mlrun 1.7.0rc13__py3-none-any.whl → 1.7.0rc15__py3-none-any.whl

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/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

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

@@ -42,6 +42,7 @@ 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"):
@@ -116,6 +117,7 @@ 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 {},
     )

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)

mlrun/feature_store/retrieval/spark_merger.py

@@ -225,7 +225,12 @@ class SparkFeatureMerger(BaseMerger):
         start_time=None,
         end_time=None,
         time_column=None,
+        additional_filters=None,
     ):
+        mlrun.utils.helpers.additional_filters_warning(
+            additional_filters, self.__class__
+        )
+
         source_kwargs = {}
         if feature_set.spec.passthrough:
             if not feature_set.spec.source:

mlrun/frameworks/_dl_common/loggers/tensorboard_logger.py

@@ -547,9 +547,9 @@ class TensorboardLogger(Logger, Generic[DLTypes.WeightType]):
                     "inputs",
                     "parameters",
                 ]:
-                    text += "\n  * **{}**: {}".format(
-                        property_name.capitalize(),
-                        self._markdown_print(value=property_value, tabs=2),
+                    text += (
+                        f"\n  * **{property_name.capitalize()}**: "
+                        f"{self._markdown_print(value=property_value, tabs=2)}"
                     )
         else:
             for property_name, property_value in self._extract_epoch_results().items():
@@ -614,13 +614,8 @@ class TensorboardLogger(Logger, Generic[DLTypes.WeightType]):
         :return: The generated link.
         """
         return (
-            '<a href="{}/{}/{}/jobs/monitor/{}/overview" target="_blank">{}</a>'.format(
-                config.resolve_ui_url(),
-                config.ui.projects_prefix,
-                context.project,
-                context.uid,
-                link_text,
-            )
+            f'<a href="{config.resolve_ui_url()}/{config.ui.projects_prefix}/{context.project}'
+            f'/jobs/monitor/{context.uid}/overview" target="_blank">{link_text}</a>'
         )
 
     @staticmethod

mlrun/kfpops.py

@@ -33,7 +33,6 @@ from .utils import (
     get_in,
     get_workflow_url,
     is_ipython,
-    is_legacy_artifact,
     logger,
     run_keys,
     version,
@@ -121,14 +120,8 @@ def get_kfp_outputs(artifacts, labels, project):
     outputs = []
     out_dict = {}
     for output in artifacts:
-        if is_legacy_artifact(output):
-            key = output["key"]
-            # The spec in a legacy artifact is contained in the main object, so using this assignment saves us a lot
-            # of if/else in the rest of this function.
-            output_spec = output
-        else:
-            key = output.get("metadata")["key"]
-            output_spec = output.get("spec", {})
+        key = output.get("metadata")["key"]
+        output_spec = output.get("spec", {})
 
         target = output_spec.get("target_path", "")
         target = output_spec.get("inline", target)
@@ -655,7 +648,9 @@ def add_default_env(k8s_client, cop):
             )
         )
 
-    auth_env_var = mlrun.runtimes.constants.FunctionEnvironmentVariables.auth_session
+    auth_env_var = (
+        mlrun.common.runtimes.constants.FunctionEnvironmentVariables.auth_session
+    )
     if auth_env_var in os.environ or "V3IO_ACCESS_KEY" in os.environ:
         cop.container.add_env_variable(
             k8s_client.V1EnvVar(

mlrun/launcher/base.py

@@ -403,7 +403,7 @@ class BaseLauncher(abc.ABC):
             )
             if (
                 run.status.state
-                in mlrun.runtimes.constants.RunStates.error_and_abortion_states()
+                in mlrun.common.runtimes.constants.RunStates.error_and_abortion_states()
             ):
                 if runtime._is_remote and not runtime.is_child:
                     logger.error(

mlrun/launcher/client.py

@@ -71,7 +71,7 @@ class ClientBaseLauncher(launcher.BaseLauncher, abc.ABC):
     ):
         run.metadata.labels["kind"] = runtime.kind
         mlrun.runtimes.utils.enrich_run_labels(
-            run.metadata.labels, [mlrun.runtimes.constants.RunLabels.owner]
+            run.metadata.labels, [mlrun.common.runtimes.constants.RunLabels.owner]
         )
         if run.spec.output_path:
             run.spec.output_path = run.spec.output_path.replace(

