Gemini-Agent

screen-capture.online-video-cutter.com.1.mp4

A modular AI agent framework powered by Gemini, designed to enable tool-based interactions and intelligent task execution using Streamlit for a smooth web interface.

📁 Project Structure

Gemini-Agent/
├── .streamlit/                # Streamlit configuration files
├── src/
│   ├── __pycache__/           # Python cache
│   ├── images/                # Image assets used in the app
│   ├── gemini_history.py      # Handles history and memory
│   ├── gemini_llm.py          # Gemini LLM API integration
│   ├── gemini_tool_selector.py # Tool selection logic
│   ├── gemini_tools_defination.py # Tool definitions
│   ├── gemini_tools.py        # Tool execution logic
│   ├── streamlit_app.py       # Main Streamlit app
│   ├── system_prompt.py       # System prompt setup
│   └── utils.py               # Utility functions
├── .env                       # Environment variables
├── .gitattributes
├── .gitignore
├── Dockerfile
├── README.md
└── requirements.txt           # Python dependencies

🚀 Getting Started

1. Clone the Repository

git clone https://github.com/your-username/Gemini-Agent.git
cd Gemini-Agent

2. Install Dependencies

Make sure you have Python 3.10+ installed.

pip install -r requirements.txt

3. Activate Virtual Environment (if not already)

Ensure your virtual environment is activated. If you're using .venv, run:

• On Windows:

  .venv\Scripts\activate

• On macOS/Linux:

  source .venv/bin/activate

4. Run the App

Navigate to the src folder and run:

cd src
py -m streamlit run streamlit_app.py

On Linux/macOS, use:

python3 -m streamlit run streamlit_app.py

🛠 Features

• Modular tool definitions and selection
• Gemini LLM integration
• Session history handling
• Customizable system prompts
• Visual interface with Streamlit

📄 License

This project is licensed under the MIT License.