mlrun 1.7.0rc4__py3-none-any.whl → 1.7.2__py3-none-any.whl

mlrun/common/schemas/feature_store.py

@@ -14,7 +14,7 @@
 #
 from typing import Optional
 
-from pydantic import BaseModel, Extra, Field
+import pydantic
 
 from .auth import AuthorizationResourceTypes, Credentials
 from .object import (
@@ -27,32 +27,42 @@ from .object import (
 )
 
 
-class Feature(BaseModel):
+class FeatureStoreBaseModel(pydantic.BaseModel):
+    """
+    Intermediate base class, in order to override pydantic's configuration, as per
+    https://docs.pydantic.dev/1.10/usage/model_config/#change-behaviour-globally
+    """
+
+    class Config:
+        copy_on_model_validation = "none"
+
+
+class Feature(FeatureStoreBaseModel):
     name: str
     value_type: str
     labels: Optional[dict] = {}
 
     class Config:
-        extra = Extra.allow
+        extra = pydantic.Extra.allow
 
 
-class Entity(BaseModel):
+class Entity(FeatureStoreBaseModel):
     name: str
     value_type: str
     labels: Optional[dict] = {}
 
     class Config:
-        extra = Extra.allow
+        extra = pydantic.Extra.allow
 
 
 class FeatureSetSpec(ObjectSpec):
     entities: list[Entity] = []
     features: list[Feature] = []
-    engine: Optional[str] = Field(default="storey")
+    engine: Optional[str] = pydantic.Field(default="storey")
 
 
-class FeatureSet(BaseModel):
-    kind: ObjectKind = Field(ObjectKind.feature_set, const=True)
+class FeatureSet(FeatureStoreBaseModel):
+    kind: ObjectKind = pydantic.Field(ObjectKind.feature_set, const=True)
     metadata: ObjectMetadata
     spec: FeatureSetSpec
     status: ObjectStatus
@@ -62,7 +72,7 @@ class FeatureSet(BaseModel):
         return AuthorizationResourceTypes.feature_set
 
 
-class EntityRecord(BaseModel):
+class EntityRecord(FeatureStoreBaseModel):
     name: str
     value_type: str
     labels: list[LabelRecord]
@@ -71,7 +81,7 @@ class EntityRecord(BaseModel):
         orm_mode = True
 
 
-class FeatureRecord(BaseModel):
+class FeatureRecord(FeatureStoreBaseModel):
     name: str
     value_type: str
     labels: list[LabelRecord]
@@ -88,44 +98,64 @@ class FeatureSetRecord(ObjectRecord):
         orm_mode = True
 
 
-class FeatureSetsOutput(BaseModel):
+class FeatureSetsOutput(FeatureStoreBaseModel):
     feature_sets: list[FeatureSet]
 
 
-class FeatureSetsTagsOutput(BaseModel):
+class FeatureSetsTagsOutput(FeatureStoreBaseModel):
     tags: list[str] = []
 
 
-class FeatureSetDigestSpec(BaseModel):
+class FeatureSetDigestSpec(FeatureStoreBaseModel):
     entities: list[Entity]
     features: list[Feature]
 
 
-class FeatureSetDigestOutput(BaseModel):
+class FeatureSetDigestOutput(FeatureStoreBaseModel):
     metadata: ObjectMetadata
     spec: FeatureSetDigestSpec
 
 
-class FeatureListOutput(BaseModel):
+class FeatureSetDigestSpecV2(FeatureStoreBaseModel):
+    entities: list[Entity]
+
+
+class FeatureSetDigestOutputV2(FeatureStoreBaseModel):
+    feature_set_index: int
+    metadata: ObjectMetadata
+    spec: FeatureSetDigestSpecV2
+
+
+class FeatureListOutput(FeatureStoreBaseModel):
     feature: Feature
     feature_set_digest: FeatureSetDigestOutput
 
 
-class FeaturesOutput(BaseModel):
+class FeaturesOutput(FeatureStoreBaseModel):
     features: list[FeatureListOutput]
 
