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

mlrun/db/nopdb.py

@@ -16,6 +16,9 @@
 import datetime
 from typing import Optional, Union
 
+import mlrun.alerts
+import mlrun.common.formatters
+import mlrun.common.runtimes.constants
 import mlrun.common.schemas
 import mlrun.errors
 
@@ -79,7 +82,10 @@ class NopDB(RunDBInterface):
         uid: Optional[Union[str, list[str]]] = None,
         project: Optional[str] = None,
         labels: Optional[Union[str, list[str]]] = None,
-        state: Optional[str] = None,
+        state: Optional[
+            mlrun.common.runtimes.constants.RunStates
+        ] = None,  # Backward compatibility
+        states: Optional[list[mlrun.common.runtimes.constants.RunStates]] = None,
         sort: bool = True,
         last: int = 0,
         iter: bool = False,
@@ -128,7 +134,18 @@ class NopDB(RunDBInterface):
     ):
         pass
 
-    def del_artifact(self, key, tag="", project="", tree=None, uid=None):
+    def del_artifact(
+        self,
+        key,
+        tag="",
+        project="",
+        tree=None,
+        uid=None,
+        deletion_strategy: mlrun.common.schemas.artifact.ArtifactsDeletionStrategies = (
+            mlrun.common.schemas.artifact.ArtifactsDeletionStrategies.metadata_only
+        ),
+        secrets: dict = None,
+    ):
         pass
 
     def del_artifacts(self, name="", project="", tag="", labels=None):
@@ -196,7 +213,7 @@ class NopDB(RunDBInterface):
     def list_projects(
         self,
         owner: str = None,
-        format_: mlrun.common.schemas.ProjectsFormat = mlrun.common.schemas.ProjectsFormat.name_only,
+        format_: mlrun.common.formatters.ProjectFormat = mlrun.common.formatters.ProjectFormat.name_only,
         labels: list[str] = None,
         state: mlrun.common.schemas.ProjectState = None,
     ) -> mlrun.common.schemas.ProjectsOutput:
@@ -351,8 +368,8 @@ class NopDB(RunDBInterface):
         namespace: str = None,
         timeout: int = 30,
         format_: Union[
-            str, mlrun.common.schemas.PipelinesFormat
-        ] = mlrun.common.schemas.PipelinesFormat.summary,
+            str, mlrun.common.formatters.PipelineFormat
+        ] = mlrun.common.formatters.PipelineFormat.summary,
         project: str = None,
     ):
         pass
@@ -365,8 +382,8 @@ class NopDB(RunDBInterface):
         page_token: str = "",
         filter_: str = "",
         format_: Union[
-            str, mlrun.common.schemas.PipelinesFormat
-        ] = mlrun.common.schemas.PipelinesFormat.metadata_only,
+            str, mlrun.common.formatters.PipelineFormat
+        ] = mlrun.common.formatters.PipelineFormat.metadata_only,
         page_size: int = None,
     ) -> mlrun.common.schemas.PipelinesOutput:
         pass
@@ -508,8 +525,11 @@ class NopDB(RunDBInterface):
 
     def store_api_gateway(
         self,
-        project: str,
-        api_gateway: mlrun.runtimes.nuclio.APIGateway,
+        api_gateway: Union[
+            mlrun.common.schemas.APIGateway,
+            mlrun.runtimes.nuclio.api_gateway.APIGateway,
+        ],
+        project: str = None,
     ) -> mlrun.common.schemas.APIGateway:
         pass
 
