openmetadata-ingestion 1.6.7.1__py3-none-any.whl → 1.7.0.0rc1__py3-none-any.whl

metadata/generated/schema/configuration/searchSettings.py

@@ -1,10 +1,11 @@
 # generated by datamodel-codegen:
 #   filename:  configuration/searchSettings.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 
-from typing import Optional
+from enum import Enum
+from typing import Any, Dict, List, Optional
 
 from pydantic import ConfigDict, Field
 from typing_extensions import Annotated
@@ -12,7 +13,244 @@ from typing_extensions import Annotated
 from metadata.ingestion.models.custom_pydantic import BaseModel
 
 
-class SearchSettings(BaseModel):
+class ScoreMode(Enum):
+    multiply = 'multiply'
+    sum = 'sum'
+    avg = 'avg'
+    first = 'first'
+    max = 'max'
+    min = 'min'
+
+
+class BoostMode(Enum):
+    multiply = 'multiply'
+    replace = 'replace'
+    sum = 'sum'
+    avg = 'avg'
+    max = 'max'
+    min = 'min'
+
+
+class FieldBoost(BaseModel):
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+    field: Annotated[str, Field(description='Field name to search/boost.')]
+    boost: Annotated[
+        Optional[float],
+        Field(1.0, description='Relative boost factor for the above field.'),
+    ]
+
+
+class TermBoost(BaseModel):
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+    field: Annotated[
+        str,
+        Field(
+            description='The keyword field to match, e.g. tier.tagFQN, tags.tagFQN, certification.tagLabel.tagFQN, etc.'
+        ),
+    ]
+    value: Annotated[
+        str, Field(description='The exact keyword value to match in the above field.')
+    ]
+    boost: Annotated[
+        float,
+        Field(
+            description='Numeric boost factor to apply if a document has field==value.'
+        ),
+    ]
+
+
+class Modifier(Enum):
+    none = 'none'
+    log = 'log'
+    log1p = 'log1p'
+    log2p = 'log2p'
+    ln = 'ln'
+    ln1p = 'ln1p'
+    ln2p = 'ln2p'
+    square = 'square'
+    sqrt = 'sqrt'
+    reciprocal = 'reciprocal'
+
+
+class Range(BaseModel):
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+    gt: Optional[float] = None
+    gte: Optional[float] = None
+    lt: Optional[float] = None
+    lte: Optional[float] = None
+
+
+class Condition(BaseModel):
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+    range: Optional[Range] = None
+
+
+class FieldValueBoost(BaseModel):
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+    field: Annotated[
+        str, Field(description='Numeric field name whose value will affect the score.')
+    ]
+    factor: Annotated[
+        float, Field(description='Multiplier factor for the field value.')
+    ]
+    modifier: Annotated[
+        Optional[Modifier],
+        Field(
+            None,
+            description='Optional mathematical transformation to apply to the field value.',
+        ),
+    ]
+    missing: Annotated[
+        Optional[float],
+        Field(None, description='Value to use if the field is missing on a document.'),
+    ]
+    condition: Annotated[
+        Optional[Condition],
+        Field(
+            None,
+            description='Conditional logic (e.g., range constraints) to apply the boost only for certain values.',
+        ),
+    ]
+
+
+class Type(Enum):
+    terms = 'terms'
+    range = 'range'
+    histogram = 'histogram'
+    date_histogram = 'date_histogram'
+    filters = 'filters'
+    missing = 'missing'
+    nested = 'nested'
+    reverse_nested = 'reverse_nested'
+    top_hits = 'top_hits'
+    max = 'max'
+    min = 'min'
+    avg = 'avg'
+    sum = 'sum'
+    stats = 'stats'
+
+
+class Aggregation(BaseModel):
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+    name: Annotated[str, Field(description='A descriptive name for the aggregation.')]
+    type: Annotated[Type, Field(description='The type of aggregation to perform.')]
+    field: Annotated[
+        str, Field(description='The field on which this aggregation is performed.')
+    ]
+
+
+class Field1(BaseModel):
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+    name: Annotated[
+        str, Field(description='Field name that can be used in searchFields')
+    ]
+    description: Annotated[
+        str,
+        Field(
+            description='Detailed explanation of what this field represents and how it affects search behavior'
