fix numpy invert error in metrics (#1835)

#1796 TypeError(ufunc 'invert' not supported for the input types, and
the inputs could not be safely coerced to any supported types according
to the casting rule ''safe'') will trigger when evaluating by
`FactualCorrectness`

Author: oslijunw

src/ragas/metrics/_factual_correctness.py

@@ -260,6 +260,7 @@ async def _single_turn_ascore(
         tp = sum(reference_response)
         fp = sum(~reference_response)
         if self.mode != "precision":
+            response_reference = np.array(response_reference, dtype=bool)
             fn = sum(~response_reference)
         else:
             fn = 0