databricks-sdk 0.55.0__py3-none-any.whl → 0.56.0__py3-none-any.whl

databricks/sdk/service/qualitymonitorv2.py

@@ -0,0 +1,275 @@
+# Code generated from OpenAPI specs by Databricks SDK Generator. DO NOT EDIT.
+
+from __future__ import annotations
+
+import logging
+from dataclasses import dataclass
+from enum import Enum
+from typing import Any, Dict, Iterator, List, Optional
+
+from ._internal import _enum, _from_dict, _repeated_dict
+
+_LOG = logging.getLogger("databricks.sdk")
+
+
+# all definitions in this file are in alphabetical order
+
+
+@dataclass
+class AnomalyDetectionConfig:
+    last_run_id: Optional[str] = None
+    """Run id of the last run of the workflow"""
+
+    latest_run_status: Optional[AnomalyDetectionRunStatus] = None
+    """The status of the last run of the workflow."""
+
+    def as_dict(self) -> dict:
+        """Serializes the AnomalyDetectionConfig into a dictionary suitable for use as a JSON request body."""
+        body = {}
+        if self.last_run_id is not None:
+            body["last_run_id"] = self.last_run_id
+        if self.latest_run_status is not None:
+            body["latest_run_status"] = self.latest_run_status.value
+        return body
+
+    def as_shallow_dict(self) -> dict:
+        """Serializes the AnomalyDetectionConfig into a shallow dictionary of its immediate attributes."""
+        body = {}
+        if self.last_run_id is not None:
+            body["last_run_id"] = self.last_run_id
+        if self.latest_run_status is not None:
+            body["latest_run_status"] = self.latest_run_status
+        return body
+
+    @classmethod
+    def from_dict(cls, d: Dict[str, Any]) -> AnomalyDetectionConfig:
+        """Deserializes the AnomalyDetectionConfig from a dictionary."""
+        return cls(
+            last_run_id=d.get("last_run_id", None),
+            latest_run_status=_enum(d, "latest_run_status", AnomalyDetectionRunStatus),
+        )
+
+
+class AnomalyDetectionRunStatus(Enum):
+    """Status of Anomaly Detection Job Run"""
+
+    ANOMALY_DETECTION_RUN_STATUS_CANCELED = "ANOMALY_DETECTION_RUN_STATUS_CANCELED"
+    ANOMALY_DETECTION_RUN_STATUS_FAILED = "ANOMALY_DETECTION_RUN_STATUS_FAILED"
+    ANOMALY_DETECTION_RUN_STATUS_JOB_DELETED = "ANOMALY_DETECTION_RUN_STATUS_JOB_DELETED"
+    ANOMALY_DETECTION_RUN_STATUS_PENDING = "ANOMALY_DETECTION_RUN_STATUS_PENDING"
+    ANOMALY_DETECTION_RUN_STATUS_RUNNING = "ANOMALY_DETECTION_RUN_STATUS_RUNNING"
+    ANOMALY_DETECTION_RUN_STATUS_SUCCESS = "ANOMALY_DETECTION_RUN_STATUS_SUCCESS"
+    ANOMALY_DETECTION_RUN_STATUS_UNKNOWN = "ANOMALY_DETECTION_RUN_STATUS_UNKNOWN"
+    ANOMALY_DETECTION_RUN_STATUS_WORKSPACE_MISMATCH_ERROR = "ANOMALY_DETECTION_RUN_STATUS_WORKSPACE_MISMATCH_ERROR"
+
+
+@dataclass
+class DeleteQualityMonitorResponse:
+    def as_dict(self) -> dict:
+        """Serializes the DeleteQualityMonitorResponse into a dictionary suitable for use as a JSON request body."""
+        body = {}
+        return body
+
+    def as_shallow_dict(self) -> dict:
+        """Serializes the DeleteQualityMonitorResponse into a shallow dictionary of its immediate attributes."""
+        body = {}
+        return body
+
+    @classmethod
+    def from_dict(cls, d: Dict[str, Any]) -> DeleteQualityMonitorResponse:
+        """Deserializes the DeleteQualityMonitorResponse from a dictionary."""
+        return cls()
+
+
+@dataclass
+class ListQualityMonitorResponse:
+    next_page_token: Optional[str] = None