 
-class EntityListOutput(BaseModel):
+class FeaturesOutputV2(FeatureStoreBaseModel):
+    features: list[Feature]
+    feature_set_digests: list[FeatureSetDigestOutputV2]
+
+
+class EntityListOutput(FeatureStoreBaseModel):
     entity: Entity
     feature_set_digest: FeatureSetDigestOutput
 
 
-class EntitiesOutput(BaseModel):
+class EntitiesOutputV2(FeatureStoreBaseModel):
+    entities: list[Entity]
+    feature_set_digests: list[FeatureSetDigestOutputV2]
+
+
+class EntitiesOutput(FeatureStoreBaseModel):
     entities: list[EntityListOutput]
 
 
-class FeatureVector(BaseModel):
-    kind: ObjectKind = Field(ObjectKind.feature_vector, const=True)
+class FeatureVector(FeatureStoreBaseModel):
+    kind: ObjectKind = pydantic.Field(ObjectKind.feature_vector, const=True)
     metadata: ObjectMetadata
     spec: ObjectSpec
     status: ObjectStatus
@@ -139,39 +169,39 @@ class FeatureVectorRecord(ObjectRecord):
     pass
 
 
-class FeatureVectorsOutput(BaseModel):
+class FeatureVectorsOutput(FeatureStoreBaseModel):
     feature_vectors: list[FeatureVector]
 
 
-class FeatureVectorsTagsOutput(BaseModel):
+class FeatureVectorsTagsOutput(FeatureStoreBaseModel):
     tags: list[str] = []
 
 
-class DataSource(BaseModel):
+class DataSource(FeatureStoreBaseModel):
     kind: str
     name: str
     path: str
 
     class Config:
-        extra = Extra.allow
+        extra = pydantic.Extra.allow
 
 
-class DataTarget(BaseModel):
+class DataTarget(FeatureStoreBaseModel):
     kind: str
     name: str
     path: Optional[str]
 
     class Config:
-        extra = Extra.allow
+        extra = pydantic.Extra.allow
 
 
-class FeatureSetIngestInput(BaseModel):
+class FeatureSetIngestInput(FeatureStoreBaseModel):
     source: Optional[DataSource]
     targets: Optional[list[DataTarget]]
     infer_options: Optional[int]
     credentials: Credentials = Credentials()
 
 
-class FeatureSetIngestOutput(BaseModel):
+class FeatureSetIngestOutput(FeatureStoreBaseModel):
     feature_set: FeatureSet
     run_object: dict

mlrun/common/schemas/frontend_spec.py

@@ -50,6 +50,12 @@ class FeatureFlags(pydantic.BaseModel):
     preemption_nodes: PreemptionNodesFeatureFlag
 
 
+class ArtifactLimits(pydantic.BaseModel):
+    max_chunk_size: int
+    max_preview_size: int
+    max_download_size: int
+
+
 class FrontendSpec(pydantic.BaseModel):
     jobs_dashboard_url: typing.Optional[str]
     model_monitoring_dashboard_url: typing.Optional[str]
@@ -70,3 +76,5 @@ class FrontendSpec(pydantic.BaseModel):
     feature_store_data_prefixes: typing.Optional[dict[str, str]]
     allowed_artifact_path_prefixes_list: list[str]
     ce: typing.Optional[dict]
+    internal_labels: list[str] = []
+    artifact_limits: ArtifactLimits

mlrun/common/schemas/function.py

@@ -45,6 +45,9 @@ class FunctionState:
     # same goes for the build which is not coming from the pod, but is used and we can't just omit it for BC reasons
     build = "build"
 
+    # for pipeline steps
+    skipped = "skipped"
+
     @classmethod
     def get_function_state_from_pod_state(cls, pod_state: str):
         if pod_state == "succeeded":
@@ -60,6 +63,7 @@ class FunctionState:
         return [
             cls.ready,
             cls.error,
+            cls.skipped,
         ]
 
 
@@ -115,6 +119,13 @@ class FunctionSpec(pydantic.BaseModel):
     service_account: typing.Optional[ServiceAccount]
     state_thresholds: typing.Optional[StateThresholds]
 
