Dom/OmniParser
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

app logo file name fix； Acknowledgment; risk mitigation

Browse Source
This commit is contained in:
yadonglu
2025-02-05 23:37:19 -08:00
parent cb92e432b3
commit dbb86b2f4c
3 changed files with 8 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@@ -9,3 +9,4 @@ debug.ipynb
util/__pycache__/ util/__pycache__/
index.html?linkid=2289031 index.html?linkid=2289031
wget-log wget-log
weights/omniv2/

2
omnitool/gradio/app.py
View File

@@ -259,7 +259,7 @@ def get_header_image_base64():
try: try:
# Get the absolute path to the image relative to this script # Get the absolute path to the image relative to this script
script_dir = Path(__file__).parent script_dir = Path(__file__).parent
image_path = script_dir.parent.parent / "imgs" / "header_bar_small.png" image_path = script_dir.parent.parent / "imgs" / "header_bar_thin.png"
with open(image_path, "rb") as image_file: with open(image_path, "rb") as image_file:
encoded_string = base64.b64encode(image_file.read()).decode() encoded_string = base64.b64encode(image_file.read()).decode()

5
omnitool/readme.md
View File

@@ -84,3 +84,8 @@ There are three components:
c. Start the server with `python app.py --windows_host_url localhost:8006 --omniparser_server_url localhost:8000` c. Start the server with `python app.py --windows_host_url localhost:8006 --omniparser_server_url localhost:8000`
d. Open the URL in the terminal output, set your API Key and start playing with the AI agent! d. Open the URL in the terminal output, set your API Key and start playing with the AI agent!
## Acknowledgment
Kudos to the amazing resources that are indispensable in the development of our code: [Claude Computer Use](https://github.com/anthropics/anthropic-quickstarts/blob/main/computer-use-demo/README.md), [OS World](https://github.com/xlang-ai/OSWorld), [Windows Agent Arena](https://github.com/microsoft/WindowsAgentArena), and [computer_use_ootb](https://github.com/showlab/computer_use_ootb).
We are grateful for helpful suggestions and feedbacks provided by Francesco Bonacci, Jianwei Yang, Dillon DuPont, Yue Wu, Anh Nguyen.