@@ -658,6 +678,22 @@ class NopDB(RunDBInterface):
     ) -> None:
         pass
 
+    def disable_model_monitoring(
+        self,
+        project: str,
+        delete_resources: bool = True,
+        delete_stream_function: bool = False,
+        delete_histogram_data_drift_app: bool = True,
+        delete_user_applications: bool = False,
+        user_application_list: list[str] = None,
+    ) -> bool:
+        pass
+
+    def delete_model_monitoring_function(
+        self, project: str, functions: list[str]
+    ) -> bool:
+        pass
+
     def deploy_histogram_data_drift_app(
         self, project: str, image: str = "mlrun/mlrun"
     ) -> None:
@@ -671,7 +707,7 @@ class NopDB(RunDBInterface):
     def store_alert_config(
         self,
         alert_name: str,
-        alert_data: Union[dict, mlrun.common.schemas.AlertConfig],
+        alert_data: Union[dict, mlrun.alerts.alert.AlertConfig],
         project="",
     ):
         pass
@@ -687,3 +723,9 @@ class NopDB(RunDBInterface):
 
     def reset_alert_config(self, alert_name: str, project=""):
         pass
+
+    def get_alert_template(self, template_name: str):
+        pass
+
+    def list_alert_templates(self):
+        pass

mlrun/errors.py

@@ -155,6 +155,10 @@ class MLRunNotFoundError(MLRunHTTPStatusError):
     error_status_code = HTTPStatus.NOT_FOUND.value
 
 
+class MLRunPaginationEndOfResultsError(MLRunNotFoundError):
+    pass
+
+
 class MLRunBadRequestError(MLRunHTTPStatusError):
     error_status_code = HTTPStatus.BAD_REQUEST.value
 
@@ -183,6 +187,10 @@ class MLRunInternalServerError(MLRunHTTPStatusError):
     error_status_code = HTTPStatus.INTERNAL_SERVER_ERROR.value
 
 
+class MLRunNotImplementedServerError(MLRunHTTPStatusError):
+    error_status_code = HTTPStatus.NOT_IMPLEMENTED.value
+
+
 class MLRunServiceUnavailableError(MLRunHTTPStatusError):
     error_status_code = HTTPStatus.SERVICE_UNAVAILABLE.value
 
@@ -234,4 +242,7 @@ STATUS_ERRORS = {
     HTTPStatus.PRECONDITION_FAILED.value: MLRunPreconditionFailedError,
     HTTPStatus.INTERNAL_SERVER_ERROR.value: MLRunInternalServerError,
     HTTPStatus.SERVICE_UNAVAILABLE.value: MLRunServiceUnavailableError,
+    HTTPStatus.NOT_IMPLEMENTED.value: MLRunNotImplementedServerError,
 }
+
+EXPECTED_ERRORS = (MLRunPaginationEndOfResultsError,)

mlrun/execution.py

@@ -22,6 +22,7 @@ import yaml
 from dateutil import parser
 
 import mlrun
+import mlrun.common.constants as mlrun_constants
 from mlrun.artifacts import ModelArtifact
 from mlrun.datastore.store_resources import get_store_resource
 from mlrun.errors import MLRunInvalidArgumentError
@@ -110,6 +111,7 @@ class MLClientCtx:
 
         self._project_object = None
         self._allow_empty_resources = None
+        self._reset_on_run = None
 
     def __enter__(self):
         return self
@@ -129,7 +131,9 @@ class MLClientCtx:
     @property
     def tag(self):
         """Run tag (uid or workflow id if exists)"""
-        return self._labels.get("workflow") or self._uid
+        return (
+            self._labels.get(mlrun_constants.MLRunInternalLabels.workflow) or self._uid
+        )
 
     @property
     def state(self):
@@ -329,8 +333,10 @@ class MLClientCtx:
             "uri": uri,
             "owner": get_in(self._labels, "owner"),
         }
-        if "workflow" in self._labels:
-            resp["workflow"] = self._labels["workflow"]
+        if mlrun_constants.MLRunInternalLabels.workflow in self._labels:
+            resp[mlrun_constants.MLRunInternalLabels.workflow] = self._labels[
+                mlrun_constants.MLRunInternalLabels.workflow
+            ]
         return resp
 
     @classmethod
@@ -384,6 +390,7 @@ class MLClientCtx:
             self._state_thresholds = spec.get(
                 "state_thresholds", self._state_thresholds
             )
+            self._reset_on_run = spec.get("reset_on_run", self._reset_on_run)
 
         self._init_dbs(rundb)
 
