mlrun 1.7.0rc14__py3-none-any.whl → 1.7.0rc22__py3-none-any.whl

mlrun/common/schemas/model_monitoring/constants.py

@@ -81,6 +81,8 @@ class EventFieldType:
     DRIFT_DETECTED_THRESHOLD = "drift_detected_threshold"
     POSSIBLE_DRIFT_THRESHOLD = "possible_drift_threshold"
     SAMPLE_PARQUET_PATH = "sample_parquet_path"
+    TIME = "time"
+    TABLE_COLUMN = "table_column"
 
 
 class FeatureSetFeatures(MonitoringStrEnum):
@@ -99,14 +101,17 @@ class FeatureSetFeatures(MonitoringStrEnum):
 
 class ApplicationEvent:
     APPLICATION_NAME = "application_name"
-    CURRENT_STATS = "current_stats"
-    FEATURE_STATS = "feature_stats"
-    SAMPLE_PARQUET_PATH = "sample_parquet_path"
     START_INFER_TIME = "start_infer_time"
     END_INFER_TIME = "end_infer_time"
     LAST_REQUEST = "last_request"
     ENDPOINT_ID = "endpoint_id"
     OUTPUT_STREAM_URI = "output_stream_uri"
+    MLRUN_CONTEXT = "mlrun_context"
+
+    # Deprecated fields - TODO : delete in 1.9.0  (V1 app deprecation)
+    SAMPLE_PARQUET_PATH = "sample_parquet_path"
+    CURRENT_STATS = "current_stats"
+    FEATURE_STATS = "feature_stats"
 
 
 class WriterEvent(MonitoringStrEnum):
@@ -114,6 +119,21 @@ class WriterEvent(MonitoringStrEnum):
     ENDPOINT_ID = "endpoint_id"
     START_INFER_TIME = "start_infer_time"
     END_INFER_TIME = "end_infer_time"
+    EVENT_KIND = "event_kind"  # metric or result
+    DATA = "data"
+
+
+class WriterEventKind(MonitoringStrEnum):
+    METRIC = "metric"
+    RESULT = "result"
+
+
+class MetricData(MonitoringStrEnum):
+    METRIC_NAME = "metric_name"
+    METRIC_VALUE = "metric_value"
+
+
+class ResultData(MonitoringStrEnum):
     RESULT_NAME = "result_name"
     RESULT_VALUE = "result_value"
     RESULT_KIND = "result_kind"
@@ -138,10 +158,6 @@ class EventKeyMetrics:
     REAL_TIME = "real_time"
 
 
-class TimeSeriesTarget:
-    TSDB = "tsdb"
-
-
 class ModelEndpointTarget:
     V3IO_NOSQL = "v3io-nosql"
     SQL = "sql"
@@ -153,6 +169,7 @@ class ProjectSecretKeys:
     PIPELINES_ACCESS_KEY = "MODEL_MONITORING_PIPELINES_ACCESS_KEY"
     KAFKA_BROKERS = "KAFKA_BROKERS"
     STREAM_PATH = "STREAM_PATH"
+    TSDB_CONNECTION = "TSDB_CONNECTION"
 
 
 class ModelMonitoringStoreKinds:
@@ -170,12 +187,15 @@ class SchedulingKeys:
 class FileTargetKind:
     ENDPOINTS = "endpoints"
     EVENTS = "events"
+    PREDICTIONS = "predictions"
     STREAM = "stream"
     PARQUET = "parquet"
     APPS_PARQUET = "apps_parquet"
     LOG_STREAM = "log_stream"
     APP_RESULTS = "app_results"
+    APP_METRICS = "app_metrics"
     MONITORING_SCHEDULES = "monitoring_schedules"
+    MONITORING_APPLICATION = "monitoring_application"
 
 
 class ModelMonitoringMode(str, Enum):
@@ -210,6 +230,18 @@ class MonitoringFunctionNames(MonitoringStrEnum):
     WRITER = "model-monitoring-writer"
 
