openmetadata-ingestion 1.5.4.1__py3-none-any.whl → 1.5.5.0__py3-none-any.whl

metadata/generated/schema/type/entityReferenceList.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/entityReferenceList.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/entityRelationship.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/entityRelationship.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/entityUsage.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/entityUsage.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/filterPattern.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/filterPattern.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/function.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/function.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/include.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/include.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/jdbcConnection.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/jdbcConnection.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/lifeCycle.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/lifeCycle.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/paging.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/paging.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/profile.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/profile.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/queryParserData.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/queryParserData.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/reaction.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/reaction.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/schedule.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/schedule.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/schema.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/schema.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/tableQuery.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/tableQuery.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/tableUsageCount.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/tableUsageCount.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/tagLabel.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/tagLabel.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/usageDetails.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/usageDetails.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/usageRequest.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/usageRequest.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/votes.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/votes.json
-#   timestamp: 2024-09-19T13:48:25+00:00
+#   timestamp: 2024-09-25T04:53:10+00:00
 
 from __future__ import annotations
 

metadata/ingestion/ometa/mixins/lineage_mixin.py

@@ -22,13 +22,14 @@ from pydantic import BaseModel
 
 from metadata.generated.schema.api.lineage.addLineage import AddLineageRequest
 from metadata.generated.schema.entity.services.databaseService import DatabaseService
+from metadata.generated.schema.type.basic import FullyQualifiedEntityName, Uuid
 from metadata.generated.schema.type.entityLineage import EntitiesEdge
 from metadata.generated.schema.type.entityReference import EntityReference
 from metadata.ingestion.lineage.models import ConnectionTypeDialectMapper
 from metadata.ingestion.lineage.parser import LINEAGE_PARSING_TIMEOUT
 from metadata.ingestion.models.patch_request import build_patch
 from metadata.ingestion.ometa.client import REST, APIError
-from metadata.ingestion.ometa.utils import get_entity_type, quote
+from metadata.ingestion.ometa.utils import get_entity_type, model_str, quote
 from metadata.utils.logger import ometa_logger
 from metadata.utils.lru_cache import LRU_CACHE_SIZE, LRUCache
 
@@ -248,7 +249,7 @@ class OMetaLineageMixin(Generic[T]):
     def get_lineage_by_id(
         self,
         entity: Union[Type[T], str],
-        entity_id: str,
+        entity_id: Union[str, Uuid],
         up_depth: int = 1,
         down_depth: int = 1,
     ) -> Optional[Dict[str, Any]]:
@@ -260,13 +261,16 @@ class OMetaLineageMixin(Generic[T]):
         :param down_depth: Downstream depth of lineage (default=1, min=0, max=3)
         """
         return self._get_lineage(
-            entity=entity, path=entity_id, up_depth=up_depth, down_depth=down_depth
+            entity=entity,
+            path=model_str(entity_id),
+            up_depth=up_depth,
+            down_depth=down_depth,
         )
 
     def get_lineage_by_name(
         self,
         entity: Union[Type[T], str],
-        fqn: str,
+        fqn: Union[str, FullyQualifiedEntityName],
         up_depth: int = 1,
         down_depth: int = 1,
     ) -> Optional[Dict[str, Any]]:
@@ -279,7 +283,7 @@ class OMetaLineageMixin(Generic[T]):
         """
         return self._get_lineage(
             entity=entity,
-            path=f"name/{quote(fqn)}",
+            path=f"name/{quote(model_str(fqn))}",
             up_depth=up_depth,
             down_depth=down_depth,
         )

metadata/ingestion/sink/metadata_rest.py

@@ -565,9 +565,9 @@ class MetadataRestSink(Sink):  # pylint: disable=too-many-public-methods
             f"Successfully ingested profile metrics for {record.table.fullyQualifiedName.root}"
         )
 
-        if record.sample_data:
+        if record.sample_data and record.sample_data.store:
             table_data = self.metadata.ingest_table_sample_data(
-                table=record.table, sample_data=record.sample_data
+                table=record.table, sample_data=record.sample_data.data
             )
             if not table_data:
                 self.status.failed(

metadata/ingestion/source/database/bigquery/connection.py

@@ -17,7 +17,6 @@ from datetime import datetime
 from functools import partial
 from typing import Optional
 
