acryl-datahub 1.3.1__py3-none-any.whl → 1.3.1.1__py3-none-any.whl

datahub/ingestion/source/dremio/dremio_source.py

@@ -336,10 +336,10 @@ class DremioSource(StatefulIngestionSourceBase):
             return
 
         dataset_urn = make_dataset_urn_with_platform_instance(
-            platform=self.get_platform(),
-            name=dataset_name,
-            platform_instance=self.config.platform_instance,
+            platform=make_data_platform_urn(self.get_platform()),
+            name=f"dremio.{dataset_name}",
             env=self.config.env,
+            platform_instance=self.config.platform_instance,
         )
 
         for dremio_mcp in self.dremio_aspects.populate_dataset_mcp(
@@ -419,10 +419,10 @@ class DremioSource(StatefulIngestionSourceBase):
         schema_str = ".".join(dataset_info.path)
         dataset_name = f"{schema_str}.{dataset_info.resource_name}".lower()
         dataset_urn = make_dataset_urn_with_platform_instance(
-            platform=self.get_platform(),
-            name=dataset_name,
-            platform_instance=self.config.platform_instance,
+            platform=make_data_platform_urn(self.get_platform()),
+            name=f"dremio.{dataset_name}",
             env=self.config.env,
+            platform_instance=self.config.platform_instance,
         )
         yield from self.profiler.get_workunits(dataset_info, dataset_urn)
 
@@ -434,10 +434,10 @@ class DremioSource(StatefulIngestionSourceBase):
         """
         upstream_urns = [
             make_dataset_urn_with_platform_instance(
-                platform=self.get_platform(),
-                name=upstream_table.lower(),
-                platform_instance=self.config.platform_instance,
+                platform=make_data_platform_urn(self.get_platform()),
+                name=f"dremio.{upstream_table.lower()}",
                 env=self.config.env,
+                platform_instance=self.config.platform_instance,
             )
             for upstream_table in parents
         ]
@@ -496,19 +496,19 @@ class DremioSource(StatefulIngestionSourceBase):
         if query.query and query.affected_dataset:
             upstream_urns = [
                 make_dataset_urn_with_platform_instance(
-                    platform=self.get_platform(),
-                    name=ds.lower(),
-                    platform_instance=self.config.platform_instance,
+                    platform=make_data_platform_urn(self.get_platform()),
+                    name=f"dremio.{ds.lower()}",
                     env=self.config.env,
+                    platform_instance=self.config.platform_instance,
                 )
                 for ds in query.queried_datasets
             ]
 
             downstream_urn = make_dataset_urn_with_platform_instance(
-                platform=self.get_platform(),
-                name=query.affected_dataset.lower(),
-                platform_instance=self.config.platform_instance,
+                platform=make_data_platform_urn(self.get_platform()),
+                name=f"dremio.{query.affected_dataset.lower()}",
                 env=self.config.env,
+                platform_instance=self.config.platform_instance,
             )
 
             # Add query to SqlParsingAggregator

datahub/ingestion/source/dynamodb/dynamodb.py

@@ -200,7 +200,7 @@ class DynamoDBSource(StatefulIngestionSourceBase):
 
     @classmethod
     def create(cls, config_dict: dict, ctx: PipelineContext) -> "DynamoDBSource":
-        config = DynamoDBConfig.parse_obj(config_dict)
+        config = DynamoDBConfig.model_validate(config_dict)
         return cls(ctx, config, "dynamodb")
 
     def get_workunit_processors(self) -> List[Optional[MetadataWorkUnitProcessor]]:

datahub/ingestion/source/elastic_search.py

@@ -8,7 +8,7 @@ from hashlib import md5
 from typing import Any, Dict, Generator, Iterable, List, Optional, Tuple, Type, Union
 
 from elasticsearch import Elasticsearch
-from pydantic import validator
+from pydantic import field_validator
 from pydantic.fields import Field
 
 from datahub.configuration.common import AllowDenyPattern, ConfigModel
@@ -330,7 +330,8 @@ class ElasticsearchSourceConfig(
             self.profiling.operation_config
         )
 
