Local models are not working on docker instance

[alaa-eddine]

When I configure a custom model that runs on my local machine (using LM Studio or Ollama) on http://127.0.0.1/v1 the LLM does not work.

if I configure it with a fallback, the fallback is called (which means the main did not work)
if I don't configure a fallback, it just fails

[AhmedEssam05]

Thanks for reporting this @alaa-eddine

@forhad-hosain could u please check and follow up on this issue