@@ -396,7 +403,7 @@ class MLClientCtx:
                         self._set_input(k, v)
 
         if host and not is_api:
-            self.set_label("host", host)
+            self.set_label(mlrun_constants.MLRunInternalLabels.host, host)
 
         start = get_in(attrs, "status.start_time")
         if start:
@@ -990,10 +997,15 @@ class MLClientCtx:
         # If it's a OpenMPI job, get the global rank and compare to the logging rank (worker) set in MLRun's
         # configuration:
         labels = self.labels
-        if "host" in labels and labels.get("kind", "job") == "mpijob":
+        if (
+            mlrun_constants.MLRunInternalLabels.host in labels
+            and labels.get(mlrun_constants.MLRunInternalLabels.kind, "job") == "mpijob"
+        ):
             # The host (pod name) of each worker is created by k8s, and by default it uses the rank number as the id in
             # the following template: ...-worker-<rank>
-            rank = int(labels["host"].rsplit("-", 1)[1])
+            rank = int(
+                labels[mlrun_constants.MLRunInternalLabels.host].rsplit("-", 1)[1]
+            )
             return rank == mlrun.mlconf.packagers.logging_worker
 
         # Single worker is always the logging worker:
@@ -1029,9 +1041,14 @@ class MLClientCtx:
             "status.last_update": to_date_str(self._last_update),
         }
 
-        # completion of runs is not decided by the execution as there may be
-        # multiple executions for a single run (e.g. mpi)
-        if self._state != "completed":
+        # Completion of runs is decided by the API runs monitoring as there may be
+        # multiple executions for a single run (e.g. mpi).
+        # For kinds that are not monitored by the API (local) we allow changing the state.
+        run_kind = self.labels.get(mlrun_constants.MLRunInternalLabels.kind, "")
+        if (
+            mlrun.runtimes.RuntimeKinds.is_local_runtime(run_kind)
+            or self._state != "completed"
+        ):
             struct["status.state"] = self._state
 
         if self.is_logging_worker():

mlrun/feature_store/__init__.py

@@ -19,7 +19,6 @@ __all__ = [
     "get_online_feature_service",
     "ingest",
     "preview",
-    "deploy_ingestion_service",
     "deploy_ingestion_service_v2",
     "delete_feature_set",
     "delete_feature_vector",
@@ -41,7 +40,6 @@ from ..features import Entity, Feature
 from .api import (
     delete_feature_set,
     delete_feature_vector,
-    deploy_ingestion_service,
     deploy_ingestion_service_v2,
     get_feature_set,
     get_feature_vector,

mlrun/feature_store/api.py

@@ -113,6 +113,7 @@ def get_offline_features(
     order_by: Union[str, list[str]] = None,
     spark_service: str = None,
     timestamp_for_filtering: Union[str, dict[str, str]] = None,
+    additional_filters: list = None,
 ):
     """retrieve offline feature vector results
 
@@ -175,6 +176,13 @@ def get_offline_features(
                                     By default, the filter executes on the timestamp_key of each feature set.
                                     Note: the time filtering is performed on each feature set before the
                                     merge process using start_time and end_time params.
+    :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
+
 
     """
     return _get_offline_features(
@@ -194,6 +202,7 @@ def get_offline_features(
         order_by,
         spark_service,
         timestamp_for_filtering,
+        additional_filters,
     )
 
 
@@ -214,6 +223,7 @@ def _get_offline_features(
     order_by: Union[str, list[str]] = None,
     spark_service: str = None,
     timestamp_for_filtering: Union[str, dict[str, str]] = None,
+    additional_filters=None,
 ) -> Union[OfflineVectorResponse, RemoteVectorResponse]:
     if entity_rows is None and entity_timestamp_column is not None:
         raise mlrun.errors.MLRunInvalidArgumentError(
@@ -252,6 +262,7 @@ def _get_offline_features(
             start_time=start_time,
             end_time=end_time,
             timestamp_for_filtering=timestamp_for_filtering,
+            additional_filters=additional_filters,
         )
 
     merger = merger_engine(feature_vector, **(engine_args or {}))
@@ -267,6 +278,7 @@ def _get_offline_features(
         update_stats=update_stats,
         query=query,
         order_by=order_by,
+        additional_filters=additional_filters,
     )
 