-    @validator("host")
+    @field_validator("host", mode="after")
+    @classmethod
     def host_colon_port_comma(cls, host_val: str) -> str:
         for entry in host_val.split(","):
             entry = remove_protocol(entry)
@@ -382,7 +383,7 @@ class ElasticsearchSource(StatefulIngestionSourceBase):
     def create(
         cls, config_dict: Dict[str, Any], ctx: PipelineContext
     ) -> "ElasticsearchSource":
-        config = ElasticsearchSourceConfig.parse_obj(config_dict)
+        config = ElasticsearchSourceConfig.model_validate(config_dict)
         return cls(config, ctx)
 
     def get_workunit_processors(self) -> List[Optional[MetadataWorkUnitProcessor]]:

datahub/ingestion/source/excel/source.py

@@ -156,7 +156,7 @@ class ExcelSource(StatefulIngestionSourceBase):
 
     @classmethod
     def create(cls, config_dict: dict, ctx: PipelineContext) -> "ExcelSource":
-        config = ExcelSourceConfig.parse_obj(config_dict)
+        config = ExcelSourceConfig.model_validate(config_dict)
         return cls(ctx, config)
 
     def get_workunit_processors(self) -> List[Optional[MetadataWorkUnitProcessor]]:

datahub/ingestion/source/feast.py

@@ -462,7 +462,7 @@ class FeastRepositorySource(StatefulIngestionSourceBase):
 
     @classmethod
     def create(cls, config_dict, ctx):
-        config = FeastRepositorySourceConfig.parse_obj(config_dict)
+        config = FeastRepositorySourceConfig.model_validate(config_dict)
         return cls(config, ctx)
 
     def get_workunit_processors(self) -> List[Optional[MetadataWorkUnitProcessor]]:

datahub/ingestion/source/file.py

@@ -9,7 +9,7 @@ from functools import partial
 from typing import Any, Iterable, Iterator, List, Optional, Tuple, Union
 
 import ijson
-from pydantic import validator
+from pydantic import field_validator
 from pydantic.fields import Field
 
 from datahub.configuration.common import ConfigEnum
@@ -103,7 +103,8 @@ class FileSourceConfig(StatefulIngestionConfigBase):
 
     stateful_ingestion: Optional[StatefulStaleMetadataRemovalConfig] = None
 
-    @validator("file_extension", always=True)
+    @field_validator("file_extension", mode="after")
+    @classmethod
     def add_leading_dot_to_extension(cls, v: str) -> str:
         if v:
             if v.startswith("."):
@@ -205,7 +206,7 @@ class GenericFileSource(StatefulIngestionSourceBase, TestableSource):
 
     @classmethod
     def create(cls, config_dict, ctx):
-        config = FileSourceConfig.parse_obj(config_dict)
+        config = FileSourceConfig.model_validate(config_dict)
         return cls(ctx, config)
 
     def get_filenames(self) -> Iterable[FileInfo]:
@@ -358,7 +359,7 @@ class GenericFileSource(StatefulIngestionSourceBase, TestableSource):
 
     @staticmethod
     def test_connection(config_dict: dict) -> TestConnectionReport:
-        config = FileSourceConfig.parse_obj(config_dict)
+        config = FileSourceConfig.model_validate(config_dict)
         exists = os.path.exists(config.path)
         if not exists:
             return TestConnectionReport(

datahub/ingestion/source/fivetran/config.py

@@ -1,10 +1,10 @@
 import dataclasses
 import logging
 import warnings
-from typing import Dict, Optional
+from typing import Any, Dict, Optional
 
 import pydantic
-from pydantic import Field, root_validator
+from pydantic import Field, field_validator, model_validator
 from typing_extensions import Literal
 
 from datahub.configuration.common import (
@@ -98,7 +98,8 @@ class DatabricksDestinationConfig(UnityCatalogConnectionConfig):
     catalog: str = Field(description="The fivetran connector log catalog.")
     log_schema: str = Field(description="The fivetran connector log schema.")
 