 
+class V3IOTSDBTables(MonitoringStrEnum):
+    APP_RESULTS = "app-results"
+    METRICS = "metrics"
+    EVENTS = "events"
+
+
+class TDEngineSuperTables(MonitoringStrEnum):
+    APP_RESULTS = "app_results"
+    METRICS = "metrics"
+    PREDICTIONS = "predictions"
+
+
 @dataclass
 class FunctionURI:
     project: str
@@ -286,6 +318,7 @@ class ResultKindApp(Enum):
     concept_drift = 1
     model_performance = 2
     system_performance = 3
+    custom = 4
 
 
 class ResultStatusApp(IntEnum):
@@ -303,11 +336,29 @@ class ModelMonitoringAppLabel:
     KEY = "mlrun__type"
     VAL = "mlrun__model-monitoring-application"
 
+    def __str__(self) -> str:
+        return f"{self.KEY}={self.VAL}"
+
 
 class ControllerPolicy:
     BASE_PERIOD = "base_period"
 
 
+class TSDBTarget:
+    V3IO_TSDB = "v3io-tsdb"
+    TDEngine = "tdengine"
+    PROMETHEUS = "prometheus"
+
+
 class HistogramDataDriftApplicationConstants:
     NAME = "histogram-data-drift"
     GENERAL_RESULT_NAME = "general_drift"
+
+
+class PredictionsQueryConstants:
+    DEFAULT_AGGREGATION_GRANULARITY = "10m"
+    INVOCATIONS = "invocations"
+
+
+class SpecialApps:
+    MLRUN_INFRA = "mlrun-infra"

mlrun/common/schemas/model_monitoring/grafana.py

@@ -11,12 +11,18 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-#
 
 from typing import Optional, Union
 
 from pydantic import BaseModel
 
+import mlrun.common.types
+
+
+class GrafanaColumnType(mlrun.common.types.StrEnum):
+    NUMBER = "number"
+    STRING = "string"
+
 
 class GrafanaColumn(BaseModel):
     text: str
@@ -24,13 +30,11 @@ class GrafanaColumn(BaseModel):
 
 
 class GrafanaNumberColumn(GrafanaColumn):
-    text: str
-    type: str = "number"
+    type: str = GrafanaColumnType.NUMBER
 
 
 class GrafanaStringColumn(GrafanaColumn):
-    text: str
-    type: str = "string"
+    type: str = GrafanaColumnType.STRING
 
 
 class GrafanaTable(BaseModel):

mlrun/common/schemas/model_monitoring/model_endpoints.py

@@ -11,16 +11,18 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-#
 
 import enum
 import json
-from typing import Any, Optional
+import re
+from datetime import datetime
+from typing import Any, NamedTuple, Optional
 
 from pydantic import BaseModel, Field, validator
 from pydantic.main import Extra
 
 import mlrun.common.model_monitoring
+import mlrun.common.types
 
 from ..object import ObjectKind, ObjectSpec, ObjectStatus
 from .constants import (
@@ -29,6 +31,8 @@ from .constants import (
     EventKeyMetrics,
     EventLiveStats,
     ModelMonitoringMode,
+    ResultKindApp,
+    ResultStatusApp,
 )
 
 
@@ -100,6 +104,7 @@ class ModelEndpointSpec(ObjectSpec):
         )
 
     @validator("monitor_configuration")
+    @classmethod
     def set_name(cls, monitor_configuration):
         return monitor_configuration or {
             EventFieldType.DRIFT_DETECTED_THRESHOLD: (
@@ -111,6 +116,7 @@ class ModelEndpointSpec(ObjectSpec):
         }
 
     @validator("model_uri")
+    @classmethod
     def validate_model_uri(cls, model_uri):
         """Validate that the model uri includes the required prefix"""
         prefix, uri = mlrun.datastore.parse_store_uri(model_uri)
@@ -292,6 +298,84 @@ class ModelEndpointList(BaseModel):
     endpoints: list[ModelEndpoint] = []
 
