qwak-core 0.4.378__py3-none-any.whl → 0.5.12__py3-none-any.whl

_qwak_proto/qwak/projects/projects_pb2.py

@@ -11,12 +11,12 @@ from google.protobuf.internal import builder as _builder
 _sym_db = _symbol_database.Default()
 
 
+from google.protobuf import timestamp_pb2 as google_dot_protobuf_dot_timestamp__pb2
 from _qwak_proto.qwak.models import models_pb2 as qwak_dot_models_dot_models__pb2
 from _qwak_proto.qwak.projects import jfrog_project_spec_pb2 as qwak_dot_projects_dot_jfrog__project__spec__pb2
-from google.protobuf import timestamp_pb2 as google_dot_protobuf_dot_timestamp__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\x1cqwak/projects/projects.proto\x12\x18qwak.projects.management\x1a\x18qwak/models/models.proto\x1a&qwak/projects/jfrog_project_spec.proto\x1a\x1fgoogle/protobuf/timestamp.proto\"\xad\x03\n\x0eProjectRequest\x12P\n\x16\x63reate_project_request\x18\x01 \x01(\x0b\x32..qwak.projects.management.CreateProjectRequestH\x00\x12P\n\x16\x64\x65lete_project_request\x18\x02 \x01(\x0b\x32..qwak.projects.management.DeleteProjectRequestH\x00\x12P\n\x16update_project_request\x18\x03 \x01(\x0b\x32..qwak.projects.management.UpdateProjectRequestH\x00\x12J\n\x13get_project_request\x18\x04 \x01(\x0b\x32+.qwak.projects.management.GetProjectRequestH\x00\x12N\n\x15list_projects_request\x18\x05 \x01(\x0b\x32-.qwak.projects.management.ListProjectsRequestH\x00\x42\t\n\x07request\"\x91\x01\n\x14\x43reateProjectRequest\x12\x14\n\x0cproject_name\x18\x01 \x01(\t\x12\x1b\n\x13project_description\x18\x02 \x01(\t\x12\x46\n\njfrog_spec\x18\x03 \x01(\x0b\x32\x32.qwak.projects.management.ModelRepositoryJFrogSpec\"O\n\x15\x43reateProjectResponse\x12\x36\n\x07project\x18\x01 \x01(\x0b\x32%.qwak.projects.management.ProjectSpec\"\x15\n\x13ListProjectsRequest\"O\n\x14ListProjectsResponse\x12\x37\n\x08projects\x18\x01 \x03(\x0b\x32%.qwak.projects.management.ProjectSpec\"=\n\x11GetProjectRequest\x12\x12\n\nproject_id\x18\x01 \x01(\t\x12\x14\n\x0cproject_name\x18\x02 \x01(\t\"H\n\x12GetProjectResponse\x12\x32\n\x07project\x18\x01 \x01(\x0b\x32!.qwak.projects.management.Project\"*\n\x14\x44\x65leteProjectRequest\x12\x12\n\nproject_id\x18\x01 \x01(\t\"%\n\x15\x44\x65leteProjectResponse\x12\x0c\n\x04info\x18\x01 \x01(\t\"{\n\x14UpdateProjectRequest\x12\x12\n\nproject_id\x18\x01 \x01(\t\x12O\n\x13project_spec_config\x18\x02 \x01(\x0b\x32\x32.qwak.projects.management.ProjectSpecConfiguration\"T\n\x15UpdateProjectResponse\x12;\n\x0cproject_spec\x18\x01 \x01(\x0b\x32%.qwak.projects.management.ProjectSpec\"\xac\x01\n\x07Project\x12\x33\n\x04spec\x18\x01 \x01(\x0b\x32%.qwak.projects.management.ProjectSpec\x12\x31\n\x06models\x18\x02 \x03(\x0b\x32\x1d.qwak.models.management.ModelB\x02\x18\x01\x12\x39\n\rmodels_briefs\x18\x03 \x03(\x0b\x32\".qwak.models.management.ModelBrief\"\xeb\x03\n\x0bProjectSpec\x12\x12\n\nproject_id\x18\x01 \x01(\t\x12\x14\n\x0cproject_name\x18\x02 \x01(\t\x12\x1b\n\x13project_description\x18\x03 \x01(\t\x12\x44\n\x0eproject_status\x18\x04 \x01(\x0e\x32,.qwak.projects.management.ProjectSpec.Status\x12.