+    class Config:
+        extra = pydantic.Extra.allow
+
 
 class Function(pydantic.BaseModel):
     spec: typing.Optional[FunctionSpec]
+    application: typing.Optional[dict[str, typing.Any]]
+
+    class Config:
+        extra = pydantic.Extra.allow

mlrun/common/schemas/hub.py

@@ -59,28 +59,26 @@ class HubSource(BaseModel):
         return f"{self.spec.path}/{self.spec.object_type}/{self.spec.channel}/{relative_path}"
 
     def get_catalog_uri(self):
-        return self.get_full_uri(mlrun.config.config.hub.catalog_filename)
+        return self.get_full_uri(mlrun.mlconf.hub.catalog_filename)
 
     @classmethod
     def generate_default_source(cls):
-        if not mlrun.config.config.hub.default_source.create:
+        if not mlrun.mlconf.hub.default_source.create:
             return None
 
         now = datetime.now(timezone.utc)
         hub_metadata = HubObjectMetadata(
-            name=mlrun.config.config.hub.default_source.name,
-            description=mlrun.config.config.hub.default_source.description,
+            name=mlrun.mlconf.hub.default_source.name,
+            description=mlrun.mlconf.hub.default_source.description,
             created=now,
             updated=now,
         )
         return cls(
             metadata=hub_metadata,
             spec=HubSourceSpec(
-                path=mlrun.config.config.hub.default_source.url,
-                channel=mlrun.config.config.hub.default_source.channel,
-                object_type=HubSourceType(
-                    mlrun.config.config.hub.default_source.object_type
-                ),
+                path=mlrun.mlconf.hub.default_source.url,
+                channel=mlrun.mlconf.hub.default_source.channel,
+                object_type=HubSourceType(mlrun.mlconf.hub.default_source.object_type),
             ),
             status=ObjectStatus(state="created"),
         )

mlrun/common/schemas/model_monitoring/__init__.py

@@ -11,10 +11,9 @@
 # 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.
-#
-# flake8: noqa  - this is until we take care of the F401 violations with respect to __all__ & sphinx
 
 from .constants import (
+    V3IO_MODEL_MONITORING_DB,
     ControllerPolicy,
     DriftStatus,
     EndpointType,
@@ -22,19 +21,33 @@ from .constants import (
     EventFieldType,
     EventKeyMetrics,
     EventLiveStats,
+    FeatureSetFeatures,
     FileTargetKind,
     FunctionURI,
+    MetricData,
+    ModelEndpointMonitoringMetricType,
     ModelEndpointTarget,
+    ModelEndpointTargetSchemas,
     ModelMonitoringMode,
     ModelMonitoringStoreKinds,
     MonitoringFunctionNames,
+    PredictionsQueryConstants,
     ProjectSecretKeys,
-    PrometheusMetric,
-    TimeSeriesTarget,
+    ResultData,
+    ResultKindApp,
+    ResultStatusApp,
+    SchedulingKeys,
+    SpecialApps,
+    TDEngineSuperTables,
+    TSDBTarget,
+    V3IOTSDBTables,
     VersionedModel,
+    WriterEvent,
+    WriterEventKind,
 )
 from .grafana import (
     GrafanaColumn,
+    GrafanaColumnType,
     GrafanaDataPoint,
     GrafanaNumberColumn,
     GrafanaStringColumn,
@@ -47,6 +60,10 @@ from .model_endpoints import (
     ModelEndpoint,
     ModelEndpointList,
     ModelEndpointMetadata,
+    ModelEndpointMonitoringMetric,
+    ModelEndpointMonitoringMetricNoData,
+    ModelEndpointMonitoringMetricValues,
+    ModelEndpointMonitoringResultValues,
     ModelEndpointSpec,
     ModelEndpointStatus,
 )

mlrun/common/schemas/model_monitoring/constants.py

@@ -13,14 +13,22 @@
 # limitations under the License.
 