-from google.api_core.exceptions import NotFound
 from google.cloud.datacatalog_v1 import PolicyTagManagerClient
 from sqlalchemy.engine import Engine
 
@@ -150,8 +149,8 @@ def test_connection(
         test_fn = {
             "CheckAccess": partial(test_connection_engine_step, engine),
             "GetSchemas": partial(execute_inspector_func, engine, "get_schema_names"),
-            "GetTables": partial(get_table_view_names, engine),
-            "GetViews": partial(get_table_view_names, engine),
+            "GetTables": partial(execute_inspector_func, engine, "get_table_names"),
+            "GetViews": partial(execute_inspector_func, engine, "get_view_names"),
             "GetTags": test_tags,
             "GetQueries": partial(
                 test_query,
@@ -171,28 +170,3 @@ def test_connection(
         )
 
     test_connection_inner(engine)
-
-
-def get_table_view_names(connection, schema=None):
-    with connection.connect() as conn:
-        current_schema = schema
-        client = conn.connection._client
-        item_types = ["TABLE", "EXTERNAL", "VIEW", "MATERIALIZED_VIEW"]
-        datasets = client.list_datasets()
-        result = []
-        for dataset in datasets:
-            if current_schema is not None and current_schema != dataset.dataset_id:
-                continue
-
-            try:
-                tables = client.list_tables(dataset.reference, page_size=1)
-                for table in tables:
-                    if table.table_type in item_types:
-                        break
-            except NotFound:
-                # It's possible that the dataset was deleted between when we
-                # fetched the list of datasets and when we try to list the
-                # tables from it. See:
-                # https://github.com/googleapis/python-bigquery-sqlalchemy/issues/105
-                pass
-        return result

metadata/ingestion/source/database/redshift/connection.py

@@ -16,7 +16,6 @@ from functools import partial
 from typing import Optional
 
 from sqlalchemy.engine import Engine
-from sqlalchemy.sql import text
 
 from metadata.generated.schema.entity.automations.workflow import (
     Workflow as AutomationWorkflow,
@@ -39,7 +38,6 @@ from metadata.ingestion.connections.test_connections import (
 from metadata.ingestion.ometa.ometa_api import OpenMetadata
 from metadata.ingestion.source.connections import kill_active_connections
 from metadata.ingestion.source.database.redshift.queries import (
-    REDSHIFT_GET_ALL_RELATIONS,
     REDSHIFT_GET_DATABASE_NAMES,
     REDSHIFT_TEST_GET_QUERIES,
     REDSHIFT_TEST_PARTITION_DETAILS,
@@ -67,11 +65,6 @@ def test_connection(
     Test connection. This can be executed either as part
     of a metadata workflow or during an Automation Workflow
     """
-    table_and_view_query = text(
-        REDSHIFT_GET_ALL_RELATIONS.format(
-            schema_clause="", table_clause="", limit_clause="LIMIT 1"
-        )
-    )
 
     def test_get_queries_permissions(engine_: Engine):
         """Check if we have the right permissions to list queries"""
@@ -85,8 +78,8 @@ def test_connection(
     test_fn = {
         "CheckAccess": partial(test_connection_engine_step, engine),
         "GetSchemas": partial(execute_inspector_func, engine, "get_schema_names"),
-        "GetTables": partial(test_query, statement=table_and_view_query, engine=engine),
-        "GetViews": partial(test_query, statement=table_and_view_query, engine=engine),
+        "GetTables": partial(execute_inspector_func, engine, "get_table_names"),
+        "GetViews": partial(execute_inspector_func, engine, "get_view_names"),
         "GetQueries": partial(test_get_queries_permissions, engine),
         "GetDatabases": partial(
             test_query, statement=REDSHIFT_GET_DATABASE_NAMES, engine=engine

