[Evaluation] Change RougeType to Enum (Azure#38131)

* Change RougeType to Enum

* update test recording

* update assets.json

* try to update recordings to fix the failed tests

* update

* revert assets.json

* update

Author: ninghu

sdk/evaluation/azure-ai-evaluation/assets.json

@@ -2,5 +2,5 @@
   "AssetsRepo": "Azure/azure-sdk-assets",
   "AssetsRepoPrefixPath": "python",
   "TagPrefix": "python/evaluation/azure-ai-evaluation",
-  "Tag": "python/evaluation/azure-ai-evaluation_eb4989f81d"
+  "Tag": "python/evaluation/azure-ai-evaluation_e3ec13551e"
 }

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_rouge/_rouge.py

@@ -6,10 +6,9 @@
 from promptflow._utils.async_utils import async_run_allowing_running_loop
 
 from azure.ai.evaluation._vendor.rouge_score import rouge_scorer
-from azure.core import CaseInsensitiveEnumMeta
 
 
-class RougeType(str, Enum, metaclass=CaseInsensitiveEnumMeta):
+class RougeType(Enum):
     """
     Enumeration of ROUGE (Recall-Oriented Understudy for Gisting Evaluation) types.
     """
@@ -38,8 +37,8 @@ def __init__(self, rouge_type: RougeType):
         self._rouge_type = rouge_type
 
     async def __call__(self, *, ground_truth: str, response: str, **kwargs):
-        scorer = rouge_scorer.RougeScorer(rouge_types=[self._rouge_type])
-        metrics = scorer.score(ground_truth, response)[self._rouge_type]
+        scorer = rouge_scorer.RougeScorer(rouge_types=[self._rouge_type.value])
+        metrics = scorer.score(ground_truth, response)[self._rouge_type.value]
         return {
             "rouge_precision": metrics.precision,
             "rouge_recall": metrics.recall,