 
+class ModelEndpointMonitoringMetricType(mlrun.common.types.StrEnum):
+    RESULT = "result"
+    METRIC = "metric"
+
+
+class ModelEndpointMonitoringMetric(BaseModel):
+    project: str
+    app: str
+    type: ModelEndpointMonitoringMetricType
+    name: str
+    full_name: str
+
+
+def _compose_full_name(
+    *,
+    project: str,
+    app: str,
+    name: str,
+    type: ModelEndpointMonitoringMetricType = ModelEndpointMonitoringMetricType.RESULT,
+) -> str:
+    return ".".join([project, app, type, name])
+
+
+_FQN_PART_PATTERN = r"[a-zA-Z0-9_-]+"
+_FQN_PATTERN = (
+    rf"^(?P<project>{_FQN_PART_PATTERN})\."
+    rf"(?P<app>{_FQN_PART_PATTERN})\."
+    rf"(?P<type>{ModelEndpointMonitoringMetricType.RESULT}|{ModelEndpointMonitoringMetricType.METRIC})\."
+    rf"(?P<name>{_FQN_PART_PATTERN})$"
+)
+_FQN_REGEX = re.compile(_FQN_PATTERN)
+
+
+def _parse_metric_fqn_to_monitoring_metric(fqn: str) -> ModelEndpointMonitoringMetric:
+    match = _FQN_REGEX.fullmatch(fqn)
+    if match is None:
+        raise ValueError("The fully qualified name is not in the expected format")
+    return ModelEndpointMonitoringMetric.parse_obj(
+        match.groupdict() | {"full_name": fqn}
+    )
+
+
+class _MetricPoint(NamedTuple):
+    timestamp: datetime
+    value: float
+
+
+class _ResultPoint(NamedTuple):
+    timestamp: datetime
+    value: float
+    status: ResultStatusApp
+
+
+class _ModelEndpointMonitoringMetricValuesBase(BaseModel):
+    full_name: str
+    type: ModelEndpointMonitoringMetricType
+    data: bool
+
+
+class ModelEndpointMonitoringMetricValues(_ModelEndpointMonitoringMetricValuesBase):
+    type: ModelEndpointMonitoringMetricType = ModelEndpointMonitoringMetricType.METRIC
+    values: list[_MetricPoint]
+    data: bool = True
+
+
+class ModelEndpointMonitoringResultValues(_ModelEndpointMonitoringMetricValuesBase):
+    type: ModelEndpointMonitoringMetricType = ModelEndpointMonitoringMetricType.RESULT
+    result_kind: ResultKindApp
+    values: list[_ResultPoint]
+    data: bool = True
+
+
+class ModelEndpointMonitoringMetricNoData(_ModelEndpointMonitoringMetricValuesBase):
+    full_name: str
+    type: ModelEndpointMonitoringMetricType
+    data: bool = False
+
+
 def _mapping_attributes(
     base_model: BaseModel,
     flattened_dictionary: dict,

mlrun/common/schemas/pipeline.py

@@ -16,15 +16,6 @@ import typing
 
 import pydantic
 
-import mlrun.common.types
-
-
-class PipelinesFormat(mlrun.common.types.StrEnum):
-    full = "full"
-    metadata_only = "metadata_only"
-    summary = "summary"
-    name_only = "name_only"
-
 
 class PipelinesPagination(str):
     default_page_size = 20

mlrun/common/schemas/project.py

@@ -23,16 +23,6 @@ from .common import ImageBuilder
 from .object import ObjectKind, ObjectStatus
 
 
-class ProjectsFormat(mlrun.common.types.StrEnum):
-    full = "full"
-    name_only = "name_only"
-    # minimal format removes large fields from the response (e.g. functions, workflows, artifacts)
-    # and is used for faster response times (in the UI)
-    minimal = "minimal"
-    # internal - allowed only in follower mode, only for the leader for upgrade purposes
-    leader = "leader"
-
-
 class ProjectMetadata(pydantic.BaseModel):
     name: str
     created: typing.Optional[datetime.datetime] = None
@@ -113,7 +103,11 @@ class ProjectSummary(pydantic.BaseModel):
     runs_completed_recent_count: int
     runs_failed_recent_count: int
     runs_running_count: int
-    schedules_count: int
+    distinct_schedules_count: int
+    distinct_scheduled_jobs_pending_count: int
+    distinct_scheduled_pipelines_pending_count: int
+    pipelines_completed_recent_count: typing.Optional[int] = None
+    pipelines_failed_recent_count: typing.Optional[int] = None
     pipelines_running_count: typing.Optional[int] = None
 
