Updating evaluator id to new format (Azure#42273)

singankit · web-flow · commit 1f0488ce849c · 2025-07-30T09:16:21.000-07:00
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
@@ -54,7 +54,7 @@ class BleuScoreEvaluator(EvaluatorBase):
             :caption: Initialize with threshold and call an BleuScoreEvaluator.
     """
 
-    id = "azureml://registries/azureml/models/Bleu-Score-Evaluator/versions/3"
+    id = "azureai://built-in/evaluators/bleu_score"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     def __init__(self, *, threshold=0.5):
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_code_vulnerability/_code_vulnerability.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_code_vulnerability/_code_vulnerability.py
@@ -79,7 +79,7 @@ class CodeVulnerabilityEvaluator(RaiServiceEvaluatorBase[Union[str, bool]]):
         for the code vulnerability will be "code_vulnerability_label".
     """
 
-    id = "code_vulnerability"
+    id = "azureai://built-in/evaluators/code_vulnerability"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
     _OPTIONAL_PARAMS = ["query"]
 
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
@@ -62,7 +62,7 @@ class CoherenceEvaluator(PromptyEvaluatorBase[Union[str, float]]):
     _PROMPTY_FILE = "coherence.prompty"
     _RESULT_KEY = "coherence"
 
-    id = "azureml://registries/azureml/models/Coherence-Evaluator/versions/4"
+    id = "azureai://built-in/evaluators/coherence"
     """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/_content_safety.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_content_safety/_content_safety.py
@@ -68,7 +68,7 @@ class ContentSafetyEvaluator(MultiEvaluatorBase[Union[str, float]]):
             :caption: Initialize with threshold and call a ContentSafetyEvaluator with a query and response.
     """
 
-    id = "content_safety"
+    id = "azureai://built-in/evaluators/content_safety"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
     _OPTIONAL_PARAMS = ["query"]
 
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
@@ -80,7 +80,7 @@ class HateUnfairnessEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
             :caption: Initialize with threshold and call a HateUnfairnessEvaluator with a query and response.
     """
 
-    id = "azureml://registries/azureml/models/Hate-and-Unfairness-Evaluator/versions/4"
+    id = "azureai://built-in/evaluators/hate_unfairness"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
     _OPTIONAL_PARAMS = ["query"]
 
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
@@ -65,7 +65,7 @@ class SelfHarmEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
                 https://{resource_name}.services.ai.azure.com/api/projects/{project_name}.
     """
 
-    id = "azureml://registries/azureml/models/Self-Harm-Related-Content-Evaluator/versions/3"
+    id = "azureai://built-in/evaluators/self_harm"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
     _OPTIONAL_PARAMS = ["query"]
 
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
@@ -76,7 +76,7 @@ class SexualEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
             :caption: Initialize with threshold and call a SexualEvaluator.
     """
 
-    id = "azureml://registries/azureml/models/Sexual-Content-Evaluator/versions/3"
+    id = "azureai://built-in/evaluators/sexual"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
     _OPTIONAL_PARAMS = ["query"]
 
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
@@ -76,7 +76,7 @@ class ViolenceEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
             :caption: Initialize with threshold and call a ViolenceEvaluator.
     """
 
-    id = "azureml://registries/azureml/models/Violent-Content-Evaluator/versions/3"
+    id = "azureai://built-in/evaluators/violence"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
     _OPTIONAL_PARAMS = ["query"]
 
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_document_retrieval/_document_retrieval.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_document_retrieval/_document_retrieval.py
@@ -49,6 +49,9 @@ class DocumentRetrievalEvaluator(EvaluatorBase):
             :caption: Initialize with threshold and call a DocumentRetrievalEvaluator.
     """
 
+    id = "azureai://built-in/evaluators/document_retrieval"
+    """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/_f1_score/_f1_score.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_f1_score/_f1_score.py
@@ -58,7 +58,7 @@ class F1ScoreEvaluator(EvaluatorBase):
             :caption: Initialize with threshold and call an F1ScoreEvaluator.
     """
 
-    id = "azureml://registries/azureml/models/F1Score-Evaluator/versions/3"
+    id = "azureai://built-in/evaluators/f1_score"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     def __init__(self, *, threshold=0.5):
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
@@ -64,7 +64,7 @@ class FluencyEvaluator(PromptyEvaluatorBase[Union[str, float]]):
     _PROMPTY_FILE = "fluency.prompty"
     _RESULT_KEY = "fluency"
 
-    id = "azureml://registries/azureml/models/Fluency-Evaluator/versions/4"
+    id = "azureai://built-in/evaluators/fluency"
     """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
@@ -55,7 +55,7 @@ class GleuScoreEvaluator(EvaluatorBase):
                 https://{resource_name}.services.ai.azure.com/api/projects/{project_name}
     """
 
-    id = "azureml://registries/azureml/models/Gleu-Score-Evaluator/versions/3"
+    id = "azureai://built-in/evaluators/gleu_score"
     """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/_groundedness/_groundedness.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_groundedness/_groundedness.py
@@ -79,7 +79,7 @@ class GroundednessEvaluator(PromptyEvaluatorBase[Union[str, float]]):
     _RESULT_KEY = "groundedness"
     _OPTIONAL_PARAMS = ["query"]
 
-    id = "azureml://registries/azureml/models/Groundedness-Evaluator/versions/4"
+    id = "azureai://built-in/evaluators/groundedness"
     """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/_intent_resolution/_intent_resolution.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_intent_resolution/_intent_resolution.py
@@ -57,7 +57,7 @@ class IntentResolutionEvaluator(PromptyEvaluatorBase[Union[str, float]]):
     _MAX_INTENT_RESOLUTION_SCORE = 5
     _DEFAULT_INTENT_RESOLUTION_THRESHOLD = 3
 
