Metadata-Version: 2.4
Name: clip-streamlit
Version: 1.0.0
Summary: Zero-shot image classification using CLIP and Streamlit
Home-page: https://github.com/smiley-victim/clip-streamlit
Author: smiley-victim
Author-email: smiley-victim <itzmyprivateone@gmail.com>
License: MIT
Project-URL: Homepage, https://github.com/smiley-victim/clip-streamlit
Project-URL: Repository, https://github.com/smiley-victim/clip-streamlit.git
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: streamlit>=1.0.0
Requires-Dist: torch>=1.7.0
Requires-Dist: Pillow>=8.0.0
Dynamic: author
Dynamic: home-page
Dynamic: license-file
Dynamic: requires-python

# CLIP Streamlit

A Streamlit application for zero-shot image classification using OpenAI's CLIP model.

## Features

- Zero-shot image classification
- Interactive web interface
- Support for custom labels
- Confidence threshold adjustment
- Visual results with bar charts

## Installation

Simple installation:
```bash
pip install clip-streamlit
```

The package will automatically install CLIP when you first run the application.

## Usage

Run the application:
```bash
clip-streamlit
```

The first time you run it, it will install CLIP if needed.

Or use it in your Python code:

```python
from clip_streamlit import run_app

run_app()
```

## Requirements

- Python 3.7+
- Streamlit
- PyTorch
- CLIP
- Pillow

## License

MIT License