\n\ncreated_at\x18\x05 \x01(\x0b\x32\x1a.google.protobuf.Timestamp\x12\x12\n\ncreated_by\x18\x06 \x01(\t\x12\x34\n\x10last_modified_at\x18\x07 \x01(\x0b\x32\x1a.google.protobuf.Timestamp\x12\x18\n\x10last_modified_by\x18\x08 \x01(\t\x12\x14\n\x0cmodels_count\x18\t \x01(\x05\x12\x15\n\rmodels_active\x18\n \x01(\x05\x12N\n\x0ejfrog_settings\x18\x0b \x01(\x0b\x32\x36.qwak.projects.management.ModelRepositoryJFrogSettings\">\n\x06Status\x12\x0b\n\x07INVALID\x10\x00\x12\x0c\n\x08\x44ISABLED\x10\x01\x12\r\n\tSUSPENDED\x10\x02\x12\n\n\x06\x41\x43TIVE\x10\x03\"M\n\x18ProjectSpecConfiguration\x12\x14\n\x0cproject_name\x18\x01 \x01(\t\x12\x1b\n\x13project_description\x18\x02 \x01(\t\"\xb1\x02\n\x1cModelRepositoryJFrogSettings\x12S\n\x11pull_image_secret\x18\x01 \x01(\x0b\x32\x38.qwak.projects.management.ModelRepositoryPullImageSecret\x12[\n\x15jfrog_project_details\x18\x02 \x01(\x0b\x32<.qwak.projects.management.ModelRepositoryJFrogProjectDetails\x12_\n\x1ajfrog_repositories_details\x18\x03 \x01(\x0b\x32;.qwak.projects.management.ModelRepositoryArtifactoryDetails\"@\n\x1eModelRepositoryPullImageSecret\x12\x1e\n\x16pull_image_secret_name\x18\x01 \x01(\t\"?\n\"ModelRepositoryJFrogProjectDetails\x12\x19\n\x11jfrog_project_key\x18\x01 \x01(\t\"\xb7\x02\n!ModelRepositoryArtifactoryDetails\x12[\n\x1b\x61rtifact_repository_details\x18\x01 \x01(\x0b\x32\x36.qwak.projects.management.ArtifactoryRepositoryDetails\x12Z\n\x1a\x64\x61taset_repository_details\x18\x02 \x01(\x0b\x32\x36.qwak.projects.management.ArtifactoryRepositoryDetails\x12Y\n\x19\x64ocker_repository_details\x18\x03 \x01(\x0b\x32\x36.qwak.projects.management.ArtifactoryRepositoryDetails\"6\n\x1c\x41rtifactoryRepositoryDetails\x12\x16\n\x0erepository_key\x18\x01 \x01(\t2\xc9\x04\n\x19ProjectsManagementService\x12p\n\rCreateProject\x12..qwak.projects.management.CreateProjectRequest\x1a/.qwak.projects.management.CreateProjectResponse\x12m\n\x0cListProjects\x12-.qwak.projects.management.ListProjectsRequest\x1a..qwak.projects.management.ListProjectsResponse\x12g\n\nGetProject\x12+.qwak.projects.management.GetProjectRequest\x1a,.qwak.projects.management.GetProjectResponse\x12p\n\rDeleteProject\x12..qwak.projects.management.DeleteProjectRequest\x1a/.qwak.projects.management.DeleteProjectResponse\x12p\n\rUpdateProject\x12..qwak.projects.management.UpdateProjectRequest\x1a/.qwak.projects.management.UpdateProjectResponseB\'\n#com.qwak.ai.management.projects.apiP\x01\x62\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\x1cqwak/projects/projects.proto\x12\x18qwak.projects.management\x1a\x1fgoogle/protobuf/timestamp.proto\x1a\x18qwak/models/models.proto\x1a&qwak/projects/jfrog_project_spec.proto\"\xad\x03\n\x0eProjectRequest\x12P\n\x16\x63reate_project_request\x18\x01 \x01(\x0b\x32..qwak.projects.management.CreateProjectRequestH\x00\x12P\n\x16\x64\x65lete_project_request\x18\x02 \x01(\x0b\x32..qwak.projects.management.DeleteProjectRequestH\x00\x12P\n\x16update_project_request\x18\x03 \x01(\x0b\x32..qwak.projects.management.UpdateProjectRequestH\x00\x12J\n\x13get_project_request\x18\x04 \x01(\x0b\x32+.qwak.projects.management.GetProjectRequestH\x00\x12N\n\x15list_projects_request\x18\x05 \x01(\x0b\x32-.qwak.projects.management.ListProjectsRequestH\x00\x42\t\n\x07request\"\x91\x01\n\x14\x43reateProjectRequest\x12\x14\n\x0cproject_name\x18\x01 \x01(\t\x12\x1b\n\x13project_description\x18\x02 \x01(\t\x12\x46\n\njfrog_spec\x18\x03 \x01(\x0b\x32\x32.qwak.projects.management.ModelRepositoryJFrogSpec\"O\n\x15\x43reateProjectResponse\x12\x36\n\x07project\x18\x01 \x01(\x0b\x32%.qwak.projects.management.ProjectSpec\"\x15\n\x13ListProjectsRequest\"O\n\x14ListProjectsResponse\x12\x37\n\x08projects\x18\x01 \x03(\x0b\x32%.qwak.projects.management.ProjectSpec\"=\n\x11GetProjectRequest\x12\x12\n\nproject_id\x18\x01 \x01(\t\x12\x14\n\x0cproject_name\x18\x02 \x01(\t\"H\n\x12GetProjectResponse\x12\x32\n\x07project\x18\x01 \x01(\x0b\x32!.qwak.projects.management.Project\"*\n\x14\x44\x65leteProjectRequest\x12\x12\n\nproject_id\x18\x01 \x01(\t\"%\n\x15\x44\x65leteProjectResponse\x12\x0c\n\x04info\x18\x01 \x01(\t\"{\n\x14UpdateProjectRequest\x12\x12\n\nproject_id\x18\x01 \x01(\t\x12O\n\x13project_spec_config\x18\x02 \x01(\x0b\x32\x32.qwak.projects.management.ProjectSpecConfiguration\"T\n\x15UpdateProjectResponse\x12;\n\x0cproject_spec\x18\x01 \x01(\x0b\x32%.qwak.projects.management.ProjectSpec\"\xac\x01\n\x07Project\x12\x33\n\x04spec\x18\x01 \x01(\x0b\x32%.qwak.projects.management.ProjectSpec\x12\x31\n\x06models\x18\x02 \x03(\x0b\x32\x1d.qwak.models.management.ModelB\x02\x18\x01\x12\x39\n\rmodels_briefs\x18\x03 \x03(\x0b\x32\".qwak.models.management.ModelBrief\"\xeb\x03\n\x0bProjectSpec\x12\x12\n\nproject_id\x18\x01 \x01(\t\x12\x14\n\x0cproject_name\x18\x02 \x01(\t\x12\x1b\n\x13project_description\x18\x03 \x01(\t\x12\x44\n\x0eproject_status\x18\x04 \x01(\x0e\x32,.qwak.projects.management.ProjectSpec.Status\x12.\n\ncreated_at\x18\x05 \x01(\x0b\x32\x1a.google.protobuf.Timestamp\x12\x12\n\ncreated_by\x18\x06 \x01(\t\x12\x34\n\x10last_modified_at\x18\x07 \x01(\x0b\x32\x1a.google.protobuf.Timestamp\x12\x18\n\x10last_modified_by\x18\x08 \x01(\t\x12\x14\n\x0cmodels_count\x18\t \x01(\x05\x12\x15\n\rmodels_active\x18\n \x01(\x05\x12N\n\x0ejfrog_settings\x18\x0b \x01(\x0b\x32\x36.qwak.projects.management.ModelRepositoryJFrogSettings\">\n\x06Status\x12\x0b\n\x07INVALID\x10\x00\x12\x0c\n\x08\x44ISABLED\x10\x01\x12\r\n\tSUSPENDED\x10\x02\x12\n\n\x06\x41\x43TIVE\x10\x03\"Q\n\x18ProjectSpecConfiguration\x12\x18\n\x0cproject_name\x18\x01 \x01(\tB\x02\x18\x01\x12\x1b\n\x13project_description\x18\x02 \x01(\t\"\xb1\x02\n\x1cModelRepositoryJFrogSettings\x12S\n\x11pull_image_secret\x18\x01 \x01(\x0b\x32\x38.qwak.projects.management.ModelRepositoryPullImageSecret\x12[\n\x15jfrog_project_details\x18\x02 \x01(\x0b\x32<.qwak.projects.management.ModelRepositoryJFrogProjectDetails\x12_\n\x1ajfrog_repositories_details\x18\x03 \x01(\x0b\x32;.qwak.projects.management.ModelRepositoryArtifactoryDetails\"@\n\x1eModelRepositoryPullImageSecret\x12\x1e\n\x16pull_image_secret_name\x18\x01 \x01(\t\"?\n\"ModelRepositoryJFrogProjectDetails\x12\x19\n\x11jfrog_project_key\x18\x01 \x01(\t\"\xb7\x02\n!ModelRepositoryArtifactoryDetails\x12[\n\x1b\x61rtifact_repository_details\x18\x01 \x01(\x0b\x32\x36.qwak.projects.management.ArtifactoryRepositoryDetails\x12Z\n\x1a\x64\x61taset_repository_details\x18\x02 \x01(\x0b\x32\x36.qwak.projects.management.ArtifactoryRepositoryDetails\x12Y\n\x19\x64ocker_repository_details\x18\x03 \x01(\x0b\x32\x36.qwak.projects.management.ArtifactoryRepositoryDetails\"6\n\x1c\x41rtifactoryRepositoryDetails\x12\x16\n\x0erepository_key\x18\x01 \x01(\t2\xc9\x04\n\x19ProjectsManagementService\x12p\n\rCreateProject\x12..qwak.projects.management.CreateProjectRequest\x1a/.qwak.projects.management.CreateProjectResponse\x12m\n\x0cListProjects\x12-.qwak.projects.management.ListProjectsRequest\x1a..qwak.projects.management.ListProjectsResponse\x12g\n\nGetProject\x12+.qwak.projects.management.GetProjectRequest\x1a,.qwak.projects.management.GetProjectResponse\x12p\n\rDeleteProject\x12..qwak.projects.management.DeleteProjectRequest\x1a/.qwak.projects.management.DeleteProjectResponse\x12p\n\rUpdateProject\x12..qwak.projects.management.UpdateProjectRequest\x1a/.qwak.projects.management.UpdateProjectResponseB\'\n#com.qwak.ai.management.projects.apiP\x01\x62\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
@@ -27,6 +27,8 @@ if _descriptor._USE_C_DESCRIPTORS == False:
   DESCRIPTOR._serialized_options = b'\n#com.qwak.ai.management.projects.apiP\001'
   _PROJECT.fields_by_name['models']._options = None
   _PROJECT.fields_by_name['models']._serialized_options = b'\030\001'
+  _PROJECTSPECCONFIGURATION.fields_by_name['project_name']._options = None
+  _PROJECTSPECCONFIGURATION.fields_by_name['project_name']._serialized_options = b'\030\001'
   _globals['_PROJECTREQUEST']._serialized_start=158
   _globals['_PROJECTREQUEST']._serialized_end=587
   _globals['_CREATEPROJECTREQUEST']._serialized_start=590
@@ -56,17 +58,17 @@ if _descriptor._USE_C_DESCRIPTORS == False:
   _globals['_PROJECTSPEC_STATUS']._serialized_start=1958
   _globals['_PROJECTSPEC_STATUS']._serialized_end=2020
   _globals['_PROJECTSPECCONFIGURATION']._serialized_start=2022
-  _globals['_PROJECTSPECCONFIGURATION']._serialized_end=2099
-  _globals['_MODELREPOSITORYJFROGSETTINGS']._serialized_start=2102
-  _globals['_MODELREPOSITORYJFROGSETTINGS']._serialized_end=2407
-  _globals['_MODELREPOSITORYPULLIMAGESECRET']._serialized_start=2409
-  _globals['_MODELREPOSITORYPULLIMAGESECRET']._serialized_end=2473
-  _globals['_MODELREPOSITORYJFROGPROJECTDETAILS']._serialized_start=2475
-  _globals['_MODELREPOSITORYJFROGPROJECTDETAILS']._serialized_end=2538
-  _globals['_MODELREPOSITORYARTIFACTORYDETAILS']._serialized_start=2541
-  _globals['_MODELREPOSITORYARTIFACTORYDETAILS']._serialized_end=2852
-  _globals['_ARTIFACTORYREPOSITORYDETAILS']._serialized_start=2854
-  _globals['_ARTIFACTORYREPOSITORYDETAILS']._serialized_end=2908
-  _globals['_PROJECTSMANAGEMENTSERVICE']._serialized_start=2911
-  _globals['_PROJECTSMANAGEMENTSERVICE']._serialized_end=3496
+  _globals['_PROJECTSPECCONFIGURATION']._serialized_end=2103
+  _globals['_MODELREPOSITORYJFROGSETTINGS']._serialized_start=2106
+  _globals['_MODELREPOSITORYJFROGSETTINGS']._serialized_end=2411
+  _globals['_MODELREPOSITORYPULLIMAGESECRET']._serialized_start=2413
+  _globals['_MODELREPOSITORYPULLIMAGESECRET']._serialized_end=2477
+  _globals['_MODELREPOSITORYJFROGPROJECTDETAILS']._serialized_start=2479
+  _globals['_MODELREPOSITORYJFROGPROJECTDETAILS']._serialized_end=2542
+  _globals['_MODELREPOSITORYARTIFACTORYDETAILS']._serialized_start=2545
+  _globals['_MODELREPOSITORYARTIFACTORYDETAILS']._serialized_end=2856
+  _globals['_ARTIFACTORYREPOSITORYDETAILS']._serialized_start=2858
+  _globals['_ARTIFACTORYREPOSITORYDETAILS']._serialized_end=2912
+  _globals['_PROJECTSMANAGEMENTSERVICE']._serialized_start=2915
+  _globals['_PROJECTSMANAGEMENTSERVICE']._serialized_end=3500
 # @@protoc_insertion_point(module_scope)

