Anthony Ivan

Results 3 comments of Anthony Ivan

How would this work with the output-based/RAG-based metrics such as `answer-relevance`, `context-relevance`, `context-faithfulness`?

I created #671 as another potential way to go about making this change, and added explanation on my end on why this functionality should be available

@shahules786 is the behaviour you are describing above implemented by setting raise_exceptions=False_ in evaluate()?