mlrun 1.7.0rc15__py3-none-any.whl → 1.7.0rc17__py3-none-any.whl

mlrun/common/schemas/model_monitoring/constants.py

@@ -156,7 +156,7 @@ class EventKeyMetrics:
     REAL_TIME = "real_time"
 
 
-class TimeSeriesTarget:
+class TimeSeriesConnector:
     TSDB = "tsdb"
 
 
@@ -188,12 +188,14 @@ class SchedulingKeys:
 class FileTargetKind:
     ENDPOINTS = "endpoints"
     EVENTS = "events"
+    PREDICTIONS = "predictions"
     STREAM = "stream"
     PARQUET = "parquet"
     APPS_PARQUET = "apps_parquet"
     LOG_STREAM = "log_stream"
     APP_RESULTS = "app_results"
     MONITORING_SCHEDULES = "monitoring_schedules"
+    MONITORING_APPLICATION = "monitoring_application"
 
 
 class ModelMonitoringMode(str, Enum):
@@ -228,6 +230,12 @@ class MonitoringFunctionNames(MonitoringStrEnum):
     WRITER = "model-monitoring-writer"
 
 
+class MonitoringTSDBTables(MonitoringStrEnum):
+    APP_RESULTS = "app-results"
+    METRICS = "metrics"
+    EVENTS = "events"
+
+
 @dataclass
 class FunctionURI:
     project: str
@@ -329,6 +337,14 @@ class ControllerPolicy:
     BASE_PERIOD = "base_period"
 
 
+class TSDBTarget:
+    V3IO_TSDB = "v3io-tsdb"
+    PROMETHEUS = "prometheus"
+    APP_RESULTS_TABLE = "app-results"
+    V3IO_BE = "tsdb"
+    V3IO_RATE = "1/s"
+
+
 class HistogramDataDriftApplicationConstants:
     NAME = "histogram-data-drift"
     GENERAL_RESULT_NAME = "general_drift"

mlrun/common/schemas/model_monitoring/model_endpoints.py

@@ -14,7 +14,9 @@
 
 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
@@ -29,6 +31,8 @@ from .constants import (
     EventKeyMetrics,
     EventLiveStats,
     ModelMonitoringMode,
+    ResultKindApp,
+    ResultStatusApp,
 )
 
 
@@ -304,6 +308,61 @@ class ModelEndpointMonitoringMetric(BaseModel):
     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>{_FQN_PART_PATTERN})\."
+    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 _ResultPoint(NamedTuple):
+    timestamp: datetime
+    value: float
+    status: ResultStatusApp
+
+
+class _ModelEndpointMonitoringResultValuesBase(BaseModel):
+    full_name: str
+    type: ModelEndpointMonitoringMetricType
+    data: bool
+
+
+class ModelEndpointMonitoringResultValues(_ModelEndpointMonitoringResultValuesBase):
+    full_name: str
+    type: ModelEndpointMonitoringMetricType
+    result_kind: ResultKindApp
+    values: list[_ResultPoint]
+    data: bool = True
+
+
+class ModelEndpointMonitoringResultNoData(_ModelEndpointMonitoringResultValuesBase):
+    full_name: str
+    type: ModelEndpointMonitoringMetricType
+    data: bool = False
+
+
 def _mapping_attributes(
     base_model: BaseModel,
     flattened_dictionary: dict,

mlrun/common/schemas/project.py

@@ -113,7 +113,11 @@ class ProjectSummary(pydantic.BaseModel):
     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
 
 