_qwak_proto/qwak/secret_service/secret_service_pb2.pyi

@@ -81,7 +81,7 @@ class DeleteSecretRequest(google.protobuf.message.Message):
 
     NAME_FIELD_NUMBER: builtins.int
     name: builtins.str
-    """The name of the secret"""
+    """Name of the secret"""
     def __init__(
         self,
         *,

qwak/__init__.py

@@ -1,7 +1,7 @@
 """Top-level package for qwak-core."""
 
 __author__ = "Qwak.ai"
-__version__ = "0.4.378"
+__version__ = "0.5.12"
 
 from qwak.inner.di_configuration import wire_dependencies
 from qwak.model.experiment_tracking import log_metric, log_param

qwak/clients/feature_store/execution_management_client.py

@@ -1,4 +1,7 @@
 from _qwak_proto.qwak.execution.v1.backfill_pb2 import BackfillSpec
+from _qwak_proto.qwak.execution.v1.streaming_aggregation_pb2 import (
+    StreamingAggregationBackfillIngestion,
+)
 from _qwak_proto.qwak.execution.v1.batch_pb2 import BatchIngestion
 from _qwak_proto.qwak.execution.v1.execution_service_pb2 import (
     GetExecutionEntryRequest,
@@ -9,6 +12,8 @@ from _qwak_proto.qwak.execution.v1.execution_service_pb2 import (
     TriggerBackfillResponse,
     TriggerBatchFeaturesetRequest,
     TriggerBatchFeaturesetResponse,
+    TriggerStreamingAggregationBackfillRequest,
+    TriggerStreamingAggregationBackfillResponse,
 )
 from _qwak_proto.qwak.execution.v1.execution_service_pb2_grpc import (
     FeatureStoreExecutionServiceStub,
@@ -29,6 +34,29 @@ class ExecutionManagementClient:
             grpc_channel
         )
 
+    def trigger_streaming_aggregation_backfill(
+        self, backfill_ingestion: StreamingAggregationBackfillIngestion
+    ) -> TriggerStreamingAggregationBackfillResponse:
+        """
+        Receives a configured streaming aggregation backfill proto and triggers a streaming aggregation
+        backfill against the execution manager
+
+        Args:
+            backfill_ingestion (StreamingAggregationBackfillIngestion): A protobuf message
+                containing the backfill specification details
+
+        Returns:
+            TriggerStreamingAggregationBackfillResponse: response object from the execution manager
+        """
+        try:
+            return self._feature_store_execution_service.TriggerStreamingAggregationBackfill(
+                TriggerStreamingAggregationBackfillRequest(backfill=backfill_ingestion)
+            )
+        except RpcError as e:
+            raise QwakException(
+                f"Failed to trigger streaming aggregation backfill job, error encountered {e}"
+            )
+
     def trigger_batch_backfill(
         self, batch_backfill_spec: BackfillSpec
     ) -> TriggerBackfillResponse:

qwak/exceptions/__init__.py

@@ -1,6 +1,7 @@
 from .quiet_error import QuietError
 from .qwak_exception import QwakException
 from .qwak_general_build_exception import QwakGeneralBuildException
+from .qwak_grpc_address_exception import QwakGrpcAddressException
 from .qwak_http_exception import QwakHTTPException
 from .qwak_inference_exception import QwakInferenceException
 from .qwak_load_configuration_exception import LoadConfigurationException

