azure-ai-evaluation 1.2.0__tar.gz → 1.3.0__tar.gz

{azure_ai_evaluation-1.2.0 → azure_ai_evaluation-1.3.0}/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Release History
 
+## 1.3.0 (2025-02-28)
+
+### Breaking Changes
+- Multimodal specific evaluators `ContentSafetyMultimodalEvaluator`, `ViolenceMultimodalEvaluator`, `SexualMultimodalEvaluator`, `SelfHarmMultimodalEvaluator`, `HateUnfairnessMultimodalEvaluator` and `ProtectedMaterialMultimodalEvaluator` has been removed. Please use `ContentSafetyEvaluator`, `ViolenceEvaluator`, `SexualEvaluator`, `SelfHarmEvaluator`, `HateUnfairnessEvaluator` and `ProtectedMaterialEvaluator` instead.
+- Metric name in ProtectedMaterialEvaluator's output is changed from `protected_material.fictional_characters_label` to `protected_material.fictional_characters_defect_rate`. It's now consistent with other evaluator's metric names (ending with `_defect_rate`).
+
 ## 1.2.0 (2025-01-27)
 
 ### Features Added

{azure_ai_evaluation-1.2.0/azure_ai_evaluation.egg-info → azure_ai_evaluation-1.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: azure-ai-evaluation
-Version: 1.2.0
+Version: 1.3.0
 Summary: Microsoft Azure Evaluation Library for Python
 Home-page: https://github.com/Azure/azure-sdk-for-python
 Author: Microsoft Corporation
@@ -377,6 +377,12 @@ This project has adopted the [Microsoft Open Source Code of Conduct][code_of_con
 
 # Release History
 
+## 1.3.0 (2025-02-28)
+
+### Breaking Changes
+- Multimodal specific evaluators `ContentSafetyMultimodalEvaluator`, `ViolenceMultimodalEvaluator`, `SexualMultimodalEvaluator`, `SelfHarmMultimodalEvaluator`, `HateUnfairnessMultimodalEvaluator` and `ProtectedMaterialMultimodalEvaluator` has been removed. Please use `ContentSafetyEvaluator`, `ViolenceEvaluator`, `SexualEvaluator`, `SelfHarmEvaluator`, `HateUnfairnessEvaluator` and `ProtectedMaterialEvaluator` instead.
+- Metric name in ProtectedMaterialEvaluator's output is changed from `protected_material.fictional_characters_label` to `protected_material.fictional_characters_defect_rate`. It's now consistent with other evaluator's metric names (ending with `_defect_rate`).
+
 ## 1.2.0 (2025-01-27)
 
 ### Features Added

{azure_ai_evaluation-1.2.0 → azure_ai_evaluation-1.3.0}/azure/ai/evaluation/__init__.py

@@ -12,14 +12,6 @@ from ._evaluators._content_safety import (
     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
@@ -72,11 +64,5 @@ __all__ = [
     "EvaluatorConfig",
     "Conversation",
     "Message",
-    "EvaluationResult",
-    "ContentSafetyMultimodalEvaluator",
-    "HateUnfairnessMultimodalEvaluator",
-    "SelfHarmMultimodalEvaluator",
-    "SexualMultimodalEvaluator",
-    "ViolenceMultimodalEvaluator",
-    "ProtectedMaterialMultimodalEvaluator",
+    "EvaluationResult"
 ]

{azure_ai_evaluation-1.2.0 → azure_ai_evaluation-1.3.0}/azure/ai/evaluation/_common/utils.py

