Handle missing verdicts in Faithfulness eval

[andreaslillebo]

Description:

The count_verified_statements method currently fails with an undefined method 'captures' for nil error when the expected string "Final verdict for each statement in order:" is absent from the LLMs response. This typically occurs if the provided context is either blank or not relevant to the question/answer.

Proposed Change:

This pull request introduces a guard clause in the count_verified_statements method to handle cases where the LLMs output does not contain the expected verdict format. I think returning a score of 0.0 makes sense given that this would be the correct score in most of these failure cases.

Code Changes:

• A conditional check is added to return 0.0 immediately if no match is found in the verifications string.

[andreibondarev]

@andreaslillebo Thank you for the PR!