mlrun/lists.py

@@ -21,7 +21,7 @@ import mlrun.frameworks
 from .artifacts import Artifact, dict_to_artifact
 from .config import config
 from .render import artifacts_to_html, runs_to_html
-from .utils import flatten, get_artifact_target, get_in, is_legacy_artifact
+from .utils import flatten, get_artifact_target, get_in
 
 list_header = [
     "project",
@@ -184,7 +184,7 @@ class ArtifactList(list):
             "uri": ["uri", "uri"],
         }
         for artifact in self:
-            fields_index = 0 if is_legacy_artifact(artifact) else 1
+            fields_index = 1
             row = [get_in(artifact, v[fields_index], "") for k, v in head.items()]
             artifact_uri = dict_to_artifact(artifact).uri
             last_index = len(row) - 1

mlrun/model.py

@@ -33,7 +33,6 @@ from .utils import (
     dict_to_json,
     dict_to_yaml,
     get_artifact_target,
-    is_legacy_artifact,
     logger,
     template_artifact_path,
 )
@@ -766,6 +765,11 @@ class RunMetadata(ModelObj):
     def iteration(self, iteration):
         self._iteration = iteration
 
+    def is_workflow_runner(self):
+        if not self.labels:
+            return False
+        return self.labels.get("job-type", "") == "workflow-runner"
+
 
 class HyperParamStrategies:
     grid = "grid"
@@ -1218,6 +1222,19 @@ class RunStatus(ModelObj):
         self.reason = reason
         self.notifications = notifications or {}
 
+    def is_failed(self) -> Optional[bool]:
+        """
+        This method returns whether a run has failed.
+        Returns none if state has yet to be defined. callee is responsible for handling None.
+        (e.g wait for state to be defined)
+        """
+        if not self.state:
+            return None
+        return self.state.casefold() in [
+            mlrun.run.RunStatuses.failed.casefold(),
+            mlrun.run.RunStatuses.error.casefold(),
+        ]
+
 
 class RunTemplate(ModelObj):
     """Run template"""
@@ -1417,11 +1434,14 @@ class RunObject(RunTemplate):
             unknown_error = ""
             if (
                 self.status.state
-                in mlrun.runtimes.constants.RunStates.abortion_states()
+                in mlrun.common.runtimes.constants.RunStates.abortion_states()
             ):
                 unknown_error = "Run was aborted"
 
-            elif self.status.state in mlrun.runtimes.constants.RunStates.error_states():
+            elif (
+                self.status.state
+                in mlrun.common.runtimes.constants.RunStates.error_states()
+            ):
                 unknown_error = "Unknown error"
 
             return (
@@ -1459,7 +1479,7 @@ class RunObject(RunTemplate):
             outputs = {k: v for k, v in self.status.results.items()}
         if self.status.artifacts:
             for a in self.status.artifacts:
-                key = a["key"] if is_legacy_artifact(a) else a["metadata"]["key"]
+                key = a["metadata"]["key"]
                 outputs[key] = get_artifact_target(a, self.metadata.project)
         return outputs
 
@@ -1502,7 +1522,10 @@ class RunObject(RunTemplate):
 
     def state(self):
         """current run state"""
-        if self.status.state in mlrun.runtimes.constants.RunStates.terminal_states():
+        if (
+            self.status.state
+            in mlrun.common.runtimes.constants.RunStates.terminal_states()
+        ):
             return self.status.state
         self.refresh()
         return self.status.state or "unknown"
@@ -1564,7 +1587,7 @@ class RunObject(RunTemplate):
         last_pull_log_time = None
         logs_enabled = show_logs is not False
         state = self.state()
-        if state not in mlrun.runtimes.constants.RunStates.terminal_states():
+        if state not in mlrun.common.runtimes.constants.RunStates.terminal_states():
             logger.info(
                 f"run {self.metadata.name} is not completed yet, waiting for it to complete",
                 current_state=state,
@@ -1574,7 +1597,8 @@ class RunObject(RunTemplate):
             if (
                 logs_enabled
                 and logs_interval
-                and state not in mlrun.runtimes.constants.RunStates.terminal_states()
+                and state
+                not in mlrun.common.runtimes.constants.RunStates.terminal_states()
                 and (
                     last_pull_log_time is None
                     or (datetime.now() - last_pull_log_time).seconds > logs_interval
@@ -1583,7 +1607,7 @@ class RunObject(RunTemplate):
                 last_pull_log_time = datetime.now()
                 state, offset = self.logs(watch=False, offset=offset)
 