-    @pydantic.validator("warehouse_id")
+    @field_validator("warehouse_id", mode="after")
+    @classmethod
     def warehouse_id_should_not_be_empty(cls, warehouse_id: Optional[str]) -> str:
         if warehouse_id is None or (warehouse_id and warehouse_id.strip() == ""):
             raise ValueError("Fivetran requires warehouse_id to be set")
@@ -141,29 +142,28 @@ class FivetranLogConfig(ConfigModel):
         "destination_config", "snowflake_destination_config"
     )
 
-    @root_validator(skip_on_failure=True)
-    def validate_destination_platfrom_and_config(cls, values: Dict) -> Dict:
-        destination_platform = values["destination_platform"]
-        if destination_platform == "snowflake":
-            if "snowflake_destination_config" not in values:
+    @model_validator(mode="after")
+    def validate_destination_platform_and_config(self) -> "FivetranLogConfig":
+        if self.destination_platform == "snowflake":
+            if self.snowflake_destination_config is None:
                 raise ValueError(
                     "If destination platform is 'snowflake', user must provide snowflake destination configuration in the recipe."
                 )
-        elif destination_platform == "bigquery":
-            if "bigquery_destination_config" not in values:
+        elif self.destination_platform == "bigquery":
+            if self.bigquery_destination_config is None:
                 raise ValueError(
                     "If destination platform is 'bigquery', user must provide bigquery destination configuration in the recipe."
                 )
-        elif destination_platform == "databricks":
-            if "databricks_destination_config" not in values:
+        elif self.destination_platform == "databricks":
+            if self.databricks_destination_config is None:
                 raise ValueError(
                     "If destination platform is 'databricks', user must provide databricks destination configuration in the recipe."
                 )
         else:
             raise ValueError(
-                f"Destination platform '{destination_platform}' is not yet supported."
+                f"Destination platform '{self.destination_platform}' is not yet supported."
             )
-        return values
+        return self
 
 
 @dataclasses.dataclass
@@ -267,8 +267,9 @@ class FivetranSourceConfig(StatefulIngestionConfigBase, DatasetSourceConfigMixin
         description="Fivetran REST API configuration, used to provide wider support for connections.",
     )
 
-    @pydantic.root_validator(pre=True)
-    def compat_sources_to_database(cls, values: Dict) -> Dict:
+    @model_validator(mode="before")
+    @classmethod
+    def compat_sources_to_database(cls, values: Any) -> Any:
         if "sources_to_database" in values:
             warnings.warn(
                 "The sources_to_database field is deprecated, please use sources_to_platform_instance instead.",

datahub/ingestion/source/fivetran/fivetran.py

@@ -234,12 +234,12 @@ class FivetranSource(StatefulIngestionSourceBase):
         return dict(
             **{
                 f"source.{k}": str(v)
-                for k, v in source_details.dict().items()
+                for k, v in source_details.model_dump().items()
                 if v is not None and not isinstance(v, bool)
             },
             **{
                 f"destination.{k}": str(v)
-                for k, v in destination_details.dict().items()
+                for k, v in destination_details.model_dump().items()
                 if v is not None and not isinstance(v, bool)
             },
         )

datahub/ingestion/source/gc/datahub_gc.py

@@ -127,7 +127,7 @@ class DataHubGcSource(Source):
 
     @classmethod
     def create(cls, config_dict, ctx):
-        config = DataHubGcSourceConfig.parse_obj(config_dict)
+        config = DataHubGcSourceConfig.model_validate(config_dict)
         return cls(ctx, config)
 
     # auto_work_unit_report is overriden to disable a couple of automation like auto status aspect, etc. which is not needed her.

datahub/ingestion/source/gcs/gcs_source.py

@@ -1,7 +1,7 @@
 import logging
-from typing import Dict, Iterable, List, Optional
+from typing import Iterable, List, Optional
 
