- Install OLLAMA from it WebSite: https://ollama.com/
- Run a OLLAMA model:
$ ollama run llama3.2 - Install Python3
- MacOS: already installed
- Windows: download it from the site: https://www.python.org/downloads/
- Install pip3
- MacOS: already installed
- Windows:
> curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py> python get-pip.py
- Install+Generate+Activate pyenv:
- create your local venv:
- Windows:
- CMD:
> python -m venv venv - GitBash:
$ python -m venv venv
- CMD:
- MacOS:
$ python3 -m venv venv
- Windows:
- activate your local venv:
- MacOS:
$ source venv/bin/activate - Windows:
- GitBash:
> source venv/Scripts/activate - CMD:
> venv\Scripts\activate
- GitBash:
- MacOS:
- install depnendencies:
$ brew install cmake apache-arrow$ pip install -r requirements.txt
- create your local venv:
- Run StreamLit:
$ streamlit run app.py - PS.:
- before running the streamlit:app on PyCharm it is necessary to run the command directly on the Terminal
- on the terminal input/insert your email to sign on it
- PyCharm Debug:
- create a config run
- if it raise any error on run/debug just delete and create a new run file:
- set it to module instead of script
- module value =
streamlit - script parameters =
run app.py
- IF errors like: "asyncio\base_events.py:182" or "Python\Python312\Lib\asyncio\events.py", line 88" you must disable
python.debug.asyncio.repl:- click on seach icon (top right near to close button X)
- type on the search input: "registry" and click on "registry..."
- look for
python.debug.asyncio.repland uncheck the checkbox
- experiments: some backup code for reference future investigations
- src: the application source code for long run
- app.py: the application entry point