This project is a full multimodal AI chatbot built using Streamlit and Google Gemini 2.0 Flash API.
It allows you to interact with text, PDFs, images, audio, and video files through a simple and intuitive web UI.
- Converse with Gemini 2.0 AI (text chat)
- Upload and chat with PDFs (ask questions about uploaded documents)
- Upload and chat with Images (describe, query image content)
- Upload and chat with Audio files (understand or summarize audio)
- Upload and chat with Video files (analyze and extract information)
- Beautiful Streamlit UI with history tracking
- Fast and lightweight (works even on local machines)
- Streamlit — Web app framework
- Google Generative AI (Gemini) — Text and Multimodal interaction
- PIL — Image processing
- Python 3.9+
📁 Project Structure
Hackathon/
├── Hackathon/
│ └── app.py ← Main Streamlit application (run this file)
└── README.md
git clone https://github.com/Jaideep193/Hackathon.git
cd Hackathon/Hackathon
streamlit run app.py