 

mlrun/common/types.py

@@ -29,3 +29,4 @@ class StrEnum(str, enum.Enum):
 class HTTPMethod(StrEnum):
     GET = "GET"
     POST = "POST"
+    DELETE = "DELETE"

mlrun/config.py

@@ -37,6 +37,7 @@ import dotenv
 import semver
 import yaml
 
+import mlrun.common.constants
 import mlrun.common.schemas
 import mlrun.errors
 
@@ -87,7 +88,7 @@ default_config = {
     "mpijob_crd_version": "",  # mpijob crd version (e.g: "v1alpha1". must be in: mlrun.runtime.MPIJobCRDVersions)
     "ipython_widget": True,
     "log_level": "INFO",
-    # log formatter (options: human | json)
+    # log formatter (options: human | human_extended | json)
     "log_formatter": "human",
     "submit_timeout": "180",  # timeout when submitting a new k8s resource
     # runtimes cleanup interval in seconds
@@ -228,10 +229,17 @@ default_config = {
                     "executing": "24h",
                 }
             },
+            # When the module is reloaded, the maximum depth recursion configuration for the recursive reload
+            # function is used to prevent infinite loop
+            "reload_max_recursion_depth": 100,
         },
         "databricks": {
             "artifact_directory_path": "/mlrun_databricks_runtime/artifacts_dictionaries"
         },
+        "application": {
+            "default_sidecar_internal_port": 8050,
+            "default_authentication_mode": "accessKey",
+        },
     },
     # TODO: function defaults should be moved to the function spec config above
     "function_defaults": {
@@ -361,12 +369,12 @@ default_config = {
             #                  is set to ClusterIP
             #  ---------------------------------------------------------------------
             # Note: adding a mode requires special handling on
-            # - mlrun.runtimes.constants.NuclioIngressAddTemplatedIngressModes
+            # - mlrun.common.runtimes.constants.NuclioIngressAddTemplatedIngressModes
             # - mlrun.runtimes.nuclio.function.enrich_function_with_ingress
             "add_templated_ingress_host_mode": "never",
             "explicit_ack": "enabled",
             # size of serving spec to move to config maps
-            "serving_spec_env_cutoff": 4096,
+            "serving_spec_env_cutoff": 0,
         },
         "logs": {
             "decode": {
@@ -503,6 +511,7 @@ default_config = {
             "default": "v3io:///users/pipelines/{project}/model-endpoints/{kind}",
             "user_space": "v3io:///projects/{project}/model-endpoints/{kind}",
             "stream": "",
+            "monitoring_application": "v3io:///users/pipelines/{project}/monitoring-apps/",
         },
         # Offline storage path can be either relative or a full path. This path is used for general offline data
         # storage such as the parquet file which is generated from the monitoring stream function for the drift analysis
@@ -516,6 +525,9 @@ default_config = {
         # See mlrun.model_monitoring.db.stores.ObjectStoreFactory for available options
         "store_type": "v3io-nosql",
         "endpoint_store_connection": "",
+        # See mlrun.model_monitoring.db.tsdb.ObjectTSDBFactory for available options
+        "tsdb_connector_type": "v3io-tsdb",
+        "tsdb_connection": "",
     },
     "secret_stores": {
         # Use only in testing scenarios (such as integration tests) to avoid using k8s for secrets (will use in-memory
@@ -554,7 +566,7 @@ default_config = {
             "nosql": "v3io:///projects/{project}/FeatureStore/{name}/nosql",
             # "authority" is optional and generalizes [userinfo "@"] host [":" port]
             "redisnosql": "redis://{authority}/projects/{project}/FeatureStore/{name}/nosql",
-            "dsnosql": "ds://{ds_profile_name}/projects/{project}/FeatureStore/{name}/nosql",
+            "dsnosql": "ds://{ds_profile_name}/projects/{project}/FeatureStore/{name}/{kind}",
         },
         "default_targets": "parquet,nosql",
         "default_job_image": "mlrun/mlrun",
@@ -692,7 +704,10 @@ default_config = {
     "grafana_url": "",
     "alerts": {
         # supported modes: "enabled", "disabled".
-        "mode": "disabled"
+        "mode": "enabled",
+        # maximum number of alerts we allow to be configured.
+        # user will get an error when exceeding this
+        "max_allowed": 1000,
     },
     "auth_with_client_id": {
         "enabled": False,
@@ -797,6 +812,7 @@ class Config:
     ):
         """
         decodes and loads the config attribute to expected type
+
         :param attribute_path: the path in the default_config e.g. preemptible_nodes.node_selector
         :param expected_type: the object type valid values are : `dict`, `list` etc...
         :return: the expected type instance
@@ -959,6 +975,10 @@ class Config:
         self.httpdb.clusterization.chief.url = chief_api_url
         return self.httpdb.clusterization.chief.url
 
