search

alondmnt / joplin-plugin-jarvis

Joplin (note-taking) assistant running a very intelligent system (OpenAI/GPT, Hugging Face, Gemini, Llama, Universal Sentence Encoder, etc.)
GNU Affero General Public License v3.0
226 stars 22 forks source link

Add instructions for additional offline embedding models #20

Closed Hegghammer closed 8 months ago

Hegghammer commented 8 months ago

Some users might want to use a custom offline embedding model, for example to get multilanguage support. These instructions show one way of doing it.

alondmnt commented 8 months ago

Great idea! Thank you, this is an excellent addition.

While testing this I noticed that this can be achieved with Xinference alone, without the need for LiteLLM, which makes the process more streamlined. I'll make this minor adjustment and then merge.