env

[newworld1020]

all needs:activate omni

models->weights

python gradio_demo.py

cd OmniParser/omnitool/omniparserserver
python -m omniparserserver

Windows 11 Enterprise Evaluation (90-day trial, English, United States) ISO rename->custom.iso

custom.iso复制OmniParser/omnitool/omnibox/vm/win11iso

cd OmniParser/omnitool/omnibox/scripts
docker->>>

./manage_vm.sh create
or
.\manage_vm.ps1 create

when VM + server is up and running!

./manage_vm.sh start
or
.\manage_vm.ps1 start

http://localhost:8006/vnc.html?view_only=1&autoconnect=1&resize=scale

test:http://localhost:5000/probe
it will print
{
"message": "Service is operational",
"status": "Probe successful"
}

activate omni

cd OmniParser/omnitool/gradio

python app.py --windows_host_url localhost:8006 --omniparser_server_url localhost:8000

api::r1-error
gpt or qwen2.5vl

if http://localhost:5000/probe error
open vm
install python
if python version error
forbidden python 2
install python 3.12
git clone omniparser
pip install -r requirments.txt
then ->find win11setup->winscripts->server->main.py
python main.py
print:::::
(omni) D:\OmniParser\omnitool\omnibox\vm\win11setup\setupscripts\server>python main.py

• Serving Flask app 'main'
• Debug mode: on

[newworld1020]

input apikey and operations
start