arthur-common 2.1.51__py3-none-any.whl → 2.1.52__py3-none-any.whl

arthur_common/models/metrics.py

@@ -4,7 +4,7 @@ from enum import Enum
 from typing import Literal, Optional
 from uuid import UUID
 
-from pydantic import BaseModel, Field, model_validator
+from pydantic import BaseModel, Field, field_validator, model_validator
 from typing_extensions import Self
 
 from arthur_common.models.datasets import ModelProblemType
@@ -112,12 +112,9 @@ class AggregationMetricType(Enum):
     NUMERIC = "numeric"
 
 
-class MetricsParameterSchema(BaseModel):
+class BaseAggregationParameterSchema(BaseModel):
+    # fields for aggregation parameters shared across all parameter types and between default and custom metrics
     parameter_key: str = Field(description="Name of the parameter.")
-    optional: bool = Field(
-        False,
-        description="Boolean denoting if the parameter is optional.",
-    )
     friendly_name: str = Field(
         description="User facing name of the parameter.",
     )
@@ -126,7 +123,16 @@ class MetricsParameterSchema(BaseModel):
     )
 
 
-class MetricsDatasetParameterSchema(MetricsParameterSchema):
+class MetricsParameterSchema(BaseAggregationParameterSchema):
+    # specific to default metrics/Python metrics—not available to custom aggregations
+    optional: bool = Field(
+        False,
+        description="Boolean denoting if the parameter is optional.",
+    )
+
+
+class BaseDatasetParameterSchema(BaseAggregationParameterSchema):
+    # fields specific to dataset parameters shared across default and custom metrics
     parameter_type: Literal["dataset"] = "dataset"
     model_problem_type: Optional[ModelProblemType] = Field(
         default=None,
@@ -134,12 +140,24 @@ class MetricsDatasetParameterSchema(MetricsParameterSchema):
     )
 
 
-class MetricsLiteralParameterSchema(MetricsParameterSchema):
+class MetricsDatasetParameterSchema(MetricsParameterSchema, BaseDatasetParameterSchema):
+    # dataset parameter schema including fields specific to default metrics
+    pass
+
+
+class BaseLiteralParameterSchema(BaseAggregationParameterSchema):
+    # fields specific to literal parameters shared across default and custom metrics
     parameter_type: Literal["literal"] = "literal"
     parameter_dtype: DType = Field(description="Data type of the parameter.")
 
 
-class MetricsColumnBaseParameterSchema(MetricsParameterSchema):
+class MetricsLiteralParameterSchema(MetricsParameterSchema, BaseLiteralParameterSchema):
+    # literal parameter schema including fields specific to default metrics
+    pass
+
+
+class BaseColumnBaseParameterSchema(BaseAggregationParameterSchema):
+    # fields specific to all single or multiple column parameters shared across default and custom metrics
     tag_hints: list[ScopeSchemaTag] = Field(
         [],
         description="List of tags that are applicable to this parameter. Datasets with columns that have matching tags can be inferred this way.",
@@ -165,12 +183,18 @@ class MetricsColumnBaseParameterSchema(MetricsParameterSchema):
         return self
 
 
-class MetricsColumnParameterSchema(MetricsColumnBaseParameterSchema):
+class BaseColumnParameterSchema(BaseColumnBaseParameterSchema):
+    # single column parameter schema common across default and custom metrics
     parameter_type: Literal["column"] = "column"
 
 
-# Not used /implemented yet. Might turn into group by column list
-class MetricsColumnListParameterSchema(MetricsColumnBaseParameterSchema):
+class MetricsColumnParameterSchema(MetricsParameterSchema, BaseColumnParameterSchema):
+    # single column parameter schema specific to default metrics
+    parameter_type: Literal["column"] = "column"
+
+
+class MetricsColumnListParameterSchema(MetricsParameterSchema, BaseColumnParameterSchema):
+    # list column parameter schema specific to default metrics
     parameter_type: Literal["column_list"] = "column_list"
 
 
@@ -186,6 +210,13 @@ MetricsColumnSchemaUnion = (
 )
 
 
+CustomAggregationParametersSchemaUnion = (
+    BaseDatasetParameterSchema
+    | BaseLiteralParameterSchema
+    | BaseColumnParameterSchema
+)
+
+
 @dataclass
 class DatasetReference:
     dataset_name: str
@@ -229,3 +260,28 @@ class AggregationSpecSchema(BaseModel):
                     f"Column parameter '{param.parameter_key}' references dataset parameter '{param.source_dataset_parameter_key}' which does not exist.",
                 )
         return self
+
+
+class BaseReportedAggregation(BaseModel):
+    # in future will be used by default metrics
+    metric_name: str = Field(description="Name of the reported aggregation metric.")
+    description: str = Field(
+        description="Description of the reported aggregation metric and what it aggregates.",
+    )
+
+
+class ReportedCustomAggregation(BaseReportedAggregation):
+    value_column: str = Field(description="Name of the column returned from the SQL query holding the metric value.")
+    timestamp_column: str = Field(description="Name of the column returned from the SQL query holding the timestamp buckets.")
+    metric_kind: AggregationMetricType = Field(
+        description="Return type of the reported aggregation metric value.",
+    )
+    dimension_columns: list[str] = Field(description="Name of any dimension columns returned from the SQL query. Max length is 1.")
+
+    @field_validator('dimension_columns')
+    @classmethod
+    def validate_dimension_columns_length(cls, v: list[str]) -> str:
+        if len(v) > 1:
+            raise ValueError('Only one dimension column can be specified.')
+        return v
+

