Modified Cha to not query OpenAI's list_model endpoint if a model is specified in the argument. This will reduce load time.
But, if the specified model is not a valid model, the Cha will still run but it will error out AFTER you enter a prompt. This is not great but I think it's worth it for the reduction in load time.
Modified Cha to not query OpenAI's list_model endpoint if a model is specified in the argument. This will reduce load time.
But, if the specified model is not a valid model, the Cha will still run but it will error out AFTER you enter a prompt. This is not great but I think it's worth it for the reduction in load time.