+        ),
+    ]
+
+
+class AllowedSearchFields(BaseModel):
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+    entityType: Annotated[
+        str, Field(description='Entity type this field configuration applies to')
+    ]
+    fields: List[Field1]
+
+
+class PromptSection(BaseModel):
+    section: Annotated[
+        str,
+        Field(
+            description="Section name (e.g., 'CRITICAL FIELD CORRECTIONS', 'QUERY PATTERNS')"
+        ),
+    ]
+    content: Annotated[
+        str, Field(description='The content for this section of the prompt')
+    ]
+    order: Annotated[
+        Optional[int],
+        Field(
+            100,
+            description='Display order for this section (lower numbers appear first)',
+        ),
+    ]
+
+
+class TitleSection(BaseModel):
+    title: Annotated[
+        Optional[str], Field('INDEX MAPPINGS', description='Title for the section')
+    ]
+    description: Annotated[
+        Optional[str],
+        Field(
+            'Below are the Elasticsearch mappings for the relevant indices. Use these to understand the document structure:',
+            description='Description text for the section',
+        ),
+    ]
+    order: Annotated[
+        Optional[int],
+        Field(
+            5,
+            description='Position of this section in the prompt (lower numbers appear first)',
+        ),
+    ]
+
+
+class FieldInterpretation(BaseModel):
+    pattern: Annotated[
+        str, Field(description="Field pattern to match (e.g., 'tags.tagFQN')")
+    ]
+    explanation: Annotated[
+        str, Field(description='How to interpret and query this field pattern')
+    ]
+
+
+class GuidelineSection(BaseModel):
+    title: Annotated[
+        str,
+        Field(
+            description="Section title (e.g., 'For EntityReference type custom properties')"
+        ),
+    ]
+    guidelines: List[str]
+
+
+class QueryExample(BaseModel):
+    description: Annotated[
+        Optional[str],
+        Field(None, description='Human-readable description of the example query'),
+    ]
+    query: Annotated[str, Field(description='Natural language query example')]
+    esQuery: Annotated[str, Field(description='The corresponding Elasticsearch query')]
+    entityTypes: Annotated[
+        Optional[List[str]],
+        Field(
+            None,
+            description='Entity types this example applies to (empty array = all types)',
+        ),
+    ]
+
+
+class GlobalSettings(BaseModel):
     model_config = ConfigDict(
         extra='forbid',
     )
@@ -20,6 +258,192 @@ class SearchSettings(BaseModel):
         Optional[bool],
         Field(
             False,
-            description='Flag to enable or disable the RBAC Search Configuration.',
+            description='Flag to enable or disable RBAC Search Configuration globally.',
+        ),
+    ]
+    maxAggregateSize: Optional[int] = 10000
+    maxResultHits: Optional[int] = 10000
+    maxAnalyzedOffset: Optional[int] = 1000
+    aggregations: Annotated[
+        Optional[List[Aggregation]],
+        Field(
+            None,
+            description='List of global aggregations to include in the search query.',
+        ),
+    ]
+    highlightFields: Annotated[
+        Optional[List[str]],
+        Field(None, description='Which fields to highlight by default.'),
+    ]
+    termBoosts: Annotated[
+        Optional[List[TermBoost]],
+        Field(
+            None,
+            description='List of field=value term-boost rules that apply only to this asset.',
+        ),
+    ]
+    fieldValueBoosts: Annotated[
+        Optional[List[FieldValueBoost]],
+        Field(
+            None,
+            description='Optional list of numeric field-based boosts applied globally.',
+        ),
+    ]
+
+
+class EntitySpecificInstruction(BaseModel):
+    entityType: Annotated[
+        str,
+        Field(
+            description="Entity type this instruction applies to (e.g., 'table', 'dashboard')"
+        ),
+    ]
+    sections: List[PromptSection]
+
+
+class MappingConfiguration(BaseModel):
+    includeMappings: Annotated[
+        Optional[bool],
+        Field(
+            True, description='Whether to include mapping information in the prompts'
+        ),
+    ]
+    mappingSection: Optional[TitleSection] = None