+
+    quality_monitors: Optional[List[QualityMonitor]] = None
+
+    def as_dict(self) -> dict:
+        """Serializes the ListQualityMonitorResponse into a dictionary suitable for use as a JSON request body."""
+        body = {}
+        if self.next_page_token is not None:
+            body["next_page_token"] = self.next_page_token
+        if self.quality_monitors:
+            body["quality_monitors"] = [v.as_dict() for v in self.quality_monitors]
+        return body
+
+    def as_shallow_dict(self) -> dict:
+        """Serializes the ListQualityMonitorResponse into a shallow dictionary of its immediate attributes."""
+        body = {}
+        if self.next_page_token is not None:
+            body["next_page_token"] = self.next_page_token
+        if self.quality_monitors:
+            body["quality_monitors"] = self.quality_monitors
+        return body
+
+    @classmethod
+    def from_dict(cls, d: Dict[str, Any]) -> ListQualityMonitorResponse:
+        """Deserializes the ListQualityMonitorResponse from a dictionary."""
+        return cls(
+            next_page_token=d.get("next_page_token", None),
+            quality_monitors=_repeated_dict(d, "quality_monitors", QualityMonitor),
+        )
+
+
+@dataclass
+class QualityMonitor:
+    object_type: str
+    """The type of the monitored object. Can be one of the following: schema."""
+
+    object_id: str
+    """The uuid of the request object. For example, schema id."""
+
+    anomaly_detection_config: Optional[AnomalyDetectionConfig] = None
+
+    def as_dict(self) -> dict:
+        """Serializes the QualityMonitor into a dictionary suitable for use as a JSON request body."""
+        body = {}
+        if self.anomaly_detection_config:
+            body["anomaly_detection_config"] = self.anomaly_detection_config.as_dict()
+        if self.object_id is not None:
+            body["object_id"] = self.object_id
+        if self.object_type is not None:
+            body["object_type"] = self.object_type
+        return body
+
+    def as_shallow_dict(self) -> dict:
+        """Serializes the QualityMonitor into a shallow dictionary of its immediate attributes."""
+        body = {}
+        if self.anomaly_detection_config:
+            body["anomaly_detection_config"] = self.anomaly_detection_config
+        if self.object_id is not None:
+            body["object_id"] = self.object_id
+        if self.object_type is not None:
+            body["object_type"] = self.object_type
+        return body
+
+    @classmethod
+    def from_dict(cls, d: Dict[str, Any]) -> QualityMonitor:
+        """Deserializes the QualityMonitor from a dictionary."""
+        return cls(
+            anomaly_detection_config=_from_dict(d, "anomaly_detection_config", AnomalyDetectionConfig),
+            object_id=d.get("object_id", None),
+            object_type=d.get("object_type", None),
+        )
+
+
+class QualityMonitorV2API:
+    """Manage data quality of UC objects (currently support `schema`)"""
+
+    def __init__(self, api_client):
+        self._api = api_client
+
+    def create_quality_monitor(self, quality_monitor: QualityMonitor) -> QualityMonitor:
+        """Create a quality monitor.
+
+        Create a quality monitor on UC object
+
+        :param quality_monitor: :class:`QualityMonitor`
+
+        :returns: :class:`QualityMonitor`
+        """
+        body = quality_monitor.as_dict()
+        headers = {
+            "Accept": "application/json",