mlrun/config.py

@@ -232,6 +232,10 @@ default_config = {
         "databricks": {
             "artifact_directory_path": "/mlrun_databricks_runtime/artifacts_dictionaries"
         },
+        "application": {
+            "default_sidecar_internal_port": 8050,
+            "default_authentication_mode": "accessKey",
+        },
     },
     # TODO: function defaults should be moved to the function spec config above
     "function_defaults": {
@@ -503,6 +507,7 @@ default_config = {
             "default": "v3io:///users/pipelines/{project}/model-endpoints/{kind}",
             "user_space": "v3io:///projects/{project}/model-endpoints/{kind}",
             "stream": "",
+            "monitoring_application": "v3io:///users/pipelines/{project}/monitoring-apps/",
         },
         # Offline storage path can be either relative or a full path. This path is used for general offline data
         # storage such as the parquet file which is generated from the monitoring stream function for the drift analysis
@@ -516,6 +521,7 @@ default_config = {
         # See mlrun.model_monitoring.db.stores.ObjectStoreFactory for available options
         "store_type": "v3io-nosql",
         "endpoint_store_connection": "",
+        "tsdb_connector_type": "v3io-tsdb",
     },
     "secret_stores": {
         # Use only in testing scenarios (such as integration tests) to avoid using k8s for secrets (will use in-memory
@@ -1088,6 +1094,7 @@ class Config:
         target: str = "online",
         artifact_path: str = None,
         function_name: str = None,
+        **kwargs,
     ) -> typing.Union[str, list[str]]:
         """Get the full path from the configuration based on the provided project and kind.
 
@@ -1114,7 +1121,7 @@ class Config:
             )
             if store_prefix_dict.get(kind):
                 # Target exist in store prefix and has a valid string value
-                return store_prefix_dict[kind].format(project=project)
+                return store_prefix_dict[kind].format(project=project, **kwargs)
 
             if (
                 function_name
@@ -1399,14 +1406,14 @@ def read_env(env=None, prefix=env_prefix):
     if log_formatter_name := config.get("log_formatter"):
         import mlrun.utils.logger
 
-        log_formatter = mlrun.utils.create_formatter_instance(
+        log_formatter = mlrun.utils.resolve_formatter_by_kind(
             mlrun.utils.FormatterKinds(log_formatter_name)
         )
         current_handler = mlrun.utils.logger.get_handler("default")
         current_formatter_name = current_handler.formatter.__class__.__name__
-        desired_formatter_name = log_formatter.__class__.__name__
+        desired_formatter_name = log_formatter.__name__
         if current_formatter_name != desired_formatter_name:
-            current_handler.setFormatter(log_formatter)
+            current_handler.setFormatter(log_formatter())
 
     # The default function pod resource values are of type str; however, when reading from environment variable numbers,
     # it converts them to type int if contains only number, so we want to convert them to str.

mlrun/datastore/datastore_profile.py

@@ -188,6 +188,7 @@ class DatastoreProfileS3(DatastoreProfile):
     bucket: typing.Optional[str] = None
 
     @pydantic.validator("bucket")
+    @classmethod
     def check_bucket(cls, v):
         if not v:
             warnings.warn(
@@ -292,6 +293,7 @@ class DatastoreProfileGCS(DatastoreProfile):
     bucket: typing.Optional[str] = None
 
     @pydantic.validator("bucket")
+    @classmethod
     def check_bucket(cls, v):
         if not v:
             warnings.warn(
@@ -344,13 +346,14 @@ class DatastoreProfileAzureBlob(DatastoreProfile):
     client_secret: typing.Optional[str] = None
     sas_token: typing.Optional[str] = None
     credential: typing.Optional[str] = None
-    bucket: typing.Optional[str] = None
+    container: typing.Optional[str] = None
 
-    @pydantic.validator("bucket")
-    def check_bucket(cls, v):
+    @pydantic.validator("container")
+    @classmethod
+    def check_container(cls, v):
         if not v:
             warnings.warn(
-                "The 'bucket' attribute will be mandatory starting from version 1.9",
+                "The 'container' attribute will be mandatory starting from version 1.9",
                 FutureWarning,
                 stacklevel=2,
             )
@@ -358,10 +361,10 @@ class DatastoreProfileAzureBlob(DatastoreProfile):
 
     def url(self, subpath) -> str:
         if subpath.startswith("/"):
-            #  in azure the path after schema is starts with bucket, wherefore it should not start with "/".
+            #  in azure the path after schema is starts with container, wherefore it should not start with "/".
             subpath = subpath[1:]
-        if self.bucket:
-            return f"az://{self.bucket}/{subpath}"
+        if self.container:
+            return f"az://{self.container}/{subpath}"
         else:
             return f"az://{subpath}"
 

mlrun/db/base.py

@@ -16,6 +16,7 @@ import datetime
 from abc import ABC, abstractmethod
 from typing import Optional, Union
 
