Ollama support

[michaelmior]

Feature request

Is your feature request related to a problem? Please describe.

I'd like to be able to use a local model with Ollama.

Describe the solution you'd like

I want to be able to use a local Ollama instance with seed.

Describe alternatives you've considered

Cloud based models require an Internet connection as well as an account with a third party.
It would be possible to use something like LocalAI which provides an OpenAI-compatible API for local models, but this is a pretty heavyweight solution.

Additional context

LangChain.js already has Ollama support.
It seems like this could be as simple as allowing an OLLAMA_MODEL environment variable that can be used to construct a ChatOllama instance.

[BRAVO68WEB]

+1

[chirag3003]

+1

[Ba3a-G]

+1 🚀

[simmorsal]

How is this still open?!

[BRAVO68WEB]

Why @simmorsal ?

[simmorsal]

@BRAVO68WEB sorry if I came across as rude. I meant, as the original feature requester mentioned, many tools now support pointing to an OpenAI compatible route to use AI with them, including the openai-edge package that this project is using.

With them supporting Ollama would be as simple as adding a URL value to the .env file, and passing it in the package's initialization options. So this confused me and I can't realize if there are problems with using Ollama inside Supabase!?