azure-ai-evaluation 1.0.0__py3-none-any.whl → 1.0.0b1__py3-none-any.whl

azure/ai/evaluation/__init__.py

@@ -4,42 +4,30 @@
 
 from ._evaluate._evaluate import evaluate
 from ._evaluators._bleu import BleuScoreEvaluator
+from ._evaluators._chat import ChatEvaluator
 from ._evaluators._coherence import CoherenceEvaluator
 from ._evaluators._content_safety import (
+    ContentSafetyChatEvaluator,
     ContentSafetyEvaluator,
     HateUnfairnessEvaluator,
     SelfHarmEvaluator,
     SexualEvaluator,
     ViolenceEvaluator,
 )
-from ._evaluators._multimodal._content_safety_multimodal import (
-    ContentSafetyMultimodalEvaluator,
-    HateUnfairnessMultimodalEvaluator,
-    SelfHarmMultimodalEvaluator,
-    SexualMultimodalEvaluator,
-    ViolenceMultimodalEvaluator,
-)
-from ._evaluators._multimodal._protected_material import ProtectedMaterialMultimodalEvaluator
 from ._evaluators._f1_score import F1ScoreEvaluator
 from ._evaluators._fluency import FluencyEvaluator
 from ._evaluators._gleu import GleuScoreEvaluator
 from ._evaluators._groundedness import GroundednessEvaluator
-from ._evaluators._service_groundedness import GroundednessProEvaluator
 from ._evaluators._meteor import MeteorScoreEvaluator
 from ._evaluators._protected_material import ProtectedMaterialEvaluator
 from ._evaluators._qa import QAEvaluator
 from ._evaluators._relevance import RelevanceEvaluator
-from ._evaluators._retrieval import RetrievalEvaluator
 from ._evaluators._rouge import RougeScoreEvaluator, RougeType
 from ._evaluators._similarity import SimilarityEvaluator
 from ._evaluators._xpia import IndirectAttackEvaluator
 from ._model_configurations import (
     AzureAIProject,
     AzureOpenAIModelConfiguration,
-    Conversation,
-    EvaluationResult,
-    EvaluatorConfig,
-    Message,
     OpenAIModelConfiguration,
 )
 
@@ -49,34 +37,24 @@ __all__ = [
     "F1ScoreEvaluator",
     "FluencyEvaluator",
     "GroundednessEvaluator",
-    "GroundednessProEvaluator",
     "RelevanceEvaluator",
     "SimilarityEvaluator",
     "QAEvaluator",
+    "ChatEvaluator",
     "ViolenceEvaluator",
     "SexualEvaluator",
     "SelfHarmEvaluator",
     "HateUnfairnessEvaluator",
     "ContentSafetyEvaluator",
+    "ContentSafetyChatEvaluator",
     "IndirectAttackEvaluator",
     "BleuScoreEvaluator",
     "GleuScoreEvaluator",
     "MeteorScoreEvaluator",
-    "RetrievalEvaluator",
     "RougeScoreEvaluator",
     "RougeType",
     "ProtectedMaterialEvaluator",
     "AzureAIProject",
     "AzureOpenAIModelConfiguration",
     "OpenAIModelConfiguration",
-    "EvaluatorConfig",
-    "Conversation",
-    "Message",
-    "EvaluationResult",
-    "ContentSafetyMultimodalEvaluator",
-    "HateUnfairnessMultimodalEvaluator",
-    "SelfHarmMultimodalEvaluator",
-    "SexualMultimodalEvaluator",
-    "ViolenceMultimodalEvaluator",
-    "ProtectedMaterialMultimodalEvaluator",
 ]

azure/ai/evaluation/_common/constants.py

@@ -3,11 +3,6 @@
 # ---------------------------------------------------------
 from enum import Enum
 
-from azure.core import CaseInsensitiveEnumMeta
-
-
-PROMPT_BASED_REASON_EVALUATORS = ["coherence", "relevance", "retrieval", "groundedness", "fluency"]
-
 
 class CommonConstants:
     """Define common constants."""
@@ -38,7 +33,6 @@ class Tasks:
     CONTENT_HARM = "content harm"
     PROTECTED_MATERIAL = "protected material"
     XPIA = "xpia"
-    GROUNDEDNESS = "groundedness"
 
 
 class _InternalAnnotationTasks:
@@ -49,7 +43,7 @@ class _InternalAnnotationTasks:
     ECI = "eci"
 
 
-class EvaluationMetrics(str, Enum, metaclass=CaseInsensitiveEnumMeta):
+class EvaluationMetrics:
     """Evaluation metrics to aid the RAI service in determining what
     metrics to request, and how to present them back to the user."""
 
@@ -60,10 +54,9 @@ class EvaluationMetrics(str, Enum, metaclass=CaseInsensitiveEnumMeta):
     SEXUAL = "sexual"
     PROTECTED_MATERIAL = "protected_material"
     XPIA = "xpia"
-    GROUNDEDNESS = "generic_groundedness"
 
 
-class _InternalEvaluationMetrics(str, Enum, metaclass=CaseInsensitiveEnumMeta):
+class _InternalEvaluationMetrics:
     """Evaluation metrics that are not publicly supported.
     These metrics are experimental and subject to potential change or migration to the main
     enum over time.