+            "Content-Type": "application/json",
+        }
+
+        res = self._api.do("POST", "/api/2.0/quality-monitors", body=body, headers=headers)
+        return QualityMonitor.from_dict(res)
+
+    def delete_quality_monitor(self, object_type: str, object_id: str):
+        """Delete a quality monitor.
+
+        Delete a quality monitor on UC object
+
+        :param object_type: str
+          The type of the monitored object. Can be one of the following: schema.
+        :param object_id: str
+          The uuid of the request object. For example, schema id.
+
+
+        """
+
+        headers = {
+            "Accept": "application/json",
+        }
+
+        self._api.do("DELETE", f"/api/2.0/quality-monitors/{object_type}/{object_id}", headers=headers)
+
+    def get_quality_monitor(self, object_type: str, object_id: str) -> QualityMonitor:
+        """Read a quality monitor.
+
+        Read a quality monitor on UC object
+
+        :param object_type: str
+          The type of the monitored object. Can be one of the following: schema.
+        :param object_id: str
+          The uuid of the request object. For example, schema id.
+
+        :returns: :class:`QualityMonitor`
+        """
+
+        headers = {
+            "Accept": "application/json",
+        }
+
+        res = self._api.do("GET", f"/api/2.0/quality-monitors/{object_type}/{object_id}", headers=headers)
+        return QualityMonitor.from_dict(res)
+
+    def list_quality_monitor(
+        self, *, page_size: Optional[int] = None, page_token: Optional[str] = None
+    ) -> Iterator[QualityMonitor]:
+        """List quality monitors.
+
+        (Unimplemented) List quality monitors
+
+        :param page_size: int (optional)
+        :param page_token: str (optional)
+
+        :returns: Iterator over :class:`QualityMonitor`
+        """
+
+        query = {}
+        if page_size is not None:
+            query["page_size"] = page_size
+        if page_token is not None:
+            query["page_token"] = page_token
+        headers = {
+            "Accept": "application/json",
+        }
+
+        while True:
+            json = self._api.do("GET", "/api/2.0/quality-monitors", query=query, headers=headers)
+            if "quality_monitors" in json:
+                for v in json["quality_monitors"]:
+                    yield QualityMonitor.from_dict(v)
+            if "next_page_token" not in json or not json["next_page_token"]:
+                return
+            query["page_token"] = json["next_page_token"]
+
+    def update_quality_monitor(
+        self, object_type: str, object_id: str, quality_monitor: QualityMonitor
+    ) -> QualityMonitor:
+        """Update a quality monitor.
+
+        (Unimplemented) Update a quality monitor on UC object
+
+        :param object_type: str
+          The type of the monitored object. Can be one of the following: schema.
+        :param object_id: str
+          The uuid of the request object. For example, schema id.
+        :param quality_monitor: :class:`QualityMonitor`
+
+        :returns: :class:`QualityMonitor`
+        """
+        body = quality_monitor.as_dict()
+        headers = {
+            "Accept": "application/json",
+            "Content-Type": "application/json",
+        }
+
+        res = self._api.do("PUT", f"/api/2.0/quality-monitors/{object_type}/{object_id}", body=body, headers=headers)
+        return QualityMonitor.from_dict(res)

