llm

Also worth knowing about in this space is ellama: https://github.com/s-kostyaev/ellama which uses the LLM package: https://github.com/ahyatt/llm#ollama to talk to ollama, and while ellama doesn't currently support talking over the network to ollama it also doesn't look like that would be a hard thing to add (specifically there are host and port params the underlying function supports but ellama doesn't use).

Maybe ellama[1] would work? It doesn't support Phind yet, but a provider could be created for the underlying connection package llm[2]. [1]: https://github.com/s-kostyaev/ellama [2]: https://github.com/ahyatt/llm