metadata/ingestion/source/database/redshift/queries.py

@@ -236,7 +236,7 @@ REDSHIFT_TEST_PARTITION_DETAILS = "select * from SVV_TABLE_INFO limit 1"
 # hence we are appending "create view <schema>.<table> as " to select query
 # to generate the column level lineage
 REDSHIFT_GET_ALL_RELATIONS = """
-    (SELECT
+    SELECT
         c.relkind,
         n.oid as "schema_oid",
         n.nspname as "schema",
@@ -255,9 +255,8 @@ REDSHIFT_GET_ALL_RELATIONS = """
             JOIN pg_catalog.pg_user u ON u.usesysid = c.relowner
     WHERE c.relkind IN ('r', 'v', 'm', 'S', 'f')
         AND n.nspname !~ '^pg_' {schema_clause} {table_clause}
-        {limit_clause})
     UNION
-    (SELECT
+    SELECT
         'r' AS "relkind",
         s.esoid AS "schema_oid",
         s.schemaname AS "schema",
@@ -273,8 +272,7 @@ REDSHIFT_GET_ALL_RELATIONS = """
         JOIN svv_external_schemas s ON s.schemaname = t.schemaname
         JOIN pg_catalog.pg_user u ON u.usesysid = s.esowner
     where 1 {schema_clause} {table_clause}
-    ORDER BY "relkind", "schema_oid", "schema"
-    {limit_clause});
+    ORDER BY "relkind", "schema_oid", "schema";
     """
 
 

metadata/ingestion/source/database/redshift/utils.py

@@ -386,7 +386,7 @@ def _get_all_relation_info(self, connection, **kw):  # pylint: disable=unused-ar
     result = connection.execute(
         sa.text(
             REDSHIFT_GET_ALL_RELATIONS.format(
-                schema_clause=schema_clause, table_clause=table_clause, limit_clause=""
+                schema_clause=schema_clause, table_clause=table_clause
             )
         )
     )

metadata/ingestion/source/database/salesforce/connection.py

@@ -15,7 +15,6 @@ Source connection handler
 from typing import Optional
 
 from simple_salesforce.api import Salesforce
-from sqlalchemy.engine import Engine
 
 from metadata.generated.schema.entity.automations.workflow import (
     Workflow as AutomationWorkflow,
@@ -27,14 +26,17 @@ from metadata.ingestion.connections.test_connections import test_connection_step
 from metadata.ingestion.ometa.ometa_api import OpenMetadata
 
 
-def get_connection(connection: SalesforceConnection) -> Engine:
+def get_connection(connection: SalesforceConnection) -> Salesforce:
     """
     Create connection
     """
     return Salesforce(
         username=connection.username,
         password=connection.password.get_secret_value(),
-        security_token=connection.securityToken.get_secret_value(),
+        security_token=connection.securityToken.get_secret_value()
+        if connection.securityToken
+        else "",
+        organizationId=connection.organizationId if connection.organizationId else "",
         domain=connection.salesforceDomain,
         version=connection.salesforceApiVersion,
         **connection.connectionArguments.root if connection.connectionArguments else {},

metadata/ingestion/source/database/snowflake/connection.py

@@ -45,7 +45,6 @@ from metadata.ingestion.source.database.snowflake.queries import (
     SNOWFLAKE_TEST_FETCH_TAG,
     SNOWFLAKE_TEST_GET_QUERIES,
     SNOWFLAKE_TEST_GET_TABLES,
-    SNOWFLAKE_TEST_GET_VIEWS,
 )
 from metadata.utils.logger import ingestion_logger
 
@@ -177,11 +176,7 @@ def test_connection(
             statement=SNOWFLAKE_TEST_GET_TABLES,
             engine_wrapper=engine_wrapper,
         ),
-        "GetViews": partial(
-            test_table_query,
-            statement=SNOWFLAKE_TEST_GET_VIEWS,
-            engine_wrapper=engine_wrapper,
-        ),
+        "GetViews": partial(execute_inspector_func, engine_wrapper, "get_view_names"),
         "GetQueries": partial(
             test_query, statement=SNOWFLAKE_TEST_GET_QUERIES, engine=engine
         ),

metadata/ingestion/source/database/snowflake/queries.py

@@ -245,10 +245,6 @@ SNOWFLAKE_TEST_GET_TABLES = """
 SELECT TABLE_NAME FROM "{database_name}".information_schema.tables LIMIT 1
 """
 
-SNOWFLAKE_TEST_GET_VIEWS = """
-SELECT TABLE_NAME FROM "{database_name}".information_schema.views LIMIT 1
-"""
-
 SNOWFLAKE_GET_DATABASES = "SHOW DATABASES"
 
