feat(inference): introducing InferenceProviders

[axel7083]

What does this PR do?

Introducing InferenceProvider interface, which is an abstraction class made to create InferenceServers. In todays implementation we do not make distinctions between backends (llamacpp, whispercpp etc.)

This is the first step in abstracting the inference providers, to ease the customization of inference server with new provider in the future (whispercpp, llamacpp-cuda, ollama etc.)

Documentation

What issues does this PR fix or reference?

Fixes #1112

How to test this PR?

• unit tests has been provided

Manually (recommended)

• Create an inference server
• Start chatbot recipe

[feloy]

In a near future, we will want to run inference servers in Kubernetes clusters too (OpenShift AI typically). I cannot see anything blocking doing this with this architecture, but just to be sure you have this scenario in mind

[axel7083]

In a near future, we will want to run inference servers in Kubernetes clusters too (OpenShift AI typically). I cannot see anything blocking doing this with this architecture, but just to be sure you have this scenario in mind

Thanks @feloy for this feedback. I was not having this in mind, but I think it would make it easier than our current architecture, as we could create a KubernetesInferenceProvider responsible of creating the pod in the Kubernetes cluster.

[lstocchi]

Codewise LGTM. Also tested and works fine. Nice job!!

[jeffmaury]

Dependency on Podman Desktop 1.11 does not seems an absolute requirement and could be relaxed with few changes so I would delay merge as @slemeur approval should be required

[axel7083]

Dependency on Podman Desktop 1.11 does not seems an absolute requirement and could be relaxed with few changes so I would delay merge as @slemeur approval should be required

@jeffmaury I revert to @podman-desktop/api 1.10.3. As mention there is not absolute requirement.