Eric Curtin
Eric Curtin
I also like where this is going, but I don't want to get into a scenario where `ramalama client` is forking from `ramalama run`... `ramalama run` is basically client +...
As an example `class RamaLamaShell` and `class RagClient` should just be one class.
> > I also like where this is going, but I don't want to get into a scenario where `ramalama client` is forking from `ramalama run`... `ramalama run` is basically...
> @bmahabirbu ack, let me know once you're done 👍 > > About the endpoint, in the OpenAI compatible API I think mainly the chat completions API is where RAG...
I like this idea, it's something I discussed with @rhatdan a couple of years ago, but ultimately never got around to writing any code or reference implementation. Meeting @cgwalters yesterday...
> I do not want to have this feature if the primary goal is to exploit and exhaust public OCI registries. Genuinely, I don't believe that is the primary goal....
Ideally we'd just call skopeo/podman or something like that. My vote at this point at least is try to integrate with podman artifact
Nice insights 😄 and how do you envision the push side? One thing I wonder about the push side, leaving the protocols and storage aside for a minute. One thing...
This code LGTM waiting on builds
> > This code LGTM waiting on builds > > Should pass now. Didn't review the latest changes from master thoroughly. > > Not sure why I get > >...