- Python 3.8+ (recommended)
- Chrome installed (for TTS via Selenium). A matching chromedriver is included at
DATA/ZERO_DRIVERS/chromedriver.exe.
- Open a Command Prompt at the project root (
R:\Projects\3_Advanced_AI_Assistant\ZERO_3.0). - Run the setup script (creates a venv and installs packages):
setup_env.bat
- Activate the environment:
call .venv\Scripts\activate
- Run the UI:
python USER_INTERFACE\ui.py(click the mic GIF to start the assistant)
Alternatives:
- Run the core assistant directly (console):
python MAIN\main.py
- If
pyaudiofails to install with pip, the setup script attempts to usepipwinto fetch a compatible wheel. - If Selenium raises version errors, update
DATA/ZERO_DRIVERS/chromedriver.exeto match your Chrome version or installwebdriver-manager. - Ensure microphone permissions are enabled in Windows settings.
requirements.txt— detected dependenciessetup_env.bat,run_ui.bat,run_main.bat— convenience scriptsREADME.md— this file
If you'd like, I can also add a small Powershell script, or create a requirements-dev.txt pinning versions. Just tell me which you'd prefer.