-from pydantic import Field, SecretStr, validator
+from pydantic import Field, SecretStr, model_validator
 
 from datahub.configuration.common import ConfigModel
 from datahub.configuration.source_common import DatasetSourceConfigMixin
@@ -64,18 +64,16 @@ class GCSSourceConfig(
 
     stateful_ingestion: Optional[StatefulStaleMetadataRemovalConfig] = None
 
-    @validator("path_specs", always=True)
-    def check_path_specs_and_infer_platform(
-        cls, path_specs: List[PathSpec], values: Dict
-    ) -> List[PathSpec]:
-        if len(path_specs) == 0:
+    @model_validator(mode="after")
+    def check_path_specs_and_infer_platform(self) -> "GCSSourceConfig":
+        if len(self.path_specs) == 0:
             raise ValueError("path_specs must not be empty")
 
         # Check that all path specs have the gs:// prefix.
-        if any([not is_gcs_uri(path_spec.include) for path_spec in path_specs]):
+        if any([not is_gcs_uri(path_spec.include) for path_spec in self.path_specs]):
             raise ValueError("All path_spec.include should start with gs://")
 
-        return path_specs
+        return self
 
 
 class GCSSourceReport(DataLakeSourceReport):
@@ -105,7 +103,7 @@ class GCSSource(StatefulIngestionSourceBase):
 
     @classmethod
     def create(cls, config_dict, ctx):
-        config = GCSSourceConfig.parse_obj(config_dict)
+        config = GCSSourceConfig.model_validate(config_dict)
         return cls(config, ctx)
 
     def create_equivalent_s3_config(self):

datahub/ingestion/source/ge_profiling_config.py

@@ -4,6 +4,7 @@ import os
 from typing import Annotated, Any, Dict, List, Optional
 
 import pydantic
+from pydantic import model_validator
 from pydantic.fields import Field
 
 from datahub.configuration.common import AllowDenyPattern, ConfigModel, SupportedSources
@@ -212,7 +213,8 @@ class GEProfilingConfig(GEProfilingBaseConfig):
         description="Whether to profile complex types like structs, arrays and maps. ",
     )
 
-    @pydantic.root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def deprecate_bigquery_temp_table_schema(cls, values):
         # TODO: Update docs to remove mention of this field.
         if "bigquery_temp_table_schema" in values:
@@ -222,16 +224,17 @@ class GEProfilingConfig(GEProfilingBaseConfig):
             del values["bigquery_temp_table_schema"]
         return values
 
-    @pydantic.root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def ensure_field_level_settings_are_normalized(
-        cls: "GEProfilingConfig", values: Dict[str, Any]
+        cls, values: Dict[str, Any]
     ) -> Dict[str, Any]:
         max_num_fields_to_profile_key = "max_number_of_fields_to_profile"
         max_num_fields_to_profile = values.get(max_num_fields_to_profile_key)
 
         # Disable all field-level metrics.
         if values.get("profile_table_level_only"):
-            for field_level_metric in cls.__fields__:
+            for field_level_metric in cls.model_fields:
                 if field_level_metric.startswith("include_field_"):
                     if values.get(field_level_metric):
                         raise ValueError(
@@ -267,7 +270,7 @@ class GEProfilingConfig(GEProfilingBaseConfig):
         )
 
     def config_for_telemetry(self) -> Dict[str, Any]:
-        config_dict = self.dict()
+        config_dict = self.model_dump()
 
         return {
             flag: config_dict[flag]

datahub/ingestion/source/grafana/grafana_api.py

@@ -69,7 +69,7 @@ class GrafanaAPIClient:
                 if not batch:
                     break
 
