Fix LLMAsJudge validation with OpenAIInferenceEngine

[lilacheden]

The current validation code states:

        if isinstance(self.inference_model, OpenAiInferenceEngine):
            if self.format and type(self.format) is not SystemFormat:
                raise ValueError(
                    "Error in 'LLMAsJudge' metric. Inference model 'OpenAiInferenceEngine' does "
                    "not support formatting. Please remove the format definition from the recipe"
                    " (OpenAi Chat API take care of the formatting automatically)."
                )

If OpenAiInferenceEngine does not support formatting, need to assure that self.format is an empty format, not any SystemFormat.