 

metadata/pii/ner.py

@@ -51,7 +51,8 @@ class NEREntity(Enum):
     UK_NHS = TagType.SENSITIVE.value
 
     # Spain
-    NIF = TagType.SENSITIVE.value
+    ES_NIF = TagType.SENSITIVE.value
+    ES_NIE = TagType.SENSITIVE.value
 
     # Italy
     IT_FISCAL_CODE = TagType.SENSITIVE.value
@@ -60,8 +61,25 @@ class NEREntity(Enum):
     IT_PASSPORT = TagType.SENSITIVE.value
     IT_IDENTITY_CARD = TagType.SENSITIVE.value
 
+    # Poland
+    PL_PESEL = TagType.SENSITIVE.value
+
+    # Singapore
+    SG_NRIC_FIN = TagType.SENSITIVE.value
+    SG_UEN = TagType.SENSITIVE.value
+
     # Australia
     AU_ABN = TagType.SENSITIVE.value
     AU_ACN = TagType.SENSITIVE.value
     AU_TFN = TagType.SENSITIVE.value
     AU_MEDICARE = TagType.SENSITIVE.value
+
+    # India
+    IN_PAN = TagType.SENSITIVE.value
+    IN_AADHAAR = TagType.SENSITIVE.value
+    IN_VEHICLE_REGISTRATION = TagType.SENSITIVE.value
+    IN_VOTER = TagType.SENSITIVE.value
+    IN_PASSPORT = TagType.SENSITIVE.value
+
+    # Finland
+    FI_PERSONAL_IDENTITY_CODE = TagType.SENSITIVE.value

metadata/pii/processor.py

@@ -171,7 +171,7 @@ class PIIProcessor(Processor):
                 col_tags = self.process_column(
                     idx=idx,
                     column=column,
-                    table_data=record.sample_data,
+                    table_data=record.sample_data.data,
                     confidence_threshold=self.confidence_threshold,
                 )
                 if col_tags:

metadata/pii/scanners/ner_scanner.py

@@ -14,6 +14,7 @@ NER Scanner based on Presidio.
 Supported Entities https://microsoft.github.io/presidio/supported_entities/
 """
 import json
+import logging
 import traceback
 from collections import defaultdict
 from typing import Any, Dict, List, Optional, Tuple, Union
@@ -26,9 +27,11 @@ from metadata.pii.models import TagAndConfidence
 from metadata.pii.ner import NEREntity
 from metadata.pii.scanners.base import BaseScanner
 from metadata.utils import fqn
-from metadata.utils.logger import pii_logger
+from metadata.utils.logger import METADATA_LOGGER, pii_logger
 
 logger = pii_logger()
+SUPPORTED_LANG = "en"
+PRESIDIO_LOGGER = "presidio-analyzer"
 
 
 class StringAnalysis(BaseModel):
@@ -40,11 +43,16 @@ class StringAnalysis(BaseModel):
     appearances: int
 
 
+class NLPEngineModel(BaseModel):
+    """Required to pass the nlp_engine as {"lang_code": "en", "model_name": "en_core_web_lg"}"""
+
+    lang_code: str
+    model_name: str
+
+
 # pylint: disable=import-outside-toplevel
 class NERScanner(BaseScanner):
-    """
-    Based on https://microsoft.github.io/presidio/
-    """
+    """Based on https://microsoft.github.io/presidio/"""
 
     def __init__(self):
         import spacy
@@ -60,8 +68,19 @@ class NERScanner(BaseScanner):
             download(SPACY_EN_MODEL)
             spacy.load(SPACY_EN_MODEL)
 
+        nlp_engine_model = NLPEngineModel(
+            lang_code=SUPPORTED_LANG, model_name=SPACY_EN_MODEL
+        )
+
+        # Set the presidio logger to talk less about internal entities unless we are debugging
+        logging.getLogger(PRESIDIO_LOGGER).setLevel(
+            logging.INFO
+            if logging.getLogger(METADATA_LOGGER).level == logging.DEBUG
+            else logging.ERROR
+        )
+
         self.analyzer = AnalyzerEngine(
-            nlp_engine=SpacyNlpEngine(models={"en": SPACY_EN_MODEL})
+            nlp_engine=SpacyNlpEngine(models=[nlp_engine_model.model_dump()])
         )
 