 
@@ -1005,53 +1017,6 @@ def _deploy_ingestion_service_v2(
     return function.deploy(), function
 
 
-@deprecated(
-    version="1.5.0",
-    reason="'deploy_ingestion_service' will be removed in 1.7.0, use 'deploy_ingestion_service_v2' instead",
-    category=FutureWarning,
-)
-def deploy_ingestion_service(
-    featureset: Union[FeatureSet, str],
-    source: DataSource = None,
-    targets: list[DataTargetBase] = None,
-    name: str = None,
-    run_config: RunConfig = None,
-    verbose=False,
-) -> str:
-    """Start real-time ingestion service using nuclio function
-
-    Deploy a real-time function implementing feature ingestion pipeline
-    the source maps to Nuclio event triggers (http, kafka, v3io stream, etc.)
-
-    the `run_config` parameter allow specifying the function and job configuration,
-    see: :py:class:`~mlrun.feature_store.RunConfig`
-
-    example::
-
-        source = HTTPSource()
-        func = mlrun.code_to_function("ingest", kind="serving").apply(mount_v3io())
-        config = RunConfig(function=func)
-        my_set.deploy_ingestion_service(source, run_config=config)
-
-    :param featureset:    feature set object or uri
-    :param source:        data source object describing the online or offline source
-    :param targets:       list of data target objects
-    :param name:          name for the job/function
-    :param run_config:    service runtime configuration (function object/uri, resources, etc..)
-    :param verbose:       verbose log
-
-    :return: URL to access the deployed ingestion service
-    """
-    endpoint, _ = featureset.deploy_ingestion_service(
-        source=source,
-        targets=targets,
-        name=name,
-        run_config=run_config,
-        verbose=verbose,
-    )
-    return endpoint
-
-
 def _ingest_with_spark(
     spark=None,
     featureset: Union[FeatureSet, str] = None,

mlrun/feature_store/feature_set.py

@@ -917,6 +917,7 @@ class FeatureSet(ModelObj):
         start_time=None,
         end_time=None,
         time_column=None,
+        additional_filters=None,
         **kwargs,
     ):
         """return featureset (offline) data as dataframe
@@ -928,6 +929,12 @@ class FeatureSet(ModelObj):
         :param end_time:     filter by end time
         :param time_column:  specify the time column name in the file
         :param kwargs:       additional reader (csv, parquet, ..) args
+        :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
         :return: DataFrame
         """
         entities = list(self.spec.entities.keys())
@@ -946,6 +953,7 @@ class FeatureSet(ModelObj):
                 start_time=start_time,
                 end_time=end_time,
                 time_field=time_column,
+                additional_filters=additional_filters,
                 **kwargs,
             )
             # to_dataframe() can sometimes return an iterator of dataframes instead of one dataframe
@@ -965,6 +973,7 @@ class FeatureSet(ModelObj):
             start_time=start_time,
             end_time=end_time,
             time_column=time_column,
+            additional_filters=additional_filters,
             **kwargs,
         )
         return result

mlrun/feature_store/feature_vector.py

@@ -741,6 +741,7 @@ class FeatureVector(ModelObj):
         order_by: Union[str, list[str]] = None,
         spark_service: str = None,
         timestamp_for_filtering: Union[str, dict[str, str]] = None,
+        additional_filters: list = None,
     ):
         """retrieve offline feature vector results
 
@@ -797,6 +798,12 @@ class FeatureVector(ModelObj):
                                         By default, the filter executes on the timestamp_key of each feature set.
                                         Note: the time filtering is performed on each feature set before the
                                         merge process using start_time and end_time params.
+        :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
 
         """
 