+import mlrun.alerts
 import mlrun.common.schemas
 import mlrun.model_monitoring
 
@@ -117,7 +118,18 @@ class RunDBInterface(ABC):
         pass
 
     @abstractmethod
-    def del_artifact(self, key, tag="", project="", tree=None, uid=None):
+    def del_artifact(
+        self,
+        key,
+        tag="",
+        project="",
+        tree=None,
+        uid=None,
+        deletion_strategy: mlrun.common.schemas.artifact.ArtifactsDeletionStrategies = (
+            mlrun.common.schemas.artifact.ArtifactsDeletionStrategies.metadata_only
+        ),
+        secrets: dict = None,
+    ):
         pass
 
     @abstractmethod
@@ -543,7 +555,7 @@ class RunDBInterface(ABC):
         end: Optional[str] = None,
         metrics: Optional[list[str]] = None,
         features: bool = False,
-    ):
+    ) -> mlrun.model_monitoring.ModelEndpoint:
         pass
 
     @abstractmethod
@@ -617,8 +629,8 @@ class RunDBInterface(ABC):
     @abstractmethod
     def store_api_gateway(
         self,
-        project: str,
         api_gateway: mlrun.common.schemas.APIGateway,
+        project: str = None,
     ):
         pass
 
@@ -664,7 +676,7 @@ class RunDBInterface(ABC):
     def store_alert_config(
         self,
         alert_name: str,
-        alert_data: Union[dict, mlrun.common.schemas.AlertConfig],
+        alert_data: Union[dict, mlrun.alerts.alert.AlertConfig],
         project="",
     ):
         pass
@@ -685,6 +697,14 @@ class RunDBInterface(ABC):
     def reset_alert_config(self, alert_name: str, project=""):
         pass
 
+    @abstractmethod
+    def get_alert_template(self, template_name: str):
+        pass
+
+    @abstractmethod
+    def list_alert_templates(self):
+        pass
+
     @abstractmethod
     def get_builder_status(
         self,

mlrun/db/httpdb.py

@@ -15,7 +15,6 @@
 import enum
 import http
 import re
-import tempfile
 import time
 import traceback
 import typing
@@ -26,9 +25,9 @@ from os import path, remove
 from typing import Optional, Union
 from urllib.parse import urlparse
 
-import kfp
 import requests
 import semver
+from mlrun_pipelines.utils import compile_pipeline
 
 import mlrun
 import mlrun.common.schemas
@@ -38,6 +37,7 @@ import mlrun.platforms
 import mlrun.projects
 import mlrun.runtimes.nuclio.api_gateway
 import mlrun.utils
+from mlrun.alerts.alert import AlertConfig
 from mlrun.db.auth_utils import OAuthClientIDTokenProvider, StaticTokenProvider
 from mlrun.errors import MLRunInvalidArgumentError, err_to_str
 
@@ -51,7 +51,6 @@ from ..utils import (
     datetime_to_iso,
     dict_to_json,
     logger,
-    new_pipe_metadata,
     normalize_name,
     version,
 )
@@ -590,7 +589,7 @@ class HTTPRunDB(RunDBInterface):
         if offset < 0:
             raise MLRunInvalidArgumentError("Offset cannot be negative")
         if size is None:
-            size = int(config.httpdb.logs.pull_logs_default_size_limit)
+            size = int(mlrun.mlconf.httpdb.logs.pull_logs_default_size_limit)
         elif size == -1:
             logger.warning(
                 "Retrieving all logs. This may be inefficient and can result in a large log."
@@ -636,23 +635,25 @@ class HTTPRunDB(RunDBInterface):
 