-                folders.extend(Folder.parse_obj(folder) for folder in batch)
+                folders.extend(Folder.model_validate(folder) for folder in batch)
                 page += 1
             except requests.exceptions.RequestException as e:
                 self.report.report_failure(
@@ -88,7 +88,7 @@ class GrafanaAPIClient:
         try:
             response = self.session.get(f"{self.base_url}/api/dashboards/uid/{uid}")
             response.raise_for_status()
-            return Dashboard.parse_obj(response.json())
+            return Dashboard.model_validate(response.json())
         except requests.exceptions.RequestException as e:
             self.report.warning(
                 title="Dashboard Fetch Error",

datahub/ingestion/source/grafana/grafana_config.py

@@ -1,6 +1,6 @@
 from typing import Dict, Optional
 
-from pydantic import Field, SecretStr, validator
+from pydantic import Field, SecretStr, field_validator
 
 from datahub.configuration.common import AllowDenyPattern, HiddenFromDocs
 from datahub.configuration.source_common import (
@@ -99,6 +99,7 @@ class GrafanaSourceConfig(
         description="Map of Grafana datasource types/UIDs to platform connection configs for lineage extraction",
     )
 
-    @validator("url", allow_reuse=True)
-    def remove_trailing_slash(cls, v):
+    @field_validator("url", mode="after")
+    @classmethod
+    def remove_trailing_slash(cls, v: str) -> str:
         return config_clean.remove_trailing_slashes(v)

datahub/ingestion/source/grafana/grafana_source.py

@@ -171,7 +171,7 @@ class GrafanaSource(StatefulIngestionSourceBase):
 
     @classmethod
     def create(cls, config_dict: dict, ctx: PipelineContext) -> "GrafanaSource":
-        config = GrafanaSourceConfig.parse_obj(config_dict)
+        config = GrafanaSourceConfig.model_validate(config_dict)
         return cls(config, ctx)
 
     def get_workunit_processors(self) -> List[Optional[MetadataWorkUnitProcessor]]:

datahub/ingestion/source/grafana/models.py

@@ -79,18 +79,29 @@ class Dashboard(_GrafanaBaseModel):
         for panel_data in panels_data:
             if panel_data.get("type") == "row" and "panels" in panel_data:
                 panels.extend(
-                    Panel.parse_obj(p)
+                    Panel.model_validate(p)
                     for p in panel_data["panels"]
                     if p.get("type") != "row"
                 )
             elif panel_data.get("type") != "row":
-                panels.append(Panel.parse_obj(panel_data))
+                panels.append(Panel.model_validate(panel_data))
         return panels
 
     @classmethod
-    def parse_obj(cls, data: Dict[str, Any]) -> "Dashboard":
+    def model_validate(
+        cls,
+        obj: Any,
+        *,
+        strict: Optional[bool] = None,
+        from_attributes: Optional[bool] = None,
+        context: Optional[Any] = None,
+        by_alias: Optional[bool] = None,
+        by_name: Optional[bool] = None,
+    ) -> "Dashboard":
         """Custom parsing to handle nested panel extraction."""
-        dashboard_data = data.get("dashboard", {})
+        # Handle both direct dashboard data and nested structure with 'dashboard' key
+        dashboard_data = obj.get("dashboard", obj)
+
         _panel_data = dashboard_data.get("panels", [])
         panels = []
         try:
@@ -113,7 +124,14 @@ class Dashboard(_GrafanaBaseModel):
         if "refresh" in dashboard_dict and isinstance(dashboard_dict["refresh"], bool):
             dashboard_dict["refresh"] = str(dashboard_dict["refresh"])
 
-        return super().parse_obj(dashboard_dict)
+        return super().model_validate(
+            dashboard_dict,
+            strict=strict,
+            from_attributes=from_attributes,
+            context=context,
+            by_alias=by_alias,
+            by_name=by_name,
+        )
 
 
 class Folder(_GrafanaBaseModel):

datahub/ingestion/source/hex/api.py

@@ -4,7 +4,7 @@ from datetime import datetime, timezone
 from typing import Any, Dict, Generator, List, Optional, Union
 
 import requests
-from pydantic import BaseModel, Field, ValidationError, validator
+from pydantic import BaseModel, Field, ValidationError, field_validator
 from requests.adapters import HTTPAdapter
 from typing_extensions import assert_never
 from urllib3.util.retry import Retry
@@ -50,7 +50,8 @@ class HexApiProjectAnalytics(BaseModel):
         default=None, alias="publishedResultsUpdatedAt"
     )
 