+    fieldInterpretations: Annotated[
+        Optional[List[FieldInterpretation]],
+        Field(
+            None,
+            description='Specific guidance for interpreting field patterns in the mapping',
+        ),
+    ]
+
+
+class ExtensionFieldGuidelines(BaseModel):
+    header: Annotated[
+        str, Field(description='Title for the extension field guidelines section')
+    ]
+    sections: List[GuidelineSection]
+    examples: Optional[List[QueryExample]] = None
+
+
+class NlqConfiguration(BaseModel):
+    promptTemplate: Annotated[
+        Optional[str],
+        Field(
+            None,
+            description='Base prompt template for the NLQ system. Use {{INSTRUCTIONS}} where entity-specific instructions should appear.',
+        ),
+    ]
+    globalInstructions: Optional[List[PromptSection]] = None
+    entitySpecificInstructions: Optional[List[EntitySpecificInstruction]] = None
+    examples: Optional[List[QueryExample]] = None
+    mappingConfiguration: Annotated[
+        Optional[MappingConfiguration],
+        Field(
+            None,
+            description='Configuration for including Elasticsearch mapping information in prompts',
+        ),
+    ]
+    extensionFieldGuidelines: Annotated[
+        Optional[ExtensionFieldGuidelines],
+        Field(
+            None,
+            description='Guidelines for querying custom properties in extension fields',
+        ),
+    ]
+
+
+class AssetTypeConfiguration(BaseModel):
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+    assetType: Annotated[
+        str,
+        Field(
+            description='Name or type of the asset to which this configuration applies.'
+        ),
+    ]
+    searchFields: Annotated[
+        Optional[List[FieldBoost]],
+        Field(
+            None,
+            description='Which fields to search for this asset, with their boost values.',
+        ),
+    ]
+    highlightFields: Annotated[
+        Optional[List[str]],
+        Field(None, description='Which fields to highlight for this asset.'),
+    ]
+    aggregations: Annotated[
+        Optional[List[Aggregation]],
+        Field(None, description='List of additional aggregations for this asset type.'),
+    ]
+    termBoosts: Annotated[
+        Optional[List[TermBoost]],
+        Field(
+            None,
+            description='List of field=value term-boost rules that apply only to this asset.',
+        ),
+    ]
+    fieldValueBoosts: Annotated[
+        Optional[List[FieldValueBoost]],
+        Field(
+            None,
+            description='List of numeric field-based boosts that apply only to this asset.',
+        ),
+    ]
+    scoreMode: Annotated[
+        Optional[ScoreMode],
+        Field(
+            None,
+            description='How to combine function scores if multiple boosts are applied.',
+        ),
+    ]
+    boostMode: Annotated[
+        Optional[BoostMode],
+        Field(
+            None,
+            description='How the function score is combined with the main query score.',
+        ),
+    ]
+    additionalSettings: Annotated[
+        Optional[Dict[str, Any]],
+        Field(
+            None,
+            description='Catch-all for any advanced or asset-specific search settings.',
+        ),
+    ]
+
+
+class SearchSettings(BaseModel):
+    model_config = ConfigDict(
+        extra='forbid',
+    )
+    globalSettings: Optional[GlobalSettings] = None
+    assetTypeConfigurations: Annotated[
+        Optional[List[AssetTypeConfiguration]],
+        Field(
+            None,
+            description='List of per-asset search configurations that override the global settings.',
+        ),
+    ]
+    defaultConfiguration: Annotated[
+        Optional[AssetTypeConfiguration],
+        Field(
+            None,
+            description='Fallback configuration for any entity/asset not matched in assetTypeConfigurations.',
+        ),
+    ]
+    allowedFields: Annotated[
+        Optional[List[AllowedSearchFields]],
+        Field(
+            None,
+            description='Configurations of allowed searchable fields for each entity type',
+        ),
+    ]
+    nlqConfiguration: Annotated[
+        Optional[NlqConfiguration],
+        Field(
+            None, description='Configuration for Natural Language Query capabilities'
         ),
     ]

