mlrun 1.7.0rc4__py3-none-any.whl → 1.7.0rc20__py3-none-any.whl

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,
         ]
 
 

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

@@ -11,8 +11,6 @@
 # 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 (
     ControllerPolicy,
@@ -22,19 +20,32 @@ from .constants import (
     EventFieldType,
     EventKeyMetrics,
     EventLiveStats,
+    FeatureSetFeatures,
     FileTargetKind,
     FunctionURI,
+    MetricData,
     ModelEndpointTarget,
     ModelMonitoringMode,
     ModelMonitoringStoreKinds,
     MonitoringFunctionNames,
+    PredictionsQueryConstants,
     ProjectSecretKeys,
+    PrometheusEndpoints,
     PrometheusMetric,
-    TimeSeriesTarget,
+    ResultData,
+    ResultKindApp,
+    SchedulingKeys,
+    SpecialApps,
+    TDEngineSuperTables,
+    TSDBTarget,
+    V3IOTSDBTables,
     VersionedModel,
+    WriterEvent,
+    WriterEventKind,
 )
 from .grafana import (
     GrafanaColumn,
+    GrafanaColumnType,
     GrafanaDataPoint,
     GrafanaNumberColumn,
     GrafanaStringColumn,
@@ -47,6 +58,11 @@ from .model_endpoints import (
     ModelEndpoint,
     ModelEndpointList,
     ModelEndpointMetadata,
+    ModelEndpointMonitoringMetric,
+    ModelEndpointMonitoringMetricNoData,
+    ModelEndpointMonitoringMetricType,
+    ModelEndpointMonitoringMetricValues,
+    ModelEndpointMonitoringResultValues,
     ModelEndpointSpec,
     ModelEndpointStatus,
 )

mlrun/common/schemas/model_monitoring/constants.py

@@ -21,6 +21,12 @@ 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"
@@ -75,25 +81,59 @@ class EventFieldType:
     DRIFT_DETECTED_THRESHOLD = "drift_detected_threshold"
     POSSIBLE_DRIFT_THRESHOLD = "possible_drift_threshold"
     SAMPLE_PARQUET_PATH = "sample_parquet_path"
+    TIME = "time"
+    TABLE_COLUMN = "table_column"
+
+
+class FeatureSetFeatures(MonitoringStrEnum):
+    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"
+    MLRUN_CONTEXT = "mlrun_context"
+
+    # Deprecated fields - TODO : delete in 1.9.0  (V1 app deprecation)
+    SAMPLE_PARQUET_PATH = "sample_parquet_path"
+    CURRENT_STATS = "current_stats"
+    FEATURE_STATS = "feature_stats"
 
 
-class WriterEvent(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 +141,6 @@ 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"
@@ -122,10 +158,6 @@ class EventKeyMetrics:
     REAL_TIME = "real_time"
 
 
-class TimeSeriesTarget:
-    TSDB = "tsdb"
-
-
 class ModelEndpointTarget:
     V3IO_NOSQL = "v3io-nosql"
     SQL = "sql"
@@ -135,8 +167,9 @@ 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"
+    KAFKA_BROKERS = "KAFKA_BROKERS"
     STREAM_PATH = "STREAM_PATH"
+    TSDB_CONNECTION = "TSDB_CONNECTION"
 
 
 class ModelMonitoringStoreKinds:
@@ -146,15 +179,23 @@ 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"
 
 
 class ModelMonitoringMode(str, Enum):
@@ -177,20 +218,28 @@ class PrometheusMetric:
     DRIFT_STATUS = "drift_status"
 
 
-class MonitoringFunctionNames:
-    WRITER = "model-monitoring-writer"
-    BATCH = "model-monitoring-batch"
-    APPLICATION_CONTROLLER = "model-monitoring-controller"
+class PrometheusEndpoints(MonitoringStrEnum):
+    MODEL_MONITORING_METRICS = "/model-monitoring-metrics"
+    MONITORING_BATCH_METRICS = "/monitoring-batch-metrics"
+    MONITORING_DRIFT_STATUS = "/monitoring-drift-status"
+
+
+class MonitoringFunctionNames(MonitoringStrEnum):
     STREAM = "model-monitoring-stream"
+    APPLICATION_CONTROLLER = "model-monitoring-controller"
+    WRITER = "model-monitoring-writer"
 
-    @staticmethod
-    def all():
-        return [
-            MonitoringFunctionNames.WRITER,
-            MonitoringFunctionNames.STREAM,
-            MonitoringFunctionNames.BATCH,
-            MonitoringFunctionNames.APPLICATION_CONTROLLER,
-        ]
+
+class V3IOTSDBTables(MonitoringStrEnum):
+    APP_RESULTS = "app-results"
+    METRICS = "metrics"
+    EVENTS = "events"
+
+
+class TDEngineSuperTables(MonitoringStrEnum):
+    APP_RESULTS = "app_results"
+    METRICS = "metrics"
+    PREDICTIONS = "predictions"
 
 
 @dataclass
@@ -269,6 +318,7 @@ class ResultKindApp(Enum):
     concept_drift = 1
     model_performance = 2
     system_performance = 3
+    custom = 4
 
 
 class ResultStatusApp(IntEnum):
@@ -286,9 +336,29 @@ class ModelMonitoringAppLabel:
     KEY = "mlrun__type"
     VAL = "mlrun__model-monitoring-application"
 
+    def __str__(self) -> str:
+        return f"{self.KEY}={self.VAL}"
+
 
 class ControllerPolicy:
     BASE_PERIOD = "base_period"
 