-            if state in mlrun.runtimes.constants.RunStates.terminal_states():
+            if state in mlrun.common.runtimes.constants.RunStates.terminal_states():
                 if logs_enabled and logs_interval:
                     self.logs(watch=False, offset=offset)
                 break
@@ -1595,7 +1619,10 @@ class RunObject(RunTemplate):
                 )
         if logs_enabled and not logs_interval:
             self.logs(watch=False)
-        if raise_on_failure and state != mlrun.runtimes.constants.RunStates.completed:
+        if (
+            raise_on_failure
+            and state != mlrun.common.runtimes.constants.RunStates.completed
+        ):
             raise mlrun.errors.MLRunRuntimeError(
                 f"Task {self.metadata.name} did not complete (state={state})"
             )

mlrun/model_monitoring/api.py

@@ -22,9 +22,10 @@ import pandas as pd
 
 import mlrun.artifacts
 import mlrun.common.helpers
-import mlrun.common.schemas.model_monitoring.constants as mm_consts
+import mlrun.common.schemas.model_monitoring.constants as mm_constants
 import mlrun.feature_store
 import mlrun.model_monitoring.application
+import mlrun.model_monitoring.applications as mm_app
 import mlrun.serving
 from mlrun.data_types.infer import InferOptions, get_df_stats
 from mlrun.utils import datetime_now, logger
@@ -48,7 +49,7 @@ def get_or_create_model_endpoint(
     sample_set_statistics: dict[str, typing.Any] = None,
     drift_threshold: float = None,
     possible_drift_threshold: float = None,
-    monitoring_mode: mm_consts.ModelMonitoringMode = mm_consts.ModelMonitoringMode.disabled,
+    monitoring_mode: mm_constants.ModelMonitoringMode = mm_constants.ModelMonitoringMode.disabled,
     db_session=None,
 ) -> ModelEndpoint:
     """
@@ -128,7 +129,7 @@ def record_results(
     context: typing.Optional[mlrun.MLClientCtx] = None,
     infer_results_df: typing.Optional[pd.DataFrame] = None,
     sample_set_statistics: typing.Optional[dict[str, typing.Any]] = None,
-    monitoring_mode: mm_consts.ModelMonitoringMode = mm_consts.ModelMonitoringMode.enabled,
+    monitoring_mode: mm_constants.ModelMonitoringMode = mm_constants.ModelMonitoringMode.enabled,
     # Deprecated arguments:
     drift_threshold: typing.Optional[float] = None,
     possible_drift_threshold: typing.Optional[float] = None,
@@ -282,7 +283,7 @@ def _model_endpoint_validations(
     # drift and possible drift thresholds
     if drift_threshold:
         current_drift_threshold = model_endpoint.spec.monitor_configuration.get(
-            mm_consts.EventFieldType.DRIFT_DETECTED_THRESHOLD,
+            mm_constants.EventFieldType.DRIFT_DETECTED_THRESHOLD,
             mlrun.mlconf.model_endpoint_monitoring.drift_thresholds.default.drift_detected,
         )
         if current_drift_threshold != drift_threshold:
@@ -293,7 +294,7 @@ def _model_endpoint_validations(
 
     if possible_drift_threshold:
         current_possible_drift_threshold = model_endpoint.spec.monitor_configuration.get(
-            mm_consts.EventFieldType.POSSIBLE_DRIFT_THRESHOLD,
+            mm_constants.EventFieldType.POSSIBLE_DRIFT_THRESHOLD,
             mlrun.mlconf.model_endpoint_monitoring.drift_thresholds.default.possible_drift,
         )
         if current_possible_drift_threshold != possible_drift_threshold:
@@ -332,14 +333,14 @@ def write_monitoring_df(
         )
 
     # Modify the DataFrame to the required structure that will be used later by the monitoring batch job
-    if mm_consts.EventFieldType.TIMESTAMP not in infer_results_df.columns:
+    if mm_constants.EventFieldType.TIMESTAMP not in infer_results_df.columns:
         # Initialize timestamp column with the current time
-        infer_results_df[mm_consts.EventFieldType.TIMESTAMP] = infer_datetime
+        infer_results_df[mm_constants.EventFieldType.TIMESTAMP] = infer_datetime
 