metadata/generated/schema/configuration/slackAppConfiguration.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  configuration/slackAppConfiguration.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/configuration/taskNotificationConfiguration.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  configuration/taskNotificationConfiguration.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/configuration/testResultNotificationConfiguration.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  configuration/testResultNotificationConfiguration.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/configuration/themeConfiguration.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  configuration/themeConfiguration.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/configuration/uiThemePreference.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  configuration/uiThemePreference.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/configuration/workflowSettings.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  configuration/workflowSettings.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 
@@ -44,6 +44,13 @@ class ExecutorConfiguration(BaseModel):
             description='The amount of Tasks that the Workflow Executor is able to pick up each time it looks for more.',
         ),
     ]
+    jobLockTimeInMillis: Annotated[
+        Optional[int],
+        Field(
+            1296000000,
+            description='The amount of time a Job gets locked before being retried. Default: 15 Days. This avoids jobs that takes too long to run being retried while running.',
+        ),
+    ]
 
 
 class HistoryCleanUpConfiguration(BaseModel):

metadata/generated/schema/dataInsight/__init__.py

@@ -1,3 +1,3 @@
 # generated by datamodel-codegen:
 #   filename:  schema
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00

metadata/generated/schema/dataInsight/custom/__init__.py

@@ -1,3 +1,3 @@
 # generated by datamodel-codegen:
 #   filename:  schema
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00

metadata/generated/schema/dataInsight/custom/dataInsightCustomChart.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  dataInsight/custom/dataInsightCustomChart.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/dataInsight/custom/dataInsightCustomChartResult.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  dataInsight/custom/dataInsightCustomChartResult.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/dataInsight/custom/dataInsightCustomChartResultList.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  dataInsight/custom/dataInsightCustomChartResultList.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/dataInsight/custom/formulaHolder.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  dataInsight/custom/formulaHolder.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/dataInsight/custom/lineChart.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  dataInsight/custom/lineChart.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 
@@ -89,3 +89,17 @@ class LineChart(BaseModel):
         Optional[str],
         Field('@timestamp', description='X-axis field for the data insight chart.'),
     ]
+    includeXAxisFiled: Annotated[
+        Optional[str],
+        Field(
+            None,
+            description='Regex to include fields in the data insight chart when xAxisField is specified.',
+        ),
+    ]
+    excludeXAxisField: Annotated[
+        Optional[str],
+        Field(
+            None,
+            description='Regex to exclude fields from the data insight chart when xAxisField is specified.',
+        ),
+    ]

metadata/generated/schema/dataInsight/custom/summaryCard.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  dataInsight/custom/summaryCard.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/dataInsight/dataInsightChart.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  dataInsight/dataInsightChart.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/dataInsight/dataInsightChartResult.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  dataInsight/dataInsightChartResult.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/dataInsight/kpi/__init__.py

@@ -1,3 +1,3 @@
 # generated by datamodel-codegen:
 #   filename:  schema
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00

metadata/generated/schema/dataInsight/kpi/basic.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  dataInsight/kpi/basic.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/dataInsight/kpi/kpi.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  dataInsight/kpi/kpi.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/dataInsight/type/__init__.py

@@ -1,3 +1,3 @@
 # generated by datamodel-codegen:
 #   filename:  schema
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00

metadata/generated/schema/dataInsight/type/aggregatedUnusedAssetsCount.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  dataInsight/type/aggregatedUnusedAssetsCount.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/dataInsight/type/aggregatedUnusedAssetsSize.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  dataInsight/type/aggregatedUnusedAssetsSize.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/dataInsight/type/aggregatedUsedVsUnusedAssetsCount.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  dataInsight/type/aggregatedUsedVsUnusedAssetsCount.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/dataInsight/type/aggregatedUsedVsUnusedAssetsSize.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  dataInsight/type/aggregatedUsedVsUnusedAssetsSize.json
-#   timestamp: 2025-04-02T12:35:09+00:00
+#   timestamp: 2025-04-02T05:35:35+00:00
 
 from __future__ import annotations