Add evaluator ids (Azure#38369)

needuv · web-flow · commit 5df580710668 · 2024-11-06T22:55:38.000Z
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_bleu/_bleu.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_bleu/_bleu.py
@@ -47,7 +47,7 @@ class BleuScoreEvaluator:
             :caption: Initialize and call an BleuScoreEvaluator.
     """
 
-    id = "bleu"
+    id = "azureml://registries/azureml/models/Bleu-Score-Evaluator/versions/3"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     def __init__(self):
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_coherence/_coherence.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_coherence/_coherence.py
@@ -41,7 +41,7 @@ class CoherenceEvaluator(PromptyEvaluatorBase[Union[str, float]]):
     _PROMPTY_FILE = "coherence.prompty"
     _RESULT_KEY = "coherence"
 
-    id = "coherence"
+    id = "azureml://registries/azureml/models/Coherence-Evaluator/versions/4"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     @override
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_content_safety/_hate_unfairness.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_content_safety/_hate_unfairness.py
@@ -58,7 +58,7 @@ class HateUnfairnessEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
             :caption: Initialize and call a HateUnfairnessEvaluator.
     """
 
-    id = "hate_unfairness"
+    id = "azureml://registries/azureml/models/Hate-and-Unfairness-Evaluator/versions/4"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     @override
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_content_safety/_self_harm.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_content_safety/_self_harm.py
@@ -52,7 +52,7 @@ class SelfHarmEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
             :caption: Initialize and call a SelfHarmEvaluator.
     """
 
-    id = "self_harm"
+    id = "azureml://registries/azureml/models/Self-Harm-Related-Content-Evaluator/versions/3"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     @override
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_content_safety/_sexual.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_content_safety/_sexual.py
@@ -54,7 +54,7 @@ class SexualEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
             :caption: Initialize and call a SexualEvaluator.
     """
 
-    id = "sexual"
+    id = "azureml://registries/azureml/models/Sexual-Content-Evaluator/versions/3"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     @override
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_content_safety/_violence.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_content_safety/_violence.py
@@ -54,7 +54,7 @@ class ViolenceEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
             :caption: Initialize and call a ViolenceEvaluator.
     """
 
-    id = "violence"
+    id = "azureml://registries/azureml/models/Violent-Content-Evaluator/versions/3"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     @override
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_f1_score/_f1_score.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_f1_score/_f1_score.py
@@ -131,7 +131,7 @@ class F1ScoreEvaluator:
             :caption: Initialize and call an F1ScoreEvaluator.
     """
 
-    id = "f1_score"
+    id = "azureml://registries/azureml/models/F1Score-Evaluator/versions/3"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     def __init__(self):
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_fluency/_fluency.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_fluency/_fluency.py
@@ -43,7 +43,7 @@ class FluencyEvaluator(PromptyEvaluatorBase[Union[str, float]]):
     _PROMPTY_FILE = "fluency.prompty"
     _RESULT_KEY = "fluency"
 
-    id = "fluency"
+    id = "azureml://registries/azureml/models/Fluency-Evaluator/versions/3"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     @override
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_gleu/_gleu.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_gleu/_gleu.py
@@ -44,7 +44,7 @@ class GleuScoreEvaluator:
             :caption: Initialize and call a GleuScoreEvaluator.
     """
 
-    id = "gleu_score"
+    id = "azureml://registries/azureml/models/Gleu-Score-Evaluator/versions/3"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     def __init__(self):
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_groundedness/_groundedness.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_groundedness/_groundedness.py
@@ -55,7 +55,7 @@ class GroundednessEvaluator(PromptyEvaluatorBase[Union[str, float]]):
     _RESULT_KEY = "groundedness"
     _OPTIONAL_PARAMS = ["query"]
 
-    id = "groundedness"
+    id = "azureml://registries/azureml/models/Groundedness-Evaluator/versions/4"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     @override
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_meteor/_meteor.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_meteor/_meteor.py
@@ -65,7 +65,7 @@ class MeteorScoreEvaluator:
             :caption: Initialize and call a MeteorScoreEvaluator with alpha of 0.8.
     """
 
-    id = "meteor"
+    id = "azureml://registries/azureml/models/Meteor-Score-Evaluator/versions/3"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     def __init__(self, alpha: float = 0.9, beta: float = 3.0, gamma: float = 0.5):
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_protected_material/_protected_material.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_protected_material/_protected_material.py
@@ -39,7 +39,7 @@ class ProtectedMaterialEvaluator(RaiServiceEvaluatorBase[Union[str, bool]]):
             :caption: Initialize and call a ProtectedMaterialEvaluator.
     """
 
-    id = "protected_material"
+    id = "azureml://registries/azureml/models/Protected-Material-Evaluator/versions/3"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     @override
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_relevance/_relevance.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_relevance/_relevance.py
@@ -48,7 +48,7 @@ class RelevanceEvaluator(PromptyEvaluatorBase):
     _PROMPTY_FILE = "relevance.prompty"
     _RESULT_KEY = "relevance"
 
-    id = "relevance"
+    id = "azureml://registries/azureml/models/Relevance-Evaluator/versions/4"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     @override
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_retrieval/_retrieval.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_retrieval/_retrieval.py
@@ -147,7 +147,7 @@ class RetrievalEvaluator(PromptyEvaluatorBase[Union[str, float]]):
         however, it is recommended to use the new key moving forward as the old key will be deprecated in the future.
     """
 
-    id = "retrieval"
+    id = "azureml://registries/azureml/models/Retrieval-Evaluator/versions/1"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     def __init__(self, model_config):  # pylint: disable=super-init-not-called
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_rouge/_rouge.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_rouge/_rouge.py
@@ -73,7 +73,7 @@ class RougeScoreEvaluator:
             :caption: Initialize and call a RougeScoreEvaluator with a four-gram rouge type.
     """
 
-    id = "rouge"
+    id = "azureml://registries/azureml/models/Rouge-Score-Evaluator/versions/3"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     def __init__(self, rouge_type: RougeType):
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_service_groundedness/_service_groundedness.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_service_groundedness/_service_groundedness.py
@@ -45,7 +45,7 @@ class GroundednessProEvaluator(RaiServiceEvaluatorBase[Union[str, bool]]):
         for the groundedness pro label will be "groundedness_pro_passing_rate".
     """
 
-    id = "groundedness_pro"
+    id = "azureml://registries/azureml/models/Groundedness-Pro-Evaluator/versions/1"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     @override
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_similarity/_similarity.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_similarity/_similarity.py
@@ -113,7 +113,7 @@ class SimilarityEvaluator:
         however, it is recommended to use the new key moving forward as the old key will be deprecated in the future.
     """
 
-    id = "similarity"
+    id = "azureml://registries/azureml/models/Similarity-Evaluator/versions/3"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     def __init__(self, model_config):
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_xpia/xpia.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_xpia/xpia.py
@@ -54,7 +54,7 @@ class IndirectAttackEvaluator(RaiServiceEvaluatorBase[Union[str, bool]]):
             :caption: Initialize and call an IndirectAttackEvaluator.
     """
 
-    id = "xpia"
+    id = "azureml://registries/azureml/models/Indirect-Attack-Evaluator/versions/3"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     @override
diff --git a/sdk/evaluation/azure-ai-evaluation/tests/unittests/test_evaluator_ids.py b/sdk/evaluation/azure-ai-evaluation/tests/unittests/test_evaluator_ids.py