databricks/sdk/service/serving.py

@@ -3005,9 +3005,17 @@ class ServedEntityInput:
     instance_profile_arn: Optional[str] = None
     """ARN of the instance profile that the served entity uses to access AWS resources."""
 
+    max_provisioned_concurrency: Optional[int] = None
+    """The maximum provisioned concurrency that the endpoint can scale up to. Do not use if
+    workload_size is specified."""
+
     max_provisioned_throughput: Optional[int] = None
     """The maximum tokens per second that the endpoint can scale up to."""
 
+    min_provisioned_concurrency: Optional[int] = None
+    """The minimum provisioned concurrency that the endpoint can scale down to. Do not use if
+    workload_size is specified."""
+
     min_provisioned_throughput: Optional[int] = None
     """The minimum tokens per second that the endpoint can scale down to."""
 
@@ -3030,7 +3038,7 @@ class ServedEntityInput:
     "Medium" (8 - 16 provisioned concurrency), and "Large" (16 - 64 provisioned concurrency).
     Additional custom workload sizes can also be used when available in the workspace. If
     scale-to-zero is enabled, the lower bound of the provisioned concurrency for each workload size
-    is 0."""
+    is 0. Do not use if min_provisioned_concurrency and max_provisioned_concurrency are specified."""
 
     workload_type: Optional[ServingModelWorkloadType] = None
     """The workload type of the served entity. The workload type selects which type of compute to use
@@ -3053,8 +3061,12 @@ class ServedEntityInput:
             body["external_model"] = self.external_model.as_dict()
         if self.instance_profile_arn is not None:
             body["instance_profile_arn"] = self.instance_profile_arn
+        if self.max_provisioned_concurrency is not None:
+            body["max_provisioned_concurrency"] = self.max_provisioned_concurrency
         if self.max_provisioned_throughput is not None:
             body["max_provisioned_throughput"] = self.max_provisioned_throughput
+        if self.min_provisioned_concurrency is not None:
+            body["min_provisioned_concurrency"] = self.min_provisioned_concurrency
         if self.min_provisioned_throughput is not None:
             body["min_provisioned_throughput"] = self.min_provisioned_throughput
         if self.name is not None:
@@ -3082,8 +3094,12 @@ class ServedEntityInput:
             body["external_model"] = self.external_model
         if self.instance_profile_arn is not None:
             body["instance_profile_arn"] = self.instance_profile_arn
+        if self.max_provisioned_concurrency is not None:
+            body["max_provisioned_concurrency"] = self.max_provisioned_concurrency
         if self.max_provisioned_throughput is not None:
             body["max_provisioned_throughput"] = self.max_provisioned_throughput
+        if self.min_provisioned_concurrency is not None:
+            body["min_provisioned_concurrency"] = self.min_provisioned_concurrency
         if self.min_provisioned_throughput is not None:
             body["min_provisioned_throughput"] = self.min_provisioned_throughput
         if self.name is not None:
@@ -3107,7 +3123,9 @@ class ServedEntityInput:
             environment_vars=d.get("environment_vars", None),
             external_model=_from_dict(d, "external_model", ExternalModel),
             instance_profile_arn=d.get("instance_profile_arn", None),
+            max_provisioned_concurrency=d.get("max_provisioned_concurrency", None),
             max_provisioned_throughput=d.get("max_provisioned_throughput", None),
+            min_provisioned_concurrency=d.get("min_provisioned_concurrency", None),
             min_provisioned_throughput=d.get("min_provisioned_throughput", None),
             name=d.get("name", None),
             provisioned_model_units=d.get("provisioned_model_units", None),
@@ -3152,9 +3170,17 @@ class ServedEntityOutput:
     instance_profile_arn: Optional[str] = None
     """ARN of the instance profile that the served entity uses to access AWS resources."""
 
+    max_provisioned_concurrency: Optional[int] = None
+    """The maximum provisioned concurrency that the endpoint can scale up to. Do not use if
+    workload_size is specified."""
+
     max_provisioned_throughput: Optional[int] = None
     """The maximum tokens per second that the endpoint can scale up to."""
 
+    min_provisioned_concurrency: Optional[int] = None
+    """The minimum provisioned concurrency that the endpoint can scale down to. Do not use if
+    workload_size is specified."""
+
     min_provisioned_throughput: Optional[int] = None
     """The minimum tokens per second that the endpoint can scale down to."""
 
@@ -3179,7 +3205,7 @@ class ServedEntityOutput:
     "Medium" (8 - 16 provisioned concurrency), and "Large" (16 - 64 provisioned concurrency).
     Additional custom workload sizes can also be used when available in the workspace. If
     scale-to-zero is enabled, the lower bound of the provisioned concurrency for each workload size
-    is 0."""
+    is 0. Do not use if min_provisioned_concurrency and max_provisioned_concurrency are specified."""
 