+    @staticmethod
+    def internal_labels():
+        return mlrun.common.constants.MLRunInternalLabels.all()
+
     @staticmethod
     def get_storage_auto_mount_params():
         auto_mount_params = {}
@@ -1088,6 +1108,7 @@ class Config:
         target: str = "online",
         artifact_path: str = None,
         function_name: str = None,
+        **kwargs,
     ) -> typing.Union[str, list[str]]:
         """Get the full path from the configuration based on the provided project and kind.
 
@@ -1114,7 +1135,7 @@ class Config:
             )
             if store_prefix_dict.get(kind):
                 # Target exist in store prefix and has a valid string value
-                return store_prefix_dict[kind].format(project=project)
+                return store_prefix_dict[kind].format(project=project, **kwargs)
 
             if (
                 function_name
@@ -1399,14 +1420,14 @@ def read_env(env=None, prefix=env_prefix):
     if log_formatter_name := config.get("log_formatter"):
         import mlrun.utils.logger
 
-        log_formatter = mlrun.utils.create_formatter_instance(
+        log_formatter = mlrun.utils.resolve_formatter_by_kind(
             mlrun.utils.FormatterKinds(log_formatter_name)
         )
         current_handler = mlrun.utils.logger.get_handler("default")
         current_formatter_name = current_handler.formatter.__class__.__name__
-        desired_formatter_name = log_formatter.__class__.__name__
+        desired_formatter_name = log_formatter.__name__
         if current_formatter_name != desired_formatter_name:
-            current_handler.setFormatter(log_formatter)
+            current_handler.setFormatter(log_formatter())
 
     # The default function pod resource values are of type str; however, when reading from environment variable numbers,
     # it converts them to type int if contains only number, so we want to convert them to str.

mlrun/data_types/to_pandas.py

@@ -65,10 +65,10 @@ def toPandas(spark_df):
                 msg = (
                     "toPandas attempted Arrow optimization because "
                     "'spark.sql.execution.arrow.pyspark.enabled' is set to true; however, "
-                    "failed by the reason below:\n  %s\n"
+                    f"failed by the reason below:\n  {e}\n"
                     "Attempting non-optimization as "
                     "'spark.sql.execution.arrow.pyspark.fallback.enabled' is set to "
-                    "true." % str(e)
+                    "true."
                 )
                 warnings.warn(msg)
                 use_arrow = False
@@ -78,7 +78,7 @@ def toPandas(spark_df):
                     "'spark.sql.execution.arrow.pyspark.enabled' is set to true, but has "
                     "reached the error below and will not continue because automatic fallback "
                     "with 'spark.sql.execution.arrow.pyspark.fallback.enabled' has been set to "
-                    "false.\n  %s" % str(e)
+                    f"false.\n  {e}"
                 )
                 warnings.warn(msg)
                 raise
@@ -144,7 +144,7 @@ def toPandas(spark_df):
                     "reached the error below and can not continue. Note that "
                     "'spark.sql.execution.arrow.pyspark.fallback.enabled' does not have an "
                     "effect on failures in the middle of "
-                    "computation.\n  %s" % str(e)
+                    f"computation.\n  {e}"
                 )
                 warnings.warn(msg)
                 raise
@@ -154,10 +154,10 @@ def toPandas(spark_df):
     column_counter = Counter(spark_df.columns)
 
     dtype = [None] * len(spark_df.schema)
-    for fieldIdx, field in enumerate(spark_df.schema):
+    for field_idx, field in enumerate(spark_df.schema):
         # For duplicate column name, we use `iloc` to access it.
         if column_counter[field.name] > 1:
-            pandas_col = pdf.iloc[:, fieldIdx]
+            pandas_col = pdf.iloc[:, field_idx]
         else:
             pandas_col = pdf[field.name]
 