@@ -817,6 +824,7 @@ class FeatureVector(ModelObj):
             order_by,
             spark_service,
             timestamp_for_filtering,
+            additional_filters,
         )
 
     def get_online_feature_service(

mlrun/feature_store/ingestion.py

@@ -17,6 +17,7 @@ import uuid
 import pandas as pd
 
 import mlrun
+import mlrun.common.constants as mlrun_constants
 from mlrun.datastore.sources import get_source_from_dict, get_source_step
 from mlrun.datastore.targets import (
     add_target_steps,
@@ -263,13 +264,13 @@ def run_ingestion_job(name, featureset, run_config, schedule=None, spark_service
         out_path=featureset.spec.output_path,
     )
     task.spec.secret_sources = run_config.secret_sources
-    task.set_label("job-type", "feature-ingest").set_label(
-        "feature-set", featureset.uri
-    )
+    task.set_label(
+        mlrun_constants.MLRunInternalLabels.job_type, "feature-ingest"
+    ).set_label("feature-set", featureset.uri)
     if run_config.owner:
-        task.set_label("owner", run_config.owner).set_label(
-            "v3io_user", run_config.owner
-        )
+        task.set_label(
+            mlrun_constants.MLRunInternalLabels.owner, run_config.owner
+        ).set_label(mlrun_constants.MLRunInternalLabels.v3io_user, run_config.owner)
 
     # set run UID and save in the feature set status (linking the features et to the job)
     task.metadata.uid = uuid.uuid4().hex

mlrun/feature_store/retrieval/base.py

@@ -88,6 +88,7 @@ class BaseMerger(abc.ABC):
         update_stats=None,
         query=None,
         order_by=None,
+        additional_filters=None,
     ):
         self._target = target
 
@@ -134,6 +135,7 @@ class BaseMerger(abc.ABC):
             timestamp_for_filtering=timestamp_for_filtering,
             query=query,
             order_by=order_by,
+            additional_filters=additional_filters,
         )
 
     def _write_to_offline_target(self, timestamp_key=None):
@@ -186,6 +188,7 @@ class BaseMerger(abc.ABC):
         timestamp_for_filtering=None,
         query=None,
         order_by=None,
+        additional_filters=None,
     ):
         self._create_engine_env()
 
@@ -212,7 +215,7 @@ class BaseMerger(abc.ABC):
             feature_sets.append(None)
             join_types.append(None)
 
-        filtered = False
+        timestamp_filtered = False
         for step in join_graph.steps:
             name = step.right_feature_set_name
             feature_set = feature_set_objects[name]
@@ -250,7 +253,7 @@ class BaseMerger(abc.ABC):
             if self._drop_indexes:
                 self._append_drop_column(time_column)
             if (start_time or end_time) and time_column:
-                filtered = True
+                timestamp_filtered = True
 
             df = self._get_engine_df(
                 feature_set,
@@ -259,6 +262,7 @@ class BaseMerger(abc.ABC):
                 start_time if time_column else None,
                 end_time if time_column else None,
                 time_column,
+                additional_filters,
             )
 
             fs_entities_and_timestamp = list(feature_set.spec.entities.keys())
@@ -302,8 +306,8 @@ class BaseMerger(abc.ABC):
                     new_columns.append((column, alias))
             self._update_alias(dictionary={name: alias for name, alias in new_columns})
 
-        # None of the feature sets was filtered as required
-        if not filtered and (start_time or end_time):
+        # None of the feature sets was timestamp filtered as required
+        if not timestamp_filtered and (start_time or end_time):
             raise mlrun.errors.MLRunRuntimeError(
                 "start_time and end_time can only be provided in conjunction with "
                 "a timestamp column, or when the at least one feature_set has a timestamp key"
@@ -755,6 +759,7 @@ class BaseMerger(abc.ABC):
         start_time: typing.Union[str, datetime] = None,
         end_time: typing.Union[str, datetime] = None,
         time_column: typing.Optional[str] = None,
+        additional_filters=None,
     ):
         """
         Return the feature_set data frame according to the args

mlrun/feature_store/retrieval/conversion.py

@@ -79,10 +79,10 @@ class PandasConversionMixin:
                     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
@@ -92,7 +92,7 @@ class PandasConversionMixin:
                         "'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
@@ -158,7 +158,7 @@ class PandasConversionMixin:
                         "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
@@ -168,10 +168,10 @@ class PandasConversionMixin:
         column_counter = Counter(self.columns)
 
         dtype = [None] * len(self.schema)
-        for fieldIdx, field in enumerate(self.schema):
+        for field_idx, field in enumerate(self.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]
 