-    @validator("last_viewed_at", "published_results_updated_at", pre=True)
+    @field_validator("last_viewed_at", "published_results_updated_at", mode="before")
+    @classmethod
     def parse_datetime(cls, value):
         if value is None:
             return None
@@ -167,14 +168,15 @@ class HexApiProjectApiResource(BaseModel):
     class Config:
         extra = "ignore"  # Allow extra fields in the JSON
 
-    @validator(
+    @field_validator(
         "created_at",
         "last_edited_at",
         "last_published_at",
         "archived_at",
         "trashed_at",
-        pre=True,
+        mode="before",
     )
+    @classmethod
     def parse_datetime(cls, value):
         if value is None:
             return None
@@ -292,7 +294,7 @@ class HexApi:
             )
             response.raise_for_status()
 
-            api_response = HexApiProjectsListResponse.parse_obj(response.json())
+            api_response = HexApiProjectsListResponse.model_validate(response.json())
             logger.info(f"Fetched {len(api_response.values)} items")
             params["after"] = (
                 api_response.pagination.after if api_response.pagination else None

datahub/ingestion/source/hex/hex.py

@@ -3,7 +3,7 @@ from dataclasses import dataclass
 from datetime import datetime, timedelta, timezone
 from typing import Any, Dict, Iterable, List, Optional
 
-from pydantic import Field, SecretStr, root_validator
+from pydantic import Field, SecretStr, model_validator
 from typing_extensions import assert_never
 
 from datahub.configuration.common import AllowDenyPattern
@@ -120,7 +120,8 @@ class HexSourceConfig(
         description="Number of items to fetch per DataHub API call.",
     )
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
+    @classmethod
     def validate_lineage_times(cls, data: Dict[str, Any]) -> Dict[str, Any]:
         # In-place update of the input dict would cause state contamination. This was discovered through test failures
         # in test_hex.py where the same dict is reused.
@@ -238,7 +239,7 @@ class HexSource(StatefulIngestionSourceBase):
 
     @classmethod
     def create(cls, config_dict: Dict[str, Any], ctx: PipelineContext) -> "HexSource":
-        config = HexSourceConfig.parse_obj(config_dict)
+        config = HexSourceConfig.model_validate(config_dict)
         return cls(config, ctx)
 
     def get_workunit_processors(self) -> List[Optional[MetadataWorkUnitProcessor]]:

datahub/ingestion/source/iceberg/iceberg.py

@@ -161,7 +161,7 @@ class IcebergSource(StatefulIngestionSourceBase):
 
     @classmethod
     def create(cls, config_dict: Dict, ctx: PipelineContext) -> "IcebergSource":
-        config = IcebergSourceConfig.parse_obj(config_dict)
+        config = IcebergSourceConfig.model_validate(config_dict)
         return cls(config, ctx)
 
     def get_workunit_processors(self) -> List[Optional[MetadataWorkUnitProcessor]]:

datahub/ingestion/source/iceberg/iceberg_common.py

@@ -4,7 +4,7 @@ from dataclasses import dataclass, field
 from typing import Any, Dict, Optional
 
 from humanfriendly import format_timespan
-from pydantic import Field, validator
+from pydantic import Field, field_validator
 from pyiceberg.catalog import Catalog, load_catalog
 from pyiceberg.catalog.rest import RestCatalog
 from requests.adapters import HTTPAdapter
@@ -108,7 +108,8 @@ class IcebergSourceConfig(StatefulIngestionConfigBase, DatasetSourceConfigMixin)
         default=1, description="How many threads will be processing tables"
     )
 
-    @validator("catalog", pre=True, always=True)
+    @field_validator("catalog", mode="before")
+    @classmethod
     def handle_deprecated_catalog_format(cls, value):
         # Once support for deprecated format is dropped, we can remove this validator.
         if (
@@ -131,7 +132,8 @@ class IcebergSourceConfig(StatefulIngestionConfigBase, DatasetSourceConfigMixin)
         # In case the input is already the new format or is invalid
         return value
 