     @staticmethod

metadata/profiler/api/models.py

@@ -17,9 +17,10 @@ multiple profilers per table and columns.
 """
 from typing import List, Optional, Type, Union
 
-from pydantic import ConfigDict
+from pydantic import ConfigDict, Field
 from sqlalchemy import Column
 from sqlalchemy.orm import DeclarativeMeta
+from typing_extensions import Annotated
 
 from metadata.config.common import ConfigModel
 from metadata.generated.schema.api.data.createTableProfile import (
@@ -37,6 +38,7 @@ from metadata.generated.schema.entity.services.connections.connectionBasicType i
 )
 from metadata.generated.schema.tests.customMetric import CustomMetric
 from metadata.generated.schema.type.basic import FullyQualifiedEntityName
+from metadata.ingestion.models.custom_pydantic import BaseModel
 from metadata.ingestion.models.table_metadata import ColumnTag
 from metadata.profiler.metrics.core import Metric, MetricTypes
 from metadata.profiler.processor.models import ProfilerDef
@@ -104,6 +106,15 @@ class ProfilerProcessorConfig(ConfigModel):
     databaseConfig: Optional[List[DatabaseAndSchemaConfig]] = []
 
 
+class SampleData(BaseModel):
+    """TableData wrapper to handle ephemeral SampleData"""
+
+    data: Annotated[TableData, Field(None, description="Table Sample Data")]
+    store: Annotated[
+        bool, Field(False, description="Is the sample data should be stored or not")
+    ]
+
+
 class ProfilerResponse(ConfigModel):
     """
     ORM Profiler processor response.
@@ -114,7 +125,7 @@ class ProfilerResponse(ConfigModel):
 
     table: Table
     profile: CreateTableProfileRequest
-    sample_data: Optional[TableData] = None
+    sample_data: Optional[SampleData] = None
     column_tags: Optional[List[ColumnTag]] = None
 
     def __str__(self):

metadata/profiler/processor/core.py

@@ -33,7 +33,6 @@ from metadata.generated.schema.entity.data.table import (
     ColumnProfile,
     ColumnProfilerConfig,
     SystemProfile,
-    TableData,
     TableProfile,
 )
 from metadata.generated.schema.settings.settings import Settings
@@ -41,7 +40,7 @@ from metadata.generated.schema.tests.customMetric import (
     CustomMetric as CustomMetricEntity,
 )
 from metadata.generated.schema.type.basic import Timestamp
-from metadata.profiler.api.models import ProfilerResponse, ThreadPoolMetrics
+from metadata.profiler.api.models import ProfilerResponse, SampleData, ThreadPoolMetrics
 from metadata.profiler.interface.profiler_interface import ProfilerInterface
 from metadata.profiler.metrics.core import (
     ComposedMetric,
@@ -492,7 +491,12 @@ class Profiler(Generic[TMetric]):
             )
             self.compute_metrics()
 
-        if self.source_config.generateSampleData:
+        # We need the sample data for Sample Data or PII Sensitive processing.
+        # We'll nullify the Sample Data after the PII processing so that it's not stored.
+        if (
+            self.source_config.generateSampleData
+            or self.source_config.processPiiSensitive
+        ):
             sample_data = self.generate_sample_data()
         else:
             sample_data = None
@@ -510,7 +514,7 @@ class Profiler(Generic[TMetric]):
         return table_profile
 
     @calculate_execution_time(store=False)
-    def generate_sample_data(self) -> Optional[TableData]:
+    def generate_sample_data(self) -> Optional[SampleData]:
         """Fetch and ingest sample data
 
         Returns:
@@ -532,7 +536,10 @@ class Profiler(Generic[TMetric]):
                     SAMPLE_DATA_DEFAULT_COUNT, self.profiler_interface.sample_data_count
                 )
             ]
-            return table_data
+            return SampleData(
+                data=table_data, store=self.source_config.generateSampleData
+            )
+
         except Exception as err:
             logger.debug(traceback.format_exc())
             logger.warning(f"Error fetching sample data: {err}")