     # `endpoint_id` is the monitoring feature set entity and therefore it should be defined as the df index before
     # the ingest process
-    infer_results_df[mm_consts.EventFieldType.ENDPOINT_ID] = endpoint_id
-    infer_results_df.set_index(mm_consts.EventFieldType.ENDPOINT_ID, inplace=True)
+    infer_results_df[mm_constants.EventFieldType.ENDPOINT_ID] = endpoint_id
+    infer_results_df.set_index(mm_constants.EventFieldType.ENDPOINT_ID, inplace=True)
 
     monitoring_feature_set.ingest(source=infer_results_df, overwrite=False)
 
@@ -355,7 +356,7 @@ def _generate_model_endpoint(
     sample_set_statistics: dict[str, typing.Any],
     drift_threshold: float,
     possible_drift_threshold: float,
-    monitoring_mode: mm_consts.ModelMonitoringMode = mm_consts.ModelMonitoringMode.disabled,
+    monitoring_mode: mm_constants.ModelMonitoringMode = mm_constants.ModelMonitoringMode.disabled,
 ) -> ModelEndpoint:
     """
     Write a new model endpoint record.
@@ -394,11 +395,11 @@ def _generate_model_endpoint(
     model_endpoint.spec.model_class = "drift-analysis"
     if drift_threshold:
         model_endpoint.spec.monitor_configuration[
-            mm_consts.EventFieldType.DRIFT_DETECTED_THRESHOLD
+            mm_constants.EventFieldType.DRIFT_DETECTED_THRESHOLD
         ] = drift_threshold
     if possible_drift_threshold:
         model_endpoint.spec.monitor_configuration[
-            mm_consts.EventFieldType.POSSIBLE_DRIFT_THRESHOLD
+            mm_constants.EventFieldType.POSSIBLE_DRIFT_THRESHOLD
         ] = possible_drift_threshold
 
     model_endpoint.spec.monitoring_mode = monitoring_mode
@@ -589,7 +590,10 @@ def _create_model_monitoring_function_base(
     project: str,
     func: typing.Union[str, None] = None,
     application_class: typing.Union[
-        str, mlrun.model_monitoring.application.ModelMonitoringApplicationBase, None
+        str,
+        mlrun.model_monitoring.application.ModelMonitoringApplicationBase,
+        mm_app.ModelMonitoringApplicationBaseV2,
+        None,
     ] = None,
     name: typing.Optional[str] = None,
     image: typing.Optional[str] = None,
@@ -602,6 +606,20 @@ def _create_model_monitoring_function_base(
     Note: this is an internal API only.
     This function does not set the labels or mounts v3io.
     """
+    if isinstance(
+        application_class,
+        mlrun.model_monitoring.application.ModelMonitoringApplicationBase,
+    ):
+        warnings.warn(
+            "The `ModelMonitoringApplicationBase` class is deprecated from version 1.7.0, "
+            "please use `ModelMonitoringApplicationBaseV2`. It will be removed in 1.9.0.",
+            FutureWarning,
+        )
+    if name in mm_constants.MonitoringFunctionNames.list():
+        raise mlrun.errors.MLRunInvalidArgumentError(
+            f"An application cannot have the following names: "
+            f"{mm_constants.MonitoringFunctionNames.list()}"
+        )
     if func is None:
         func = ""
     func_obj = typing.cast(
@@ -618,14 +636,19 @@ def _create_model_monitoring_function_base(
         ),
     )
     graph = func_obj.set_topology(mlrun.serving.states.StepKinds.flow)
+    prepare_step = graph.to(
+        class_name="mlrun.model_monitoring.applications._application_steps._PrepareMonitoringEvent",
+        name="PrepareMonitoringEvent",
+        application_name=name,
+    )
     if isinstance(application_class, str):
-        first_step = graph.to(class_name=application_class, **application_kwargs)
+        app_step = prepare_step.to(class_name=application_class, **application_kwargs)
     else:
-        first_step = graph.to(class_name=application_class)
-    first_step.to(
-        class_name="mlrun.model_monitoring.application.PushToMonitoringWriter",
+        app_step = prepare_step.to(class_name=application_class)
+    app_step.to(
+        class_name="mlrun.model_monitoring.applications._application_steps._PushToMonitoringWriter",
         name="PushToMonitoringWriter",
         project=project,
-        writer_application_name=mm_consts.MonitoringFunctionNames.WRITER,
+        writer_application_name=mm_constants.MonitoringFunctionNames.WRITER,
     ).respond()
     return func_obj