Docs/Maho: Difference between revisions

 

=== Maintenance ===

New media should be added to <code>/salieri/jellyfin/import</code> and separated into each subfolder depending on media type.

 

 

On the top function bar (same bar filters is in) select <code>Edit Movies</code>, <code>Select Series</code>, or however it is formatted for the *arr application. If filtered right, we should only see our newly imported media and not old media. If this is true click <code>Select All</code>, then edit at the very bottom of the page.

Under <code>Root Folder</code>, select the base path that best fits the newly indexed media (<code>/movies</code> for our Radarr example) and finally move the media to the base <code>/salieri/jellyfin/media/(media type)</code> folder.

 

(Detail about *arr setup and how to change settings)

 

Language and other models are to be hosted on the two GPU's and are than reverse proxied. A user on LUG's Sillytavern (or any front end where an API can be called on) can then select what model to prompt.

 

Koboldcpp is currently used to run .GGUF models on mixed CPU and GPU allowing for language models (LLM), embedding models (used for data vectorization), text-to-speech (TTS), speech to text, and image generation under one application.