qwak/exceptions/qwak_grpc_address_exception.py

@@ -0,0 +1,9 @@
+from typing import Union
+from urllib.parse import ParseResult
+
+from qwak.exceptions import QwakException
+
+
+class QwakGrpcAddressException(QwakException):
+    def __init__(self, details: str, grpc_address: Union[str, ParseResult]):
+        self.message = f"Not a valid gRPC address: '{grpc_address}'. Details: {details}"

qwak/feature_store/execution/streaming_backfill.py

@@ -0,0 +1,48 @@
+import pathlib
+
+from qwak.clients.feature_store.execution_management_client import (
+    ExecutionManagementClient,
+)
+from qwak.feature_store.feature_sets.streaming_backfill import StreamingBackfill
+
+
+class StreamingAggregationBackfill:
+    def __init__(
+        self,
+        streaming_backfill: StreamingBackfill,
+        source_definition_path: pathlib.Path,
+    ):
+        """
+        Initialize the streaming aggregation backfill executor.
+
+        Args:
+            streaming_backfill (StreamingBackfill): Specification containing the
+                              featureset name, time range, data sources, and transformation
+            source_definition_path (Path): Path to the Python file containing the backfill
+                                   definition. Required for locating UDF artifacts.
+        """
+        self._streaming_backfill = streaming_backfill
+        self._source_definition_path = source_definition_path
+
+    def trigger(self) -> str:
+        """
+        Triggers the streaming aggregation backfill execution.
+
+        Converts the backfill specification to proto format and sends it to
+        the execution manager to start the backfill job.
+
+        Returns:
+            str: The execution ID for tracking the backfill job status
+
+        Raises:
+            QwakException: If the execution manager request fails
+        """
+        backfill_proto = self._streaming_backfill._to_proto(
+            str(self._source_definition_path)
+        )
+
+        execution_client = ExecutionManagementClient()
+        response = execution_client.trigger_streaming_aggregation_backfill(
+            backfill_proto
+        )
+        return response.execution_id

qwak/feature_store/feature_sets/streaming.py

@@ -2,7 +2,7 @@ import collections
 import functools
 import inspect
 from dataclasses import dataclass, field
-from datetime import datetime
+from datetime import datetime, timezone
 from typing import TYPE_CHECKING, List, Optional, Tuple, Union
 
 from _qwak_proto.qwak.feature_store.features.execution_pb2 import (
@@ -21,6 +21,7 @@ from _qwak_proto.qwak.feature_store.sources.streaming_pb2 import (
     StreamingSource,
     StreamingSource as ProtoStreamingSource,
 )
+from google.protobuf.timestamp_pb2 import Timestamp as ProtoTimestamp
 from qwak.clients.feature_store import FeatureRegistryClient
 from qwak.exceptions import QwakException
 from qwak.feature_store._common.artifact_utils import ArtifactSpec, ArtifactsUploader
@@ -34,7 +35,7 @@ from qwak.feature_store.feature_sets.metadata import (
     set_metadata_on_function,
 )
 from qwak.feature_store.feature_sets.streaming_backfill import (
-    BackfillBatchDataSourceSpec,
+    BackfillDataSource,
     StreamingBackfill,
 )
 from qwak.feature_store.feature_sets.transformations import (
@@ -75,6 +76,7 @@ def feature_set(
     key: Optional[str] = None,
     auxiliary_sinks: List[BaseSink] = [],
     repository: Optional[str] = None,
+    backfill_max_timestamp: Optional[datetime] = None,
 ):
     """
     Creates a streaming feature set for the specified entity using the given streaming data sources.
@@ -110,6 +112,11 @@ def feature_set(
     """
 
     def decorator(function):
+        if isinstance(function, StreamingBackfill):
+            raise QwakException(
+                "Backfill can no longer be defined as a decorator on the feature set, it must be triggered after feature set creation."
+            )
+
         user_transformation = function()
         FeaturesetUtils.validate_base_featureset_decorator(
             user_transformation=user_transformation, entity=entity, key=key
@@ -120,10 +127,6 @@ def feature_set(
             offline_scheduling_policy=offline_scheduling_policy,
         )
 