arthur_common/models/shield.py

@@ -10,9 +10,7 @@ DEFAULT_PII_RULE_CONFIDENCE_SCORE_THRESHOLD = 0
 
 class RuleType(str, Enum):
     KEYWORD = "KeywordRule"
-    MODEL_HALLUCINATION = "ModelHallucinationRule"
     MODEL_HALLUCINATION_V2 = "ModelHallucinationRuleV2"
-    MODEL_HALLUCINATION_V3 = "ModelHallucinationRuleV3"
     MODEL_SENSITIVE_DATA = "ModelSensitiveDataRule"
     PII_DATA = "PIIDataRule"
     PROMPT_INJECTION = "PromptInjectionRule"
@@ -456,14 +454,6 @@ class NewRuleRequest(BaseModel):
                 detail="PromptInjectionRule can only be enabled for prompt. Please set the 'apply_to_response' field "
                 "to false.",
             )
-        if (self.type == RuleType.MODEL_HALLUCINATION) and (
-            self.apply_to_prompt is True
-        ):
-            raise HTTPException(
-                status_code=400,
-                detail="ModelHallucinationRule can only be enabled for response. Please set the 'apply_to_prompt' "
-                "field to false.",
-            )
         if (self.type == RuleType.MODEL_HALLUCINATION_V2) and (
             self.apply_to_prompt is True
         ):
@@ -472,14 +462,6 @@ class NewRuleRequest(BaseModel):
                 detail="ModelHallucinationRuleV2 can only be enabled for response. Please set the 'apply_to_prompt' "
                 "field to false.",
             )
-        if (self.type == RuleType.MODEL_HALLUCINATION_V3) and (
-            self.apply_to_prompt is True
-        ):
-            raise HTTPException(
-                status_code=400,
-                detail="ModelHallucinationRuleV3 can only be enabled for response. Please set the "
-                "'apply_to_prompt' field to false.",
-            )
         if (self.apply_to_prompt is False) and (self.apply_to_response is False):
             raise HTTPException(
                 status_code=400,

{arthur_common-2.1.51.dist-info → arthur_common-2.1.52.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: arthur-common
-Version: 2.1.51
+Version: 2.1.52
 Summary: Utility code common to Arthur platform components.
 License: MIT
 Author: Arthur

{arthur_common-2.1.51.dist-info → arthur_common-2.1.52.dist-info}/RECORD

@@ -23,10 +23,10 @@ arthur_common/config/settings.yaml,sha256=0CrygUwJzC5mGcO5Xnvv2ttp-P7LIsx682jllY
 arthur_common/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 arthur_common/models/connectors.py,sha256=5f5DUgOQ16P3lBPZ0zpUv9kTAqw45Agrl526F-iFJes,1862
 arthur_common/models/datasets.py,sha256=giG_8mv_3ilBf7cIvRV0_TDCDdb4qxRbYZvl7hRb6l8,491
-arthur_common/models/metrics.py,sha256=A5mtXPqqHcFNAJ02HKnlvWr-so_Mro7AYKKuGUnD9qg,8398
+arthur_common/models/metrics.py,sha256=ibJK2WkTw_yCTanx_4oU3CZFEmMWf9BcZYWeuvXsd7E,10885
 arthur_common/models/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 arthur_common/models/schema_definitions.py,sha256=0zXZKHKr49d7ATml2Tzw1AIFfM0i0HjIblM-qOwNxk8,14878
-arthur_common/models/shield.py,sha256=1ZblfULKCf5BEvYURO5WScyfmijGwjAmcj0XADlF-XY,19110
+arthur_common/models/shield.py,sha256=62SKLzlsUsuP3u7EnibtI1CrRYg3TummP4Wbwg5ZPUs,18310
 arthur_common/models/task_job_specs.py,sha256=uZo8eiTBHWf2EZGEQrDfJGVyYg_8wd9MHWLxn-5oNUk,2797
 arthur_common/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 arthur_common/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -38,6 +38,6 @@ arthur_common/tools/functions.py,sha256=FWL4eWO5-vLp86WudT-MGUKvf2B8f02IdoXQFKd6
 arthur_common/tools/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 arthur_common/tools/schema_inferer.py,sha256=Ur4CXGAkd6ZMSU0nMNrkOEElsBopHXq0lctTV8X92W8,5188
 arthur_common/tools/time_utils.py,sha256=4gfiu9NXfvPZltiVNLSIQGylX6h2W0viNi9Kv4bKyfw,1410
-arthur_common-2.1.51.dist-info/METADATA,sha256=Gfan_b1J1PObA_sIeqZXKL_jz9QpA5bx-fHscjczwqw,1609
-arthur_common-2.1.51.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-arthur_common-2.1.51.dist-info/RECORD,,
+arthur_common-2.1.52.dist-info/METADATA,sha256=LfIOLc5zbA8nx7aTwN65q7L3JmGZOdhQGSYmnSn_Mh8,1609
+arthur_common-2.1.52.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+arthur_common-2.1.52.dist-info/RECORD,,