 import hashlib
-from dataclasses import dataclass
+import re
+from dataclasses import dataclass, field
 from enum import Enum, IntEnum
 from typing import Optional
 
+import mlrun.common.constants
 import mlrun.common.helpers
 from mlrun.common.types import StrEnum
 
 
+class MonitoringStrEnum(StrEnum):
+    @classmethod
+    def list(cls):
+        return list(map(lambda c: c.value, cls))
+
+
 class EventFieldType:
     FUNCTION_URI = "function_uri"
     FUNCTION = "function"
@@ -46,9 +54,11 @@ class EventFieldType:
     PREDICTIONS = "predictions"
     NAMED_PREDICTIONS = "named_predictions"
     ERROR_COUNT = "error_count"
+    MODEL_ERROR = "model_error"
     ENTITIES = "entities"
     FIRST_REQUEST = "first_request"
     LAST_REQUEST = "last_request"
+    LAST_REQUEST_TIMESTAMP = "last_request_timestamp"
     METRIC = "metric"
     METRICS = "metrics"
     BATCH_INTERVALS_DICT = "batch_intervals_dict"
@@ -72,28 +82,53 @@ class EventFieldType:
     FEATURE_SET_URI = "monitoring_feature_set_uri"
     ALGORITHM = "algorithm"
     VALUE = "value"
-    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):
+    LATENCY = EventFieldType.LATENCY
+    ERROR_COUNT = EventFieldType.ERROR_COUNT
+    METRICS = EventFieldType.METRICS
+
+    @classmethod
+    def time_stamp(cls):
+        return EventFieldType.TIMESTAMP
+
+    @classmethod
+    def entity(cls):
+        return EventFieldType.ENDPOINT_ID
 
 
 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"
 
 
-class WriterEvent(StrEnum):
+class WriterEvent(MonitoringStrEnum):
     APPLICATION_NAME = "application_name"
     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"
@@ -101,10 +136,6 @@ class WriterEvent(StrEnum):
     RESULT_EXTRA_DATA = "result_extra_data"
     CURRENT_STATS = "current_stats"
 
-    @classmethod
-    def list(cls):
-        return list(map(lambda c: c.value, cls))
-
 
 class EventLiveStats:
     LATENCY_AVG_5M = "latency_avg_5m"
@@ -122,21 +153,40 @@ class EventKeyMetrics:
     REAL_TIME = "real_time"
 
 
-class TimeSeriesTarget:
-    TSDB = "tsdb"
-
-
-class ModelEndpointTarget:
+class ModelEndpointTarget(MonitoringStrEnum):
     V3IO_NOSQL = "v3io-nosql"
     SQL = "sql"
 
 
+class StreamKind(MonitoringStrEnum):
+    V3IO_STREAM = "v3io_stream"
+    KAFKA = "kafka"
+
+
+class TSDBTarget(MonitoringStrEnum):
+    V3IO_TSDB = "v3io-tsdb"
+    TDEngine = "tdengine"
+
+
 class ProjectSecretKeys:
     ENDPOINT_STORE_CONNECTION = "MODEL_MONITORING_ENDPOINT_STORE_CONNECTION"
     ACCESS_KEY = "MODEL_MONITORING_ACCESS_KEY"
-    PIPELINES_ACCESS_KEY = "MODEL_MONITORING_PIPELINES_ACCESS_KEY"
-    KAFKA_BOOTSTRAP_SERVERS = "KAFKA_BOOTSTRAP_SERVERS"
     STREAM_PATH = "STREAM_PATH"
+    TSDB_CONNECTION = "TSDB_CONNECTION"
+
+    @classmethod
+    def mandatory_secrets(cls):
+        return [
+            cls.ENDPOINT_STORE_CONNECTION,
+            cls.STREAM_PATH,
+            cls.TSDB_CONNECTION,
+        ]
+
+
+class ModelEndpointTargetSchemas(MonitoringStrEnum):
+    V3IO = "v3io"
+    MYSQL = "mysql"
+    SQLITE = "sqlite"
 
 
 class ModelMonitoringStoreKinds:
@@ -146,15 +196,24 @@ class ModelMonitoringStoreKinds:
 
 class SchedulingKeys:
     LAST_ANALYZED = "last_analyzed"
+    ENDPOINT_ID = "endpoint_id"
+    APPLICATION_NAME = "application_name"
+    UID = "uid"
 
 
 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"
+    ERRORS = "errors"
 
 
 class ModelMonitoringMode(str, Enum):
@@ -168,29 +227,23 @@ class EndpointType(IntEnum):
     LEAF_EP = 3  # end point that is a child of a router
 
 
-class PrometheusMetric:
-    PREDICTIONS_TOTAL = "predictions_total"
-    MODEL_LATENCY_SECONDS = "model_latency_seconds"
-    INCOME_FEATURES = "income_features"
-    ERRORS_TOTAL = "errors_total"
-    DRIFT_METRICS = "drift_metrics"
-    DRIFT_STATUS = "drift_status"
+class MonitoringFunctionNames(MonitoringStrEnum):
+    STREAM = "model-monitoring-stream"
+    APPLICATION_CONTROLLER = "model-monitoring-controller"
+    WRITER = "model-monitoring-writer"
 
 
-class MonitoringFunctionNames:
-    WRITER = "model-monitoring-writer"
-    BATCH = "model-monitoring-batch"
-    APPLICATION_CONTROLLER = "model-monitoring-controller"
-    STREAM = "model-monitoring-stream"
+class V3IOTSDBTables(MonitoringStrEnum):
+    APP_RESULTS = "app-results"
+    METRICS = "metrics"
+    EVENTS = "events"
+    ERRORS = "errors"
 
-    @staticmethod
-    def all():
-        return [
-            MonitoringFunctionNames.WRITER,
-            MonitoringFunctionNames.STREAM,
-            MonitoringFunctionNames.BATCH,
-            MonitoringFunctionNames.APPLICATION_CONTROLLER,
-        ]
+
+class TDEngineSuperTables(MonitoringStrEnum):
+    APP_RESULTS = "app_results"
+    METRICS = "metrics"
+    PREDICTIONS = "predictions"
 
 
 @dataclass
@@ -236,7 +289,7 @@ class EndpointUID:
     function_hash_key: str
     model: str
     model_version: str
-    uid: Optional[str] = None
+    uid: str = field(init=False)
 
     def __post_init__(self):
         function_ref = (
@@ -269,6 +322,7 @@ class ResultKindApp(Enum):
     concept_drift = 1
     model_performance = 2
     system_performance = 3
+    mm_app_anomaly = 4
 
 
 class ResultStatusApp(IntEnum):
@@ -283,12 +337,52 @@ class ResultStatusApp(IntEnum):
 
 
 class ModelMonitoringAppLabel:
-    KEY = "mlrun__type"
+    KEY = mlrun.common.constants.MLRunInternalLabels.mlrun_type
     VAL = "mlrun__model-monitoring-application"
 
+    def __str__(self) -> str:
+        return f"{self.KEY}={self.VAL}"
+
 
 class ControllerPolicy:
     BASE_PERIOD = "base_period"
 
 
-MLRUN_HISTOGRAM_DATA_DRIFT_APP_NAME = "histogram-data-drift"
+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"
+
+
+_RESERVED_FUNCTION_NAMES = MonitoringFunctionNames.list() + [SpecialApps.MLRUN_INFRA]
+
+
+V3IO_MODEL_MONITORING_DB = "v3io"
+
+
+class ModelEndpointMonitoringMetricType(StrEnum):
+    RESULT = "result"
+    METRIC = "metric"
+
+
+_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})$"
+)
+FQN_REGEX = re.compile(FQN_PATTERN)
+
+# refer to `mlrun.utils.regex.project_name`
+PROJECT_PATTERN = r"^[a-z0-9]([a-z0-9-]{0,61}[a-z0-9])?$"
+
+MODEL_ENDPOINT_ID_PATTERN = r"^[a-zA-Z0-9_-]+$"

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):