Other LLMs

[kqvanity]

Can I use other LLMs? I connect to other remote models via their API, then locally rebroadcast a web server that bridge any OpenAI-compatible HTTP requests to the respective model.

I can see Lumos hitting /tags so I'm not sure

Available endpoints.

Chat Completions API: http://localhost:11434/v1/chat/completions
Embeddings API:       http://localhost:11434/v1/embeddings
Rerank API:           http://localhost:11434/v1/rerank

[andrewnguonly]

Can I use other LLMs?

You can use any LLM that's available on your Ollama server.