@@ -366,7 +366,7 @@ def validate_conversation(conversation):
     if not isinstance(messages, list):
         raise_exception(
             "'messages' parameter must be a JSON-compatible list of chat messages",
-            ErrorTarget.CONTENT_SAFETY_MULTIMODAL_EVALUATOR,
+            ErrorTarget.CONTENT_SAFETY_CHAT_EVALUATOR,
         )
     expected_roles = {"user", "assistant", "system"}
     image_found = False
@@ -393,7 +393,7 @@ def validate_conversation(conversation):
             ):
                 raise_exception(
                     f"Messages must be a strongly typed class of ChatRequestMessage. Message number: {num}",
-                    ErrorTarget.CONTENT_SAFETY_MULTIMODAL_EVALUATOR,
+                    ErrorTarget.CONTENT_SAFETY_CHAT_EVALUATOR,
                 )
             if isinstance(message, AssistantMessage):
                 assistant_message_count += 1
@@ -407,7 +407,7 @@ def validate_conversation(conversation):
         if message.get("role") not in expected_roles:
             raise_exception(
                 f"Invalid role provided: {message.get('role')}. Message number: {num}",
-                ErrorTarget.CONTENT_SAFETY_MULTIMODAL_EVALUATOR,
+                ErrorTarget.CONTENT_SAFETY_CHAT_EVALUATOR,
             )
         if message.get("role") == "assistant":
             assistant_message_count += 1
@@ -417,7 +417,7 @@ def validate_conversation(conversation):
         if not isinstance(content, (str, list)):
             raise_exception(
                 f"Content in each turn must be a string or array. Message number: {num}",
-                ErrorTarget.CONTENT_SAFETY_MULTIMODAL_EVALUATOR,
+                ErrorTarget.CONTENT_SAFETY_CHAT_EVALUATOR,
             )
         if isinstance(content, list):
             if any(item.get("type") == "image_url" and "url" in item.get("image_url", {}) for item in content):
@@ -425,21 +425,21 @@ def validate_conversation(conversation):
     if not image_found:
         raise_exception(
             "Message needs to have multi-modal input like images.",
-            ErrorTarget.CONTENT_SAFETY_MULTIMODAL_EVALUATOR,
+            ErrorTarget.CONTENT_SAFETY_CHAT_EVALUATOR,
         )
     if assistant_message_count == 0:
         raise_exception(
             "Assistant role required in one of the messages.",
-            ErrorTarget.CONTENT_SAFETY_MULTIMODAL_EVALUATOR,
+            ErrorTarget.CONTENT_SAFETY_CHAT_EVALUATOR,
         )
     if user_message_count == 0:
         raise_exception(
             "User role required in one of the messages.",
-            ErrorTarget.CONTENT_SAFETY_MULTIMODAL_EVALUATOR,
+            ErrorTarget.CONTENT_SAFETY_CHAT_EVALUATOR,
         )
     if assistant_message_count > 1:
         raise_exception(
             "Evaluators for multimodal conversations only support single turn. "
             "User and assistant role expected as the only role in each message.",
-            ErrorTarget.CONTENT_SAFETY_MULTIMODAL_EVALUATOR,
+            ErrorTarget.CONTENT_SAFETY_CHAT_EVALUATOR,
         )

{azure_ai_evaluation-1.2.0 → azure_ai_evaluation-1.3.0}/azure/ai/evaluation/_constants.py

@@ -22,6 +22,9 @@ class EvaluationMetrics:
     SELF_HARM = "self_harm"
     SEXUAL = "sexual"
     PROTECTED_MATERIAL = "protected_material"
+    ARTWORK = "artwork"
+    FICTIONAL_CHARACTERS = "fictional_characters"
+    LOGOS_AND_BRANDS = "logos_and_brands"
     XPIA = "xpia"
 
 

{azure_ai_evaluation-1.2.0 → azure_ai_evaluation-1.3.0}/azure/ai/evaluation/_evaluate/_evaluate.py

@@ -147,6 +147,9 @@ def _aggregate_label_defect_metrics(df: pd.DataFrame) -> Tuple[List[str], Dict[s
     """
     handled_metrics = [
         EvaluationMetrics.PROTECTED_MATERIAL,
+        EvaluationMetrics.FICTIONAL_CHARACTERS,
+        EvaluationMetrics.ARTWORK,
+        EvaluationMetrics.LOGOS_AND_BRANDS,
         _InternalEvaluationMetrics.ECI,
         EvaluationMetrics.XPIA,
     ]
@@ -525,7 +528,7 @@ def _process_column_mappings(
 
     processed_config: Dict[str, Dict[str, str]] = {}
 
-    unexpected_references = re.compile(r"\${(?!target\.|data\.).+?}")
+    expected_references = re.compile(r"^\$\{(target|data)\.[a-zA-Z_]+\}$")
 
     if column_mapping:
         for evaluator, mapping_config in column_mapping.items():
@@ -534,7 +537,7 @@ def _process_column_mappings(
 
                 for map_to_key, map_value in mapping_config.items():
                     # Check if there's any unexpected reference other than ${target.} or ${data.}
-                    if unexpected_references.search(map_value):
+                    if not expected_references.search(map_value):
                         msg = "Unexpected references detected in 'column_mapping'. Ensure only ${target.} and ${data.} are used."
                         raise EvaluationException(
                             message=msg,

{azure_ai_evaluation-1.2.0 → azure_ai_evaluation-1.3.0}/azure/ai/evaluation/_exceptions.py

@@ -63,7 +63,6 @@ class ErrorTarget(Enum):
     RAI_CLIENT = "RAIClient"
     COHERENCE_EVALUATOR = "CoherenceEvaluator"
     CONTENT_SAFETY_CHAT_EVALUATOR = "ContentSafetyEvaluator"
-    CONTENT_SAFETY_MULTIMODAL_EVALUATOR = "ContentSafetyMultimodalEvaluator"
     ECI_EVALUATOR = "ECIEvaluator"
     F1_EVALUATOR = "F1Evaluator"
     GROUNDEDNESS_EVALUATOR = "GroundednessEvaluator"