The community member is asking if there is a 'RetryCorrectnessQueryEngine' that uses a 'CorrectnessEvaluator' instead of a 'GuidelineEvaluator', and if not, how they could evaluate a response using a golden dataset to check for correctness and retry if necessary. Another community member suggests looking into a custom query engine, and provides a link to an example. The community members also discuss some issues with the new Llama Index website.
Is there a ‘RetryGuidelineQueryEngine’ that instead of feeding a ‘GuidelineEvaluator’ instead use a ‘CorrectnessEvaluator’? So I guess it would be called a ‘RetryCorrectnessQueryEngine’? Does this exist? If not how could I evaluate a response using a golden dataset to check for correctness and retry if necessary?