@@ -171,12 +171,12 @@ def toPandas(spark_df):
             and field.nullable
             and pandas_col.isnull().any()
         ):
-            dtype[fieldIdx] = pandas_type
+            dtype[field_idx] = pandas_type
         # Ensure we fall back to nullable numpy types, even when whole column is null:
         if isinstance(field.dataType, IntegralType) and pandas_col.isnull().any():
-            dtype[fieldIdx] = np.float64
+            dtype[field_idx] = np.float64
         if isinstance(field.dataType, BooleanType) and pandas_col.isnull().any():
-            dtype[fieldIdx] = object
+            dtype[field_idx] = object
 
     df = pd.DataFrame()
     for index, t in enumerate(dtype):

mlrun/datastore/base.py

@@ -179,11 +179,23 @@ class DataStore:
         return {}
 
     @staticmethod
-    def _parquet_reader(df_module, url, file_system, time_column, start_time, end_time):
+    def _parquet_reader(
+        df_module,
+        url,
+        file_system,
+        time_column,
+        start_time,
+        end_time,
+        additional_filters,
+    ):
         from storey.utils import find_filters, find_partitions
 
         def set_filters(
-            partitions_time_attributes, start_time_inner, end_time_inner, kwargs
+            partitions_time_attributes,
+            start_time_inner,
+            end_time_inner,
+            filters_inner,
+            kwargs,
         ):
             filters = []
             find_filters(
@@ -193,20 +205,23 @@ class DataStore:
                 filters,
                 time_column,
             )
+            if filters and filters_inner:
+                filters[0] += filters_inner
+
             kwargs["filters"] = filters
 
         def reader(*args, **kwargs):
-            if start_time or end_time:
-                if time_column is None:
-                    raise mlrun.errors.MLRunInvalidArgumentError(
-                        "When providing start_time or end_time, must provide time_column"
-                    )
-
+            if time_column is None and (start_time or end_time):
+                raise mlrun.errors.MLRunInvalidArgumentError(
+                    "When providing start_time or end_time, must provide time_column"
+                )
+            if start_time or end_time or additional_filters:
                 partitions_time_attributes = find_partitions(url, file_system)
                 set_filters(
                     partitions_time_attributes,
                     start_time,
                     end_time,
+                    additional_filters,
                     kwargs,
                 )
                 try:
@@ -217,6 +232,7 @@ class DataStore:
                     ):
                         raise ex
 
+                    # TODO: fix timezone issue (ML-6308)
                     if start_time.tzinfo:
                         start_time_inner = start_time.replace(tzinfo=None)
                         end_time_inner = end_time.replace(tzinfo=None)
@@ -228,6 +244,7 @@ class DataStore:
                         partitions_time_attributes,
                         start_time_inner,
                         end_time_inner,
+                        additional_filters,
                         kwargs,
                     )
                     return df_module.read_parquet(*args, **kwargs)
@@ -246,6 +263,7 @@ class DataStore:
         start_time=None,
         end_time=None,
         time_column=None,
+        additional_filters=None,
         **kwargs,
     ):
         df_module = df_module or pd
@@ -310,7 +328,13 @@ class DataStore:
                 kwargs["columns"] = columns
 
             reader = self._parquet_reader(
-                df_module, url, file_system, time_column, start_time, end_time
+                df_module,
+                url,
+                file_system,
+                time_column,
+                start_time,
+                end_time,
+                additional_filters,
             )
 
         elif file_url.endswith(".json") or format == "json":
@@ -539,6 +563,7 @@ class DataItem:
         time_column=None,
         start_time=None,
         end_time=None,
+        additional_filters=None,
         **kwargs,
     ):
         """return a dataframe object (generated from the dataitem).
@@ -550,6 +575,12 @@ class DataItem:
         :param end_time:    filters out data after this time
         :param time_column: Store timestamp_key will be used if None.
                             The results will be filtered by this column and start_time & end_time.
+        :param additional_filters: List of additional_filter conditions as tuples.
+                                    Each tuple should be in the format (column_name, operator, value).
+                                    Supported operators: "=", ">=", "<=", ">", "<".
+                                    Example: [("Product", "=", "Computer")]
+                                    For all supported filters, please see:
+                                    https://arrow.apache.org/docs/python/generated/pyarrow.parquet.ParquetDataset.html
         """
         df = self._store.as_df(
             self._url,
@@ -560,6 +591,7 @@ class DataItem:
             time_column=time_column,
             start_time=start_time,
             end_time=end_time,
+            additional_filters=additional_filters,
             **kwargs,
         )
         return df