40 lines
1.3 KiB
Markdown
40 lines
1.3 KiB
Markdown
# OmniParser: Screen Parsing tool for Pure Vision Based GUI Agent
|
|
|
|
|
|
|
|
[](https://arxiv.org/abs/2408.00203)
|
|
[](https://opensource.org/licenses/MIT)
|
|
|
|
**OmniParser** is a comprehensive method for parsing user interface screenshots into structured and easy-to-understand elements, which significantly enhances the ability of GPT-4V to generate actions that can be accurately grounded in the corresponding regions of the interface.
|
|
|
|
## Install
|
|
```python
|
|
conda create -n "omni" python==3.12
|
|
pip install -r requirements.txt
|
|
```
|
|
|
|
## Examples:
|
|
We put together a few simple examples in the demo.ipynb.
|
|
|
|
## Gradio Demo
|
|
To run gradio demo, simply run:
|
|
```python
|
|
python gradion_demo.py
|
|
```
|
|
|
|
|
|
## 📚 Citation
|
|
Our technical report can be found [here](https://arxiv.org/abs/2408.00203).
|
|
If you find our work useful, please consider citing our work:
|
|
```
|
|
@misc{lu2024omniparserpurevisionbased,
|
|
title={OmniParser for Pure Vision Based GUI Agent},
|
|
author={Yadong Lu and Jianwei Yang and Yelong Shen and Ahmed Awadallah},
|
|
year={2024},
|
|
eprint={2408.00203},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.CV},
|
|
url={https://arxiv.org/abs/2408.00203},
|
|
}
|
|
```
|