         state, text = self.get_log(uid, project, offset=offset)
         if text:
-            print(text.decode(errors=config.httpdb.logs.decode.errors))
+            print(text.decode(errors=mlrun.mlconf.httpdb.logs.decode.errors))
         nil_resp = 0
         while True:
             offset += len(text)
             # if we get 3 nil responses in a row, increase the sleep time to 10 seconds
             # TODO: refactor this to use a conditional backoff mechanism
             if nil_resp < 3:
-                time.sleep(int(config.httpdb.logs.pull_logs_default_interval))
+                time.sleep(int(mlrun.mlconf.httpdb.logs.pull_logs_default_interval))
             else:
                 time.sleep(
-                    int(config.httpdb.logs.pull_logs_backoff_no_logs_default_interval)
+                    int(
+                        mlrun.mlconf.httpdb.logs.pull_logs_backoff_no_logs_default_interval
+                    )
                 )
             state, text = self.get_log(uid, project, offset=offset)
             if text:
                 nil_resp = 0
                 print(
-                    text.decode(errors=config.httpdb.logs.decode.errors),
+                    text.decode(errors=mlrun.mlconf.httpdb.logs.decode.errors),
                     end="",
                 )
             else:
@@ -985,7 +986,18 @@ class HTTPRunDB(RunDBInterface):
         resp = self.api_call("GET", endpoint_path, error, params=params, version="v2")
         return resp.json()
 
-    def del_artifact(self, key, tag=None, project="", tree=None, uid=None):
+    def del_artifact(
+        self,
+        key,
+        tag=None,
+        project="",
+        tree=None,
+        uid=None,
+        deletion_strategy: mlrun.common.schemas.artifact.ArtifactsDeletionStrategies = (
+            mlrun.common.schemas.artifact.ArtifactsDeletionStrategies.metadata_only
+        ),
+        secrets: dict = None,
+    ):
         """Delete an artifact.
 
         :param key: Identifying key of the artifact.
@@ -993,6 +1005,8 @@ class HTTPRunDB(RunDBInterface):
         :param project: Project that the artifact belongs to.
         :param tree: The tree which generated this artifact.
         :param uid: A unique ID for this specific version of the artifact (the uid that was generated in the backend)
+        :param deletion_strategy: The artifact deletion strategy types.
+        :param secrets: Credentials needed to access the artifact data.
         """
 
         endpoint_path = f"projects/{project}/artifacts/{key}"
@@ -1001,9 +1015,17 @@ class HTTPRunDB(RunDBInterface):
             "tag": tag,
             "tree": tree,
             "uid": uid,
+            "deletion_strategy": deletion_strategy,
         }
         error = f"del artifact {project}/{key}"
-        self.api_call("DELETE", endpoint_path, error, params=params, version="v2")
+        self.api_call(
+            "DELETE",
+            endpoint_path,
+            error,
+            params=params,
+            version="v2",
+            body=dict_to_json(secrets),
+        )
 
     def list_artifacts(
         self,
@@ -1018,6 +1040,7 @@ class HTTPRunDB(RunDBInterface):
         kind: str = None,
         category: Union[str, mlrun.common.schemas.ArtifactCategories] = None,
         tree: str = None,
+        producer_uri: str = None,
     ) -> ArtifactList:
         """List artifacts filtered by various parameters.
 
@@ -1046,9 +1069,12 @@ class HTTPRunDB(RunDBInterface):
         :param best_iteration: Returns the artifact which belongs to the best iteration of a given run, in the case of
             artifacts generated from a hyper-param run. If only a single iteration exists, will return the artifact
             from that iteration. If using ``best_iter``, the ``iter`` parameter must not be used.
-        :param kind: Return artifacts of the requested kind.
-        :param category: Return artifacts of the requested category.
-        :param tree: Return artifacts of the requested tree.
+        :param kind:            Return artifacts of the requested kind.
+        :param category:        Return artifacts of the requested category.
+        :param tree:            Return artifacts of the requested tree.
+        :param producer_uri:    Return artifacts produced by the requested producer URI. Producer URI usually
+            points to a run and is used to filter artifacts by the run that produced them when the artifact producer id
+            is a workflow id (artifact was created as part of a workflow).
         """
 