     workload_type: Optional[ServingModelWorkloadType] = None
     """The workload type of the served entity. The workload type selects which type of compute to use
@@ -3208,8 +3234,12 @@ class ServedEntityOutput:
             body["foundation_model"] = self.foundation_model.as_dict()
         if self.instance_profile_arn is not None:
             body["instance_profile_arn"] = self.instance_profile_arn
+        if self.max_provisioned_concurrency is not None:
+            body["max_provisioned_concurrency"] = self.max_provisioned_concurrency
         if self.max_provisioned_throughput is not None:
             body["max_provisioned_throughput"] = self.max_provisioned_throughput
+        if self.min_provisioned_concurrency is not None:
+            body["min_provisioned_concurrency"] = self.min_provisioned_concurrency
         if self.min_provisioned_throughput is not None:
             body["min_provisioned_throughput"] = self.min_provisioned_throughput
         if self.name is not None:
@@ -3245,8 +3275,12 @@ class ServedEntityOutput:
             body["foundation_model"] = self.foundation_model
         if self.instance_profile_arn is not None:
             body["instance_profile_arn"] = self.instance_profile_arn
+        if self.max_provisioned_concurrency is not None:
+            body["max_provisioned_concurrency"] = self.max_provisioned_concurrency
         if self.max_provisioned_throughput is not None:
             body["max_provisioned_throughput"] = self.max_provisioned_throughput
+        if self.min_provisioned_concurrency is not None:
+            body["min_provisioned_concurrency"] = self.min_provisioned_concurrency
         if self.min_provisioned_throughput is not None:
             body["min_provisioned_throughput"] = self.min_provisioned_throughput
         if self.name is not None:
@@ -3275,7 +3309,9 @@ class ServedEntityOutput:
             external_model=_from_dict(d, "external_model", ExternalModel),
             foundation_model=_from_dict(d, "foundation_model", FoundationModel),
             instance_profile_arn=d.get("instance_profile_arn", None),
+            max_provisioned_concurrency=d.get("max_provisioned_concurrency", None),
             max_provisioned_throughput=d.get("max_provisioned_throughput", None),
+            min_provisioned_concurrency=d.get("min_provisioned_concurrency", None),
             min_provisioned_throughput=d.get("min_provisioned_throughput", None),
             name=d.get("name", None),
             provisioned_model_units=d.get("provisioned_model_units", None),
@@ -3360,9 +3396,17 @@ class ServedModelInput:
     instance_profile_arn: Optional[str] = None
     """ARN of the instance profile that the served entity uses to access AWS resources."""
 
+    max_provisioned_concurrency: Optional[int] = None
+    """The maximum provisioned concurrency that the endpoint can scale up to. Do not use if
+    workload_size is specified."""
+
     max_provisioned_throughput: Optional[int] = None
     """The maximum tokens per second that the endpoint can scale up to."""
 
+    min_provisioned_concurrency: Optional[int] = None
+    """The minimum provisioned concurrency that the endpoint can scale down to. Do not use if
+    workload_size is specified."""
+
     min_provisioned_throughput: Optional[int] = None
     """The minimum tokens per second that the endpoint can scale down to."""
 
@@ -3382,7 +3426,7 @@ class ServedModelInput:
     "Medium" (8 - 16 provisioned concurrency), and "Large" (16 - 64 provisioned concurrency).
     Additional custom workload sizes can also be used when available in the workspace. If
     scale-to-zero is enabled, the lower bound of the provisioned concurrency for each workload size
-    is 0."""
+    is 0. Do not use if min_provisioned_concurrency and max_provisioned_concurrency are specified."""
 
