Skip to content

Docker

Experimental

Talemate through docker has not received a lot of testing from me, so please let me know if you encounter any issues.

You can do so by creating an issue on the GitHub repository

Quick install instructions

  1. git clone https://github.com/vegu-ai/talemate.git
  2. cd talemate
  3. copy config file
    1. linux: cp config.example.yaml config.yaml
    2. windows: copy config.example.yaml config.yaml
  4. If your host has a CUDA compatible Nvidia GPU
    1. Windows (via PowerShell): $env:CUDA_AVAILABLE="true"; docker compose up
    2. Linux: CUDA_AVAILABLE=true docker compose up
  5. If your host does NOT have a CUDA compatible Nvidia GPU
    1. Windows: docker compose up
    2. Linux: docker compose up
  6. Navigate your browser to http://localhost:8080

Note

When connecting local APIs running on the hostmachine (e.g. text-generation-webui), you need to use host.docker.internal as the hostname.