAG/Indexing)
├── simulator.py        # Script to simulate real-time data streaming
├── frontend.py         # Streamlit application for the UI
├── requirements.txt    # List of project dependencies
└── README.md           # Project documentation

---

🎥 Demo

Check out our project in action below

---

🚀 How to Clone and Run Locally

Follow these steps to get the project up and running on your local machine.

1. Clone the Repository

git clone [https://github.com/arush-07/IIT-MADRAS.git](https://github.com/arush-07/Sentinel-Project/
cd Sentinel-Project

2. Install Dependancies

Make sure you have Python installed. Then run:

pip install -r requirements.txt

3. Set Up Environment Variables

Create a .env file in the root directory and add your API keys (e.g. Gemini, OpenAI, Pathway license if applicable):

GEMINI_API_KEY=your_api_key_here

4. Run the Application

You need to run the components in the order below.

🔹 Step A: Start the Backend Initialize the Pathway engine to listen for data.

python backend.py

🔹 Step B: Start the Simulator Open a new terminal and run the simulator to start streaming data to the backend.

python simulator.py

🔹 Step C: Launch the Frontend Open a third terminal and launch the Streamlit dashboard.

streamlit run frontend.py

---

👥 Team Bitwise

Made with ❤️ by:

• Arush Pradhan
• Drishti Verma
• Aryan Verma
• Bhavya Jaggi

Built for the TechSprint GDG MUJ hackathon.