https://github.com/zeinhasan/gemini-streamlit-integration
Integrate Gemini with Streamlit
https://github.com/zeinhasan/gemini-streamlit-integration
Last synced: 4 months ago
JSON representation
Integrate Gemini with Streamlit
- Host: GitHub
- URL: https://github.com/zeinhasan/gemini-streamlit-integration
- Owner: zeinhasan
- License: mit
- Created: 2024-09-08T05:18:45.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2024-09-08T06:12:48.000Z (9 months ago)
- Last Synced: 2025-01-02T11:28:36.568Z (6 months ago)
- Language: Python
- Size: 17.6 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Gemini Streamlit Integration
This project is a Streamlit-based chatbot application utilizing various Gemini models for natural language processing. Users can switch between light and dark modes and configure model settings to customize their interactions.
## Features
- Toggle between light and dark mode.
- Choose from three different Gemini models: `Gemini 1.5 Flash`, `Gemini 1.5 Pro`, and `Gemini 1.0 Pro`.
- Adjust model parameters such as temperature, top-p, top-k, and maximum output tokens.
- Securely input and use the Gemini API key.
- Interactive chat interface with history.
## Installation
To get started, clone the repository and install the required packages:
```bash
git clone https://github.com/zeinhasan/Gemini-Streamlit-Integration
cd Gemini-Streamlit-Integration
pip install -r requirements.txt
```
## Usage
Run the Streamlit application with:
```bash
streamlit run app.py
```
## Configuration
The application settings can be adjusted via the sidebar:
- Dark Mode: Toggle between light and dark mode.
- Choose Model: Select from Gemini 1.5 Flash, Gemini 1.5 Pro, or Gemini 1.0 Pro.
- Temperature: Adjust the creativity of the model's responses.
- Top P: Control the cumulative probability for token selection.
- Top K: Limit the number of tokens considered.
- Max Output Tokens: Set the maximum number of tokens in the response.
## License
his project is licensed under the MIT License. See the LICENSE file for details.