         project = project or config.default_project
@@ -1067,6 +1093,7 @@ class HTTPRunDB(RunDBInterface):
             "category": category,
             "tree": tree,
             "format": mlrun.common.schemas.ArtifactsFormat.full.value,
+            "producer_uri": producer_uri,
         }
         error = "list artifacts"
         endpoint_path = f"projects/{project}/artifacts"
@@ -1828,14 +1855,11 @@ class HTTPRunDB(RunDBInterface):
         if isinstance(pipeline, str):
             pipe_file = pipeline
         else:
-            pipe_file = tempfile.NamedTemporaryFile(suffix=".yaml", delete=False).name
-            conf = new_pipe_metadata(
+            pipe_file = compile_pipeline(
                 artifact_path=artifact_path,
                 cleanup_ttl=cleanup_ttl,
-                op_transformers=ops,
-            )
-            kfp.compiler.Compiler().compile(
-                pipeline, pipe_file, type_check=False, pipeline_conf=conf
+                ops=ops,
+                pipeline=pipeline,
             )
 
         if pipe_file.endswith(".yaml"):
@@ -3112,14 +3136,12 @@ class HTTPRunDB(RunDBInterface):
         :param labels: A list of labels to filter by. Label filters work by either filtering a specific value of a
          label (i.e. list("key=value")) or by looking for the existence of a given key (i.e. "key")
         :param metrics: A list of metrics to return for each endpoint, read more in 'TimeMetric'
-        :param start: The start time of the metrics. Can be represented by a string containing an RFC 3339
-                                 time, a Unix timestamp in milliseconds, a relative time (`'now'` or
-                                 `'now-[0-9]+[mhd]'`, where `m` = minutes, `h` = hours, and `'d'` =
-                                 days), or 0 for the earliest time.
-        :param end: The end time of the metrics. Can be represented by a string containing an RFC 3339
-                                 time, a Unix timestamp in milliseconds, a relative time (`'now'` or
-                                 `'now-[0-9]+[mhd]'`, where `m` = minutes, `h` = hours, and `'d'` =
-                                 days), or 0 for the earliest time.
+        :param start: The start time of the metrics. Can be represented by a string containing an RFC 3339 time, a
+                      Unix timestamp in milliseconds, a relative time (`'now'` or `'now-[0-9]+[mhd]'`, where
+                      `m` = minutes, `h` = hours, `'d'` = days, and `'s'` = seconds), or 0 for the earliest time.
+        :param end: The end time of the metrics. Can be represented by a string containing an RFC 3339 time, a
+                      Unix timestamp in milliseconds, a relative time (`'now'` or `'now-[0-9]+[mhd]'`, where
+                      `m` = minutes, `h` = hours, `'d'` = days, and `'s'` = seconds), or 0 for the earliest time.
         :param top_level: if true will return only routers and endpoint that are NOT children of any router
         :param uids: if passed will return a list `ModelEndpoint` object with uid in uids
         """
@@ -3168,13 +3190,13 @@ class HTTPRunDB(RunDBInterface):
         :param project:                    The name of the project
         :param endpoint_id:                The unique id of the model endpoint.
         :param start:                      The start time of the metrics. Can be represented by a string containing an
-                                           RFC 3339 time, a Unix timestamp in milliseconds, a relative time (`'now'` or
-                                           `'now-[0-9]+[mhd]'`, where `m` = minutes, `h` = hours, and `'d'` = days), or
-                                           0 for the earliest time.
+                                           RFC 3339 time, a  Unix timestamp in milliseconds, a relative time
+                                           (`'now'` or `'now-[0-9]+[mhd]'`, where `m` = minutes, `h` = hours,
+                                           `'d'` = days, and `'s'` = seconds), or 0 for the earliest time.
         :param end:                        The end time of the metrics. Can be represented by a string containing an
-                                           RFC 3339 time, a Unix timestamp in milliseconds, a relative time (`'now'` or
-                                           `'now-[0-9]+[mhd]'`, where `m` = minutes, `h` = hours, and `'d'` = days), or
-                                           0 for the earliest time.
+                                           RFC 3339 time, a  Unix timestamp in milliseconds, a relative time
+                                           (`'now'` or `'now-[0-9]+[mhd]'`, where `m` = minutes, `h` = hours,
+                                           `'d'` = days, and `'s'` = seconds), or 0 for the earliest time.
         :param metrics:                    A list of metrics to return for the model endpoint. There are pre-defined
                                            metrics for model endpoints such as predictions_per_second and
                                            latency_avg_5m but also custom metrics defined by the user. Please note that
@@ -3915,7 +3937,7 @@ class HTTPRunDB(RunDBInterface):
             logger.warning(
                 "Building a function image to ECR and loading an S3 source to the image may require conflicting access "
                 "keys. Only the permissions granted to the platform's configured secret will take affect "
-                "(see mlrun.config.config.httpdb.builder.docker_registry_secret). "
+                "(see mlrun.mlconf.httpdb.builder.docker_registry_secret). "
                 "In case the permissions are limited to ECR scope, you may use pull_at_runtime=True instead",
                 source=func.spec.build.source,
                 load_source_on_run=func.spec.build.load_source_on_run,
@@ -3943,9 +3965,9 @@ class HTTPRunDB(RunDBInterface):
     def store_alert_config(
         self,
         alert_name: str,
-        alert_data: Union[dict, mlrun.common.schemas.AlertConfig],
+        alert_data: Union[dict, AlertConfig],
         project="",
-    ):
+    ) -> AlertConfig:
         """
         Create/modify an alert.
         :param alert_name: The name of the alert.
@@ -3956,13 +3978,19 @@ class HTTPRunDB(RunDBInterface):
         project = project or config.default_project
         endpoint_path = f"projects/{project}/alerts/{alert_name}"
         error_message = f"put alert {project}/alerts/{alert_name}"
-        if isinstance(alert_data, mlrun.common.schemas.AlertConfig):
-            alert_data = alert_data.dict()
+        alert_instance = (
+            alert_data
+            if isinstance(alert_data, AlertConfig)
+            else AlertConfig.from_dict(alert_data)
+        )
+        alert_instance.validate_required_fields()
+
+        alert_data = alert_instance.to_dict()
         body = _as_json(alert_data)
         response = self.api_call("PUT", endpoint_path, error_message, body=body)
-        return mlrun.common.schemas.AlertConfig(**response.json())
+        return AlertConfig.from_dict(response.json())
 
