non-conversational metrics, when applied to a ConversationalTestCase, will NOT evaluate the last turn

[sermakarevich]

❗BEFORE YOU BEGIN❗
Are you on discord? 🤗 We'd love to have you asking questions on discord instead: https://discord.com/invite/a3K9c8GRGt

Describe the bug
Documentation states: non-conversational metrics (which are metrics used for individual LLMTestCases), when applied to a ConversationalTestCase, will evaluate the last turn in a
While in AnswerRelevancyMetric and other 13 metrics, not the last, but first one is evaluated:

if isinstance(test_case, ConversationalTestCase):
     test_case = test_case.turns[0]

To Reproduce
not required

Expected behavior
sync documentation and implementation

Screenshots

Desktop (please complete the following information):

Smartphone (please complete the following information):

Additional context
Add any other context about the problem here.

[penguine-ip]

@sermakarevich good catch....can't believe this got unnoticed for so long