-    id = None
+    id = "azureai://built-in/evaluators/intent_resolution"
     """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(EvaluatorBase):
             :caption: Initialize with threshold and call a MeteorScoreEvaluator.
     """
 
-    id = "azureml://registries/azureml/models/Meteor-Score-Evaluator/versions/3"
+    id = "azureai://built-in/evaluators/meteor_score"
     """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/_protected_material/_protected_material.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_protected_material/_protected_material.py
@@ -50,7 +50,7 @@ class ProtectedMaterialEvaluator(RaiServiceEvaluatorBase[Union[str, bool]]):
 
     """
 
-    id = "azureml://registries/azureml/models/Protected-Material-Evaluator/versions/3"
+    id = "azureai://built-in/evaluators/protected_material"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
     _OPTIONAL_PARAMS = ["query"]
 
diff --git a/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_qa/_qa.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_qa/_qa.py
@@ -74,7 +74,7 @@ class QAEvaluator(MultiEvaluatorBase[Union[str, float]]):
         however, it is recommended to use the new keys moving forward as the old keys will be deprecated in the future.
     """
 
-    id = "qa"
+    id = "azureai://built-in/evaluators/qa"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     def __init__(
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
@@ -75,7 +75,7 @@ class RelevanceEvaluator(PromptyEvaluatorBase):
     _PROMPTY_FILE = "relevance.prompty"
     _RESULT_KEY = "relevance"
 
-    id = "azureml://registries/azureml/models/Relevance-Evaluator/versions/4"
+    id = "azureai://built-in/evaluators/relevance"
     """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/_response_completeness/_response_completeness.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_response_completeness/_response_completeness.py
@@ -64,7 +64,7 @@ class ResponseCompletenessEvaluator(PromptyEvaluatorBase[Union[str, float]]):
     _PROMPTY_FILE = "response_completeness.prompty"
     _RESULT_KEY = "response_completeness"
 
-    id = "completeness"
+    id = "azureai://built-in/evaluators/response_completeness"
 
     _MIN_COMPLETENESS_SCORE = 1
     _MAX_COMPLETENESS_SCORE = 5
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
@@ -74,7 +74,7 @@ class RetrievalEvaluator(PromptyEvaluatorBase[Union[str, float]]):
     _PROMPTY_FILE = "retrieval.prompty"
     _RESULT_KEY = "retrieval"
 
-    id = "azureml://registries/azureml/models/Retrieval-Evaluator/versions/1"
+    id = "azureai://built-in/evaluators/retrieval"
     """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/_rouge/_rouge.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_rouge/_rouge.py
@@ -90,7 +90,7 @@ class RougeScoreEvaluator(EvaluatorBase):
             :caption: Initialize with a specified threshold and call a RougeScoreEvaluator with a four-gram rouge type.
     """
 
-    id = "azureml://registries/azureml/models/Rouge-Score-Evaluator/versions/3"
+    id = "azureai://built-in/evaluators/rouge_score"
     """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/_service_groundedness/_service_groundedness.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_service_groundedness/_service_groundedness.py
@@ -66,7 +66,7 @@ class GroundednessProEvaluator(RaiServiceEvaluatorBase[Union[str, bool]]):
         for the groundedness pro label will be "groundedness_pro_passing_rate".
     """
 
-    id = "azureml://registries/azureml/models/Groundedness-Pro-Evaluator/versions/1"
+    id = "azureai://built-in/evaluators/groundedness_pro"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
     _OPTIONAL_PARAMS = ["query"]
 
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
@@ -71,7 +71,7 @@ class SimilarityEvaluator(PromptyEvaluatorBase):
     _PROMPTY_FILE = "similarity.prompty"
     _RESULT_KEY = "similarity"
 
-    id = "similarity"
+    id = "azureai://built-in/evaluators/similarity"
     """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/_task_adherence/_task_adherence.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_task_adherence/_task_adherence.py
@@ -65,7 +65,7 @@ class TaskAdherenceEvaluator(PromptyEvaluatorBase[Union[str, float]]):
 
     _DEFAULT_TASK_ADHERENCE_SCORE = 3
 
-    id = None
+    id = "azureai://built-in/evaluators/task_adherence"
     """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/_tool_call_accuracy/_tool_call_accuracy.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_tool_call_accuracy/_tool_call_accuracy.py
@@ -84,7 +84,7 @@ class ToolCallAccuracyEvaluator(PromptyEvaluatorBase[Union[str, float]]):
 
     _LLM_SCORE_KEY = "tool_calls_success_level"
 
-    id = "id"
+    id = "azureai://built-in/evaluators/tool_call_accuracy"
     """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/_ungrounded_attributes/_ungrounded_attributes.py b/sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_ungrounded_attributes/_ungrounded_attributes.py
@@ -58,7 +58,7 @@ class UngroundedAttributesEvaluator(RaiServiceEvaluatorBase[Union[str, bool]]):
         for the ungrounded attributes will be "ungrounded_attributes_label".
     """
 
-    id = "ungrounded_attributes"
+    id = "azureai://built-in/evaluators/ungrounded_attributes"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
     _OPTIONAL_PARAMS = ["query"]
 
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
@@ -67,7 +67,7 @@ class IndirectAttackEvaluator(RaiServiceEvaluatorBase[Union[str, bool]]):
 
     """
 
-    id = "azureml://registries/azureml/models/Indirect-Attack-Evaluator/versions/3"
+    id = "azureai://built-in/evaluators/indirect_attack"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
     _OPTIONAL_PARAMS = ["query"]
 