@@ -187,12 +187,12 @@ class PandasConversionMixin:
                 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/feature_store/retrieval/dask_merger.py

@@ -145,6 +145,7 @@ class DaskFeatureMerger(BaseMerger):
         start_time=None,
         end_time=None,
         time_column=None,
+        additional_filters=None,
     ):
         import dask.dataframe as dd
 
@@ -155,6 +156,7 @@ class DaskFeatureMerger(BaseMerger):
             end_time=end_time,
             time_column=time_column,
             index=False,
+            additional_filters=additional_filters,
         )
 
         return self._reset_index(df).persist()

mlrun/feature_store/retrieval/job.py

@@ -15,6 +15,7 @@
 import uuid
 
 import mlrun
+import mlrun.common.constants as mlrun_constants
 from mlrun.config import config as mlconf
 from mlrun.model import DataTargetBase, new_task
 from mlrun.runtimes.function_reference import FunctionReference
@@ -42,6 +43,7 @@ def run_merge_job(
     start_time=None,
     end_time=None,
     timestamp_for_filtering=None,
+    additional_filters=None,
 ):
     name = vector.metadata.name
     if not target or not hasattr(target, "to_dict"):
@@ -116,11 +118,14 @@ def run_merge_job(
             "end_time": end_time,
             "timestamp_for_filtering": timestamp_for_filtering,
             "engine_args": engine_args,
+            "additional_filters": additional_filters,
         },
         inputs={"entity_rows": entity_rows} if entity_rows is not None else {},
     )
     task.spec.secret_sources = run_config.secret_sources
-    task.set_label("job-type", "feature-merge").set_label("feature-vector", vector.uri)
+    task.set_label(
+        mlrun_constants.MLRunInternalLabels.job_type, "feature-merge"
+    ).set_label(mlrun_constants.MLRunInternalLabels.feature_vector, vector.uri)
     task.metadata.uid = uuid.uuid4().hex
     vector.status.run_uri = task.metadata.uid
     vector.save()
@@ -196,7 +201,8 @@ import mlrun.feature_store.retrieval
 from mlrun.datastore.targets import get_target_driver
 def merge_handler(context, vector_uri, target, entity_rows=None, 
                   entity_timestamp_column=None, drop_columns=None, with_indexes=None, query=None,
-                  engine_args=None, order_by=None, start_time=None, end_time=None, timestamp_for_filtering=None):
+                  engine_args=None, order_by=None, start_time=None, end_time=None, timestamp_for_filtering=None,
+                  additional_filters=None):
     vector = context.get_store_resource(vector_uri)
     store_target = get_target_driver(target, vector)
     if entity_rows:
@@ -206,7 +212,7 @@ def merge_handler(context, vector_uri, target, entity_rows=None,
     merger = mlrun.feature_store.retrieval.{{{engine}}}(vector, **(engine_args or {}))
     merger.start(entity_rows, entity_timestamp_column, store_target, drop_columns, with_indexes=with_indexes, 
                  query=query, order_by=order_by, start_time=start_time, end_time=end_time,
-                 timestamp_for_filtering=timestamp_for_filtering)
+                 timestamp_for_filtering=timestamp_for_filtering, additional_filters=additional_filters)
 
     target = vector.status.targets[store_target.name].to_dict()
     context.log_result('feature_vector', vector.uri)

mlrun/feature_store/retrieval/local_merger.py

@@ -114,12 +114,14 @@ class LocalFeatureMerger(BaseMerger):
         start_time=None,
         end_time=None,
         time_column=None,
+        additional_filters=None,
     ):
         df = feature_set.to_dataframe(
             columns=column_names,
             start_time=start_time,
             end_time=end_time,
             time_column=time_column,
+            additional_filters=additional_filters,
         )
         if df.index.names[0]:
             df.reset_index(inplace=True)