-    def get_alert_config(self, alert_name: str, project=""):
+    def get_alert_config(self, alert_name: str, project="") -> AlertConfig:
         """
         Retrieve an alert.
         :param alert_name: The name of the alert to retrieve.
@@ -3973,9 +4001,9 @@ class HTTPRunDB(RunDBInterface):
         endpoint_path = f"projects/{project}/alerts/{alert_name}"
         error_message = f"get alert {project}/alerts/{alert_name}"
         response = self.api_call("GET", endpoint_path, error_message)
-        return mlrun.common.schemas.AlertConfig(**response.json())
+        return AlertConfig.from_dict(response.json())
 
-    def list_alerts_configs(self, project=""):
+    def list_alerts_configs(self, project="") -> list[AlertConfig]:
         """
         Retrieve list of alerts of a project.
         :param project: The project name.
@@ -3987,7 +4015,7 @@ class HTTPRunDB(RunDBInterface):
         response = self.api_call("GET", endpoint_path, error_message).json()
         results = []
         for item in response:
-            results.append(mlrun.common.schemas.AlertConfig(**item))
+            results.append(AlertConfig(**item))
         return results
 
     def delete_alert_config(self, alert_name: str, project=""):
@@ -4012,6 +4040,32 @@ class HTTPRunDB(RunDBInterface):
         error_message = f"post alert {project}/alerts/{alert_name}/reset"
         self.api_call("POST", endpoint_path, error_message)
 
+    def get_alert_template(
+        self, template_name: str
+    ) -> mlrun.common.schemas.AlertTemplate:
+        """
+        Retrieve a specific alert template.
+        :param template_name: The name of the template to retrieve.
+        :return: The template object.
+        """
+        endpoint_path = f"alert-templates/{template_name}"
+        error_message = f"get template alert-templates/{template_name}"
+        response = self.api_call("GET", endpoint_path, error_message)
+        return mlrun.common.schemas.AlertTemplate(**response.json())
+
+    def list_alert_templates(self) -> list[mlrun.common.schemas.AlertTemplate]:
+        """
+        Retrieve list of all alert templates.
+        :return: All the alert template objects in the database.
+        """
+        endpoint_path = "alert-templates"
+        error_message = "get templates /alert-templates"
+        response = self.api_call("GET", endpoint