May I choose the RAG Embedding model? Since I have deployed openwebui onto my NAS server, which has limited computing power, can I opt for OpenAI's embedding model to reduce local computational resources usage?
Originally created by @leoleelxh on GitHub (Mar 14, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/1169
May I choose the RAG Embedding model? Since I have deployed openwebui onto my NAS server, which has limited computing power, can I opt for OpenAI's embedding model to reduce local computational resources usage?
Embedding is currently only possible locally, there's no support for using external embedding model APIs as of right now. PRs of course welcome, we could potentially support Ollama or OpenAI embedding I think.
<!-- gh-comment-id:1997558237 -->
@justinh-rahb commented on GitHub (Mar 14, 2024):
Embedding is currently only possible locally, there's no support for using external embedding model APIs as of right now. PRs of course welcome, we _could_ potentially support Ollama or OpenAI embedding I think.
Embedding is currently only possible locally, there's no support for using external embedding model APIs as of right now. PRs of course welcome, we could potentially support Ollama or OpenAI embedding I think.
Yes, that's a great idea, which would give openwebui more flexibility.
<!-- gh-comment-id:1997564368 -->
@leoleelxh commented on GitHub (Mar 14, 2024):
> Embedding is currently only possible locally, there's no support for using external embedding model APIs as of right now. PRs of course welcome, we _could_ potentially support Ollama or OpenAI embedding I think.
Yes, that's a great idea, which would give openwebui more flexibility.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @leoleelxh on GitHub (Mar 14, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/1169
May I choose the RAG Embedding model? Since I have deployed openwebui onto my NAS server, which has limited computing power, can I opt for OpenAI's embedding model to reduce local computational resources usage?
@justinh-rahb commented on GitHub (Mar 14, 2024):
Embedding is currently only possible locally, there's no support for using external embedding model APIs as of right now. PRs of course welcome, we could potentially support Ollama or OpenAI embedding I think.
@leoleelxh commented on GitHub (Mar 14, 2024):
Yes, that's a great idea, which would give openwebui more flexibility.
@jannikstdl commented on GitHub (Mar 14, 2024):
related #679
@tjbck commented on GitHub (Mar 14, 2024):
Duplicate https://github.com/open-webui/open-webui/issues/679