-        streaming_backfill: Optional[StreamingBackfill] = (
-            StreamingBackfill.get_streaming_backfill_from_function(function=function)
-        )
-
         fs_name = name or function.__name__
         streaming_feature_set = StreamingFeatureSet(
             name=fs_name,
@@ -150,7 +153,7 @@ def feature_set(
             online_cluster_template=getattr(
                 function, _ONLINE_CLUSTER_SPEC, ClusterTemplate.SMALL
             ),
-            backfill=streaming_backfill,
+            backfill_max_timestamp=backfill_max_timestamp,
             __instance_module_path__=inspect.stack()[1].filename,
             auxiliary_sinks=auxiliary_sinks,
         )
@@ -197,55 +200,68 @@ def execution_specification(
 @typechecked
 def backfill(
     *,
-    start_date: datetime,
-    end_date: datetime,
-    data_sources: Union[List[str], List[BackfillBatchDataSourceSpec]],
-    backfill_transformation: SparkSqlTransformation,
+    feature_set_name: str,
+    start_date: Optional[datetime],
+    end_date: Optional[datetime],
+    data_sources: Union[List[str], List[BackfillDataSource]],
     backfill_cluster_template: Optional[ClusterTemplate] = ClusterTemplate.SMALL,
 ):
     """
-    Configures optional backfill specification for a streaming featureset. Currently available for streaming
+    Triggers a backfill execution for an existing streaming featureset. Currently available for streaming
     aggregation featuresets only.
 
-    :param start_date: backfill start date
-    :param end_date: backfill end date
-    :param data_sources: a list of dict representations connecting each batch source name to its requested time range
-    :param backfill_transformation: a backfill SQL transformation. Only SQL transformations are supported for backfill
-    :param backfill_cluster_template: an optional cluster specification for the backfill job. Defaults to SMALL.
-
-    Example:
-
-    ... code-block:: python
-
-        @streaming.feature_set(
-            entity="users",
-            data_sources=["users_registration_stream"],
-            timestamp_column_name="reg_date"
-        )
+    Args:
+        feature_set_name (str): Name of the FeatureSet to trigger a backfill for.
+        start_date (datetime): Backfill start date, on Streaming Aggregation Feature Sets,
+            needs to align with the FeatureSet tiles.
+        end_date (datetime): Backfill end date, on Streaming Aggregation Feature Sets,
+            needs to align with the FeatureSet tiles and be smaller than the Feature Set's backfill_max_timestamp.
+        data_sources (list[BackfillDataSource] | list[str]): A list of BackfillDataSource objects containing
+            batch source name and optional time range, or a list of batch source names (with no time range limits).
+        backfill_cluster_template (ClusterTemplate, optional): An optional cluster specification for the backfill job.
+            Defaults to SMALL.
+
+    Examples:
         @streaming.backfill(
-            start_date=start_date=(2022,01,01,0,0,0),
-            end_date=start_date=(2023,09,01,0,0,0),
-            data_sources=[{"batch_backfill_source_name": BackfillSourceRange(start_date=(2023,01,01,0,0,0),
-                                                                             end_date=(2023,08,01,0,0,0))}],
+            feature_set_name="user_streaming_agg_features",
+            start_date=datetime(2022,1,1,0,0,0),
+            end_date=datetime(2023,9,1,0,0,0),
+            data_sources=[BackfillDataSource(data_source_name="backfill_data_source",
+                                             start_datetime=datetime(2023,1,1,0,0,0),
+                                             end_datetime=datetime(2023,8,1,0,0,0))],
             backfill_cluster_template=ClusterTemplate.SMALL
-            backfill_transformation=SparkSqlTransformation("SELECT user_id, reg_country, reg_date FROM backfill_data_source")
         )
-        def user_streaming_features():
-            return SparkSqlTransformation("SELECT user_id, reg_country, reg_date FROM data_source")
+        def backfill_transformation():
+            return SparkSqlTransformation("SELECT user_id, reg_country, reg_date FROM backfill_data_source")
     """
 
     def decorator(function):
-        _validate_decorator_ordering(function)
-        StreamingBackfill.set_streaming_backfill_on_function(
-            function=function,
-            start_date=start_date,
-            end_date=end_date,
-            data_sources=data_sources,
-            backfill_transformation=backfill_transformation,
-            backfill_cluster_template=backfill_cluster_template,
+        if isinstance(function, StreamingFeatureSet):
+            raise QwakException(
+                "Backfill can no longer be defined as a decorator on the feature set, it must be triggered after feature set creation."
+            )
+
+        backfill_transformation: SparkSqlTransformation = function()
+
+        if not isinstance(backfill_transformation, SparkSqlTransformation):
+            raise QwakException(
+                "Backfill must defined on a method returning a SparkSqlTransformation"
+            )
+
+        streaming_backfill = StreamingBackfill(
+            featureset_name=feature_set_name,
+            start_datetime=start_date,
+            end_datetime=end_date,
+            data_sources=StreamingBackfill._get_normalized_backfill_sources_spec(
+                data_sources
+            ),
+            transform=backfill_transformation,
+            cluster_template=backfill_cluster_template,
         )
 
