The community member is curious about the "no_text" response mode in the query evaluator and query response evaluator, and how it affects the accuracy of the evaluator. They also found that the code of the evaluators assumes an answer with the prompt. Another community member responds that the "no_text" mode only sets the source_nodes of the response object, and is useful for retrieving nodes without calling the language model, but since there is no response text, there is nothing to evaluate.
Hi all, I was going through the documentation of query evaluator & query response evaluator, I found out it examples where response_mode="no_text" So, I'm curious to know when we use no_text response mode does it affect the accuracy of evaluator?
When gone through the code of evaluators, I also found out that answer=str(response) is requried and prompt are written in such ways that It assumes an answer with it.
