[Python] How to avoid a Torch error with Open WebUI/Ollama

Discussão em 'Python' iniciado por Stack, Março 23, 2025.

  1. Stack

    Stack Membro Participativo

    I'd like to get Open WebUI working with Ollama on Ubuntu 24.10, but installing it using pip and venv leads me to a torch error.

    Firstly, Ollama (0.6.2) is working: I can type /path/to/ollama list and see the 3 models I've been working with.

    Next, I follow the guidance in the error message after pip install open-webui, relating to the use of the APT package manager, and so I use venv:

    sudo apt-get install python3-full
    python3 -m venv /path/to/venv
    source /path/to/venv/bin/activate
    python install open-webui


    I then try python open-webui serve, but this complains that there is no file or directory called open-webui in my $HOME directory. I see there is an executable file called open-webui in my /path/to/venv/bin so I try:

    python /path/to/venv/bin/open-webui serve


    ...and I see the large OPEN WEBUI text , and an error. Opening http://localhost:8080 in my browser seems to work, but how can I avoid the following error message?:

    ERROR [open_webui.main] Error updating models: cannot import name 'Tensor' from 'torch' (unknown location)

    Continue reading...

Compartilhe esta Página