-        return function
+        functools.update_wrapper(streaming_backfill, backfill_transformation)
+
+        return streaming_backfill
 
     return decorator
 
@@ -316,7 +332,7 @@ class StreamingFeatureSet(BaseFeatureSet):
     offline_cluster_template: Optional[ClusterTemplate] = None
     online_cluster_template: Optional[ClusterTemplate] = None
     metadata: Optional[Metadata] = None
-    backfill: Optional[StreamingBackfill] = None
+    backfill_max_timestamp: Optional[datetime] = None
     auxiliary_sinks: List[BaseSink] = field(default_factory=lambda: [])
 
     def __post_init__(self):
@@ -399,7 +415,6 @@ class StreamingFeatureSet(BaseFeatureSet):
             proto_featureset_type = self._get_streaming_aggregation_featureset_proto(
                 artifact_url=artifact_url,
                 streaming_sources=data_sources,
-                feature_registry=feature_registry,
                 initial_tile_size=maybe_initial_tile_size,
             )
 
@@ -453,10 +468,9 @@ class StreamingFeatureSet(BaseFeatureSet):
                 "Auxiliary Sinks Are not supported in Streaming Aggregation Feature Sets"
             )
 
-        # streaming backfill not yet supported for row-level streaming
-        if self.backfill and not is_streaming_agg:
+        if self.backfill_max_timestamp and not is_streaming_agg:
             raise QwakException(
-                "Streaming backfill is only supported for streaming aggregation feature sets at the moment"
+                "backfill_max_timestamp can only be set for Streaming Aggregation FeatureSet."
             )
 
         # Validate transformation is PySpark when multiple data sources are used
@@ -515,18 +529,29 @@ class StreamingFeatureSet(BaseFeatureSet):
                 )
             raise QwakException(error_message_str)
 
-        # Validate the backfill, if defined
-        if self.backfill:
-            self.backfill._validate_tile_size(initial_tile_size)
+        if not self.backfill_max_timestamp:
+            raise QwakException(
+                """
+                backfill_max_timestamp must be set for Streaming Aggregation FeatureSet.
+                 Events earlier than this timestamp can only be processed by triggering backfill,
+                 the Streaming job will not process events that are earlier than this timestamp.
+            """
+            )
+
+        self._validate_streaming_aggregation_backfill_max_timestamp()
 
         return initial_tile_size
 
-    def _validate_streaming_aggregation_backfill(self):
+    def _validate_streaming_aggregation_backfill_max_timestamp(self):
         initial_tile_size, _ = StreamingFeatureSet._get_default_slide_period(
             self.transformation.windows
         )
 
-        self.backfill._validate_tile_size(initial_tile_size)
+        if self.backfill_max_timestamp.timestamp() % initial_tile_size != 0:
+            raise QwakException(
+                f"Chosen backfill max timestamp is invalid,"
+                f" it has to be exactly dividable by slice size of {initial_tile_size} seconds."
+            )
 
     @staticmethod
     def _get_default_slide_period(
@@ -596,9 +621,12 @@ class StreamingFeatureSet(BaseFeatureSet):
         self,
         artifact_url: Optional[str],
         streaming_sources: List[StreamingSource],
-        feature_registry: FeatureRegistryClient,
         initial_tile_size: int,
     ) -> ProtoFeatureSetType:
+        backfill_max_timestamp = ProtoTimestamp()
+        backfill_max_timestamp.FromDatetime(
+            self.backfill_max_timestamp.astimezone(timezone.utc)
+        )
         return ProtoFeatureSetType(
             streaming_aggregation_feature_set=ProtoStreamingAggregationFeatureSet(
                 transformation=self.transformation._to_proto(
@@ -621,14 +649,7 @@ class StreamingFeatureSet(BaseFeatureSet):
                     allowed_late_arrival_seconds=60 * 10,
                     aggregations=self.transformation._get_aggregations_proto(),
                 ),
-                backfill_spec=(
-                    self.backfill._to_proto(
-                        feature_registry=feature_registry,
-                        original_instance_module_path=self.__instance_module_path__,
-                        featureset_name=self.name,
-                    )
-                    if self.backfill
-                    else None
-                ),
+                backfill_spec=None,
+                backfill_max_timestamp=backfill_max_timestamp,
             )
         )