This repository contains an easy-to-use interface for the Gemini Pro and Pro Vision models using the Gradio library. Gradio simplifies the process of creating user interfaces for machine learning models, allowing users to interact with the models through a web interface.

Before running the interface, make sure you have the following dependencies installed:

• Python (>= 3.6)
• Gradio (install using pip install gradio)

1. Clone this repository:

   git clone https://github.com/anand-sangabattuni/gemini-gradio.git

2. Navigate to the project directory:

   cd gemini-gradio

3. Install the required dependencies:

   pip install -r requirements.txt

To use the Gemini Pro and Pro Vision models, you need to obtain an API key from Google Maker Studio(https://makersuite.google.com/). Follow the documentation on Google Maker Studio to obtain the API key and update the configuration in the app.py file.

1. Run the Gradio interface:

   python app.py

2. Open your web browser and go to http://localhost:7860/ to access the Gradio interface.

3. Use the interface to interact with the Gemini Pro and Pro Vision models. Upload images or input data as required, and observe the model's predictions.

Feel free to customize the interface based on your specific needs. You can modify the app.py file to change the layout, add new features, or adjust the input/output components.

For any issues, questions, or feedback, please open an issue in the GitHub repository. We appreciate your contributions and suggestions!

This project is licensed under the MIT License