 
-MLRUN_HISTOGRAM_DATA_DRIFT_APP_NAME = "histogram-data-drift"
+class TSDBTarget:
+    V3IO_TSDB = "v3io-tsdb"
+    TDEngine = "tdengine"
+    PROMETHEUS = "prometheus"
+
+
+class HistogramDataDriftApplicationConstants:
+    NAME = "histogram-data-drift"
+    GENERAL_RESULT_NAME = "general_drift"
+
+
+class PredictionsQueryConstants:
+    DEFAULT_AGGREGATION_GRANULARITY = "10m"
+    INVOCATIONS = "invocations"
+
+
+class SpecialApps:
+    MLRUN_INFRA = "mlrun-infra"

mlrun/common/schemas/model_monitoring/grafana.py

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

mlrun/common/schemas/model_monitoring/model_endpoints.py

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

mlrun/{runtimes/mpijob/v1alpha1.py → common/schemas/pagination.py}

@@ -11,19 +11,16 @@
 # 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 deprecated import deprecated
 
-from mlrun.runtimes.constants import MPIJobCRDVersions
-from mlrun.runtimes.mpijob.abstract import AbstractMPIJobRuntime
+import typing
 
+import pydantic
 
-# TODO: Remove in 1.7.0
-@deprecated(
-    version="1.5.0",
-    reason="v1alpha1 mpi will be removed in 1.7.0, use v1 instead",
-    category=FutureWarning,
-)
-class MpiRuntimeV1Alpha1(AbstractMPIJobRuntime):
-    crd_group = "kubeflow.org"
-    crd_version = MPIJobCRDVersions.v1alpha1
-    crd_plural = "mpijobs"
+
+class PaginationInfo(pydantic.BaseModel):
+    class Config:
+        allow_population_by_field_name = True
+
+    page: typing.Optional[int]
+    page_size: typing.Optional[int] = pydantic.Field(alias="page-size")
+    page_token: typing.Optional[str] = pydantic.Field(alias="page-token")

mlrun/common/schemas/pipeline.py

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

mlrun/common/schemas/project.py

@@ -23,16 +23,6 @@ from .common import ImageBuilder
 from .object import ObjectKind, ObjectStatus
 
 
-class ProjectsFormat(mlrun.common.types.StrEnum):
-    full = "full"
-    name_only = "name_only"
-    # minimal format removes large fields from the response (e.g. functions, workflows, artifacts)
-    # and is used for faster response times (in the UI)
-    minimal = "minimal"
-    # internal - allowed only in follower mode, only for the leader for upgrade purposes
-    leader = "leader"
-
-
 class ProjectMetadata(pydantic.BaseModel):
     name: str
     created: typing.Optional[datetime.datetime] = None
@@ -87,6 +77,7 @@ class ProjectSpec(pydantic.BaseModel):
     custom_packagers: typing.Optional[list[tuple[str, bool]]] = None
     default_image: typing.Optional[str] = None
     build: typing.Optional[ImageBuilder] = None
+    default_function_node_selector: typing.Optional[dict] = {}
 
     class Config:
         extra = pydantic.Extra.allow
@@ -109,9 +100,14 @@ class ProjectSummary(pydantic.BaseModel):
     files_count: int
     feature_sets_count: int
     models_count: int
+    runs_completed_recent_count: int
     runs_failed_recent_count: int
     runs_running_count: int
-    schedules_count: int
+    distinct_schedules_count: int
+    distinct_scheduled_jobs_pending_count: int
+    distinct_scheduled_pipelines_pending_count: int
+    pipelines_completed_recent_count: typing.Optional[int] = None
+    pipelines_failed_recent_count: typing.Optional[int] = None
     pipelines_running_count: typing.Optional[int] = None
 
 
@@ -119,17 +115,22 @@ class IguazioProject(pydantic.BaseModel):
     data: dict
 
 
+# The format query param controls the project type used:
+# full - Project
+# name_only - str
+# summary - ProjectSummary
+# leader - currently only IguazioProject supported
+# The way pydantic handles typing.Union is that it takes the object and tries to coerce it to be the types of the
+# union by the definition order. Therefore we can't currently add generic dict for all leader formats, but we need
+# to add a specific classes for them. it's frustrating but couldn't find other workaround, see:
+# https://github.com/samuelcolvin/pydantic/issues/1423, https://github.com/samuelcolvin/pydantic/issues/619
+ProjectOutput = typing.TypeVar(
+    "ProjectOutput", Project, str, ProjectSummary, IguazioProject
+)
+
+
 class ProjectsOutput(pydantic.BaseModel):
-    # The format query param controls the project type used:
-    # full - Project
-    # name_only - str
-    # summary - ProjectSummary
-    # leader - currently only IguazioProject supported
-    # The way pydantic handles typing.Union is that it takes the object and tries to coerce it to be the types of the
-    # union by the definition order. Therefore we can't currently add generic dict for all leader formats, but we need
-    # to add a specific classes for them. it's frustrating but couldn't find other workaround, see:
-    # https://github.com/samuelcolvin/pydantic/issues/1423, https://github.com/samuelcolvin/pydantic/issues/619
-    projects: list[typing.Union[Project, str, ProjectSummary, IguazioProject]]
+    projects: list[ProjectOutput]
 
 
 class ProjectSummariesOutput(pydantic.BaseModel):

mlrun/common/types.py

@@ -11,7 +11,6 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-#
 
 import enum
 
@@ -23,3 +22,10 @@ class StrEnum(str, enum.Enum):
 
     def __repr__(self):
         return self.value
+
+
+# Partial backport from Python 3.11
+# https://docs.python.org/3/library/http.html#http.HTTPMethod
+class HTTPMethod(StrEnum):
+    GET = "GET"
+    POST = "POST"