     workload_type: Optional[ServedModelInputWorkloadType] = None
     """The workload type of the served entity. The workload type selects which type of compute to use
@@ -3399,8 +3443,12 @@ class ServedModelInput:
             body["environment_vars"] = self.environment_vars
         if self.instance_profile_arn is not None:
             body["instance_profile_arn"] = self.instance_profile_arn
+        if self.max_provisioned_concurrency is not None:
+            body["max_provisioned_concurrency"] = self.max_provisioned_concurrency
         if self.max_provisioned_throughput is not None:
             body["max_provisioned_throughput"] = self.max_provisioned_throughput
+        if self.min_provisioned_concurrency is not None:
+            body["min_provisioned_concurrency"] = self.min_provisioned_concurrency
         if self.min_provisioned_throughput is not None:
             body["min_provisioned_throughput"] = self.min_provisioned_throughput
         if self.model_name is not None:
@@ -3426,8 +3474,12 @@ class ServedModelInput:
             body["environment_vars"] = self.environment_vars
         if self.instance_profile_arn is not None:
             body["instance_profile_arn"] = self.instance_profile_arn
+        if self.max_provisioned_concurrency is not None:
+            body["max_provisioned_concurrency"] = self.max_provisioned_concurrency
         if self.max_provisioned_throughput is not None:
             body["max_provisioned_throughput"] = self.max_provisioned_throughput
+        if self.min_provisioned_concurrency is not None:
+            body["min_provisioned_concurrency"] = self.min_provisioned_concurrency
         if self.min_provisioned_throughput is not None:
             body["min_provisioned_throughput"] = self.min_provisioned_throughput
         if self.model_name is not None:
@@ -3452,7 +3504,9 @@ class ServedModelInput:
         return cls(
             environment_vars=d.get("environment_vars", None),
             instance_profile_arn=d.get("instance_profile_arn", None),
+            max_provisioned_concurrency=d.get("max_provisioned_concurrency", None),
             max_provisioned_throughput=d.get("max_provisioned_throughput", None),
+            min_provisioned_concurrency=d.get("min_provisioned_concurrency", None),
             min_provisioned_throughput=d.get("min_provisioned_throughput", None),
             model_name=d.get("model_name", None),
             model_version=d.get("model_version", None),
@@ -3489,6 +3543,14 @@ class ServedModelOutput:
     instance_profile_arn: Optional[str] = None
     """ARN of the instance profile that the served entity uses to access AWS resources."""
 
+    max_provisioned_concurrency: Optional[int] = None
+    """The maximum provisioned concurrency that the endpoint can scale up to. Do not use if
+    workload_size is specified."""
+
+    min_provisioned_concurrency: Optional[int] = None
+    """The minimum provisioned concurrency that the endpoint can scale down to. Do not use if
+    workload_size is specified."""
+
     model_name: Optional[str] = None
 
     model_version: Optional[str] = None
@@ -3514,7 +3576,7 @@ class ServedModelOutput:
     "Medium" (8 - 16 provisioned concurrency), and "Large" (16 - 64 provisioned concurrency).
     Additional custom workload sizes can also be used when available in the workspace. If
     scale-to-zero is enabled, the lower bound of the provisioned concurrency for each workload size
-    is 0."""
+    is 0. Do not use if min_provisioned_concurrency and max_provisioned_concurrency are specified."""
 
     workload_type: Optional[ServingModelWorkloadType] = None
     """The workload type of the served entity. The workload type selects which type of compute to use
@@ -3535,6 +3597,10 @@ class ServedModelOutput:
             body["environment_vars"] = self.environment_vars
         if self.instance_profile_arn is not None:
             body["instance_profile_arn"] = self.instance_profile_arn
+        if self.max_provisioned_concurrency is not None:
+            body["max_provisioned_concurrency"] = self.max_provisioned_concurrency
+        if self.min_provisioned_concurrency is not None:
+            body["min_provisioned_concurrency"] = self.min_provisioned_concurrency
         if self.model_name is not None:
             body["model_name"] = self.model_name
         if self.model_version is not None:
@@ -3564,6 +3630,10 @@ class ServedModelOutput:
             body["environment_vars"] = self.environment_vars
         if self.instance_profile_arn is not None:
             body["instance_profile_arn"] = self.instance_profile_arn
+        if self.max_provisioned_concurrency is not None:
+            body["max_provisioned_concurrency"] = self.max_provisioned_concurrency
+        if self.min_provisioned_concurrency is not None:
+            body["min_provisioned_concurrency"] = self.min_provisioned_concurrency
         if self.model_name is not None:
             body["model_name"] = self.model_name
         if self.model_version is not None:
@@ -3590,6 +3660,8 @@ class ServedModelOutput:
             creator=d.get("creator", None),
             environment_vars=d.get("environment_vars", None),
             instance_profile_arn=d.get("instance_profile_arn", None),
+            max_provisioned_concurrency=d.get("max_provisioned_concurrency", None),
+            min_provisioned_concurrency=d.get("min_provisioned_concurrency", None),
             model_name=d.get("model_name", None),
             model_version=d.get("model_version", None),
             name=d.get("name", None),