-    @validator("catalog")
+    @field_validator("catalog", mode="after")
+    @classmethod
     def validate_catalog_size(cls, value):
         if len(value) != 1:
             raise ValueError("The catalog must contain exactly one entry.")

datahub/ingestion/source/identity/azure_ad.py

@@ -254,7 +254,7 @@ class AzureADSource(StatefulIngestionSourceBase):
 
     @classmethod
     def create(cls, config_dict, ctx):
-        config = AzureADConfig.parse_obj(config_dict)
+        config = AzureADConfig.model_validate(config_dict)
         return cls(config, ctx)
 
     def __init__(self, config: AzureADConfig, ctx: PipelineContext):

datahub/ingestion/source/identity/okta.py

@@ -11,7 +11,7 @@ import nest_asyncio
 from okta.client import Client as OktaClient
 from okta.exceptions import OktaAPIException
 from okta.models import Group, GroupProfile, User, UserProfile, UserStatus
-from pydantic import validator
+from pydantic import model_validator
 from pydantic.fields import Field
 
 from datahub.emitter.mcp import MetadataChangeProposalWrapper
@@ -157,21 +157,21 @@ class OktaConfig(StatefulIngestionConfigBase):
     mask_group_id: bool = True
     mask_user_id: bool = True
 
-    @validator("okta_users_search")
-    def okta_users_one_of_filter_or_search(cls, v, values):
-        if v and values["okta_users_filter"]:
+    @model_validator(mode="after")
+    def okta_users_one_of_filter_or_search(self) -> "OktaConfig":
+        if self.okta_users_search and self.okta_users_filter:
             raise ValueError(
                 "Only one of okta_users_filter or okta_users_search can be set"
             )
-        return v
+        return self
 
-    @validator("okta_groups_search")
-    def okta_groups_one_of_filter_or_search(cls, v, values):
-        if v and values["okta_groups_filter"]:
+    @model_validator(mode="after")
+    def okta_groups_one_of_filter_or_search(self) -> "OktaConfig":
+        if self.okta_groups_search and self.okta_groups_filter:
             raise ValueError(
                 "Only one of okta_groups_filter or okta_groups_search can be set"
             )
-        return v
+        return self
 
 
 @dataclass
@@ -288,7 +288,7 @@ class OktaSource(StatefulIngestionSourceBase):
 
     @classmethod
     def create(cls, config_dict, ctx):
-        config = OktaConfig.parse_obj(config_dict)
+        config = OktaConfig.model_validate(config_dict)
         return cls(config, ctx)
 
     def __init__(self, config: OktaConfig, ctx: PipelineContext):

datahub/ingestion/source/kafka/kafka.py

@@ -267,7 +267,7 @@ class KafkaSource(StatefulIngestionSourceBase, TestableSource):
 
     @classmethod
     def create(cls, config_dict: Dict, ctx: PipelineContext) -> "KafkaSource":
-        config: KafkaSourceConfig = KafkaSourceConfig.parse_obj(config_dict)
+        config: KafkaSourceConfig = KafkaSourceConfig.model_validate(config_dict)
         return cls(config, ctx)
 
     def get_workunit_processors(self) -> List[Optional[MetadataWorkUnitProcessor]]:

datahub/ingestion/source/ldap.py

@@ -242,7 +242,7 @@ class LDAPSource(StatefulIngestionSourceBase):
     @classmethod
     def create(cls, config_dict: Dict[str, Any], ctx: PipelineContext) -> "LDAPSource":
         """Factory method."""
-        config = LDAPSourceConfig.parse_obj(config_dict)
+        config = LDAPSourceConfig.model_validate(config_dict)
         return cls(ctx, config)
 
     def get_workunit_processors(self) -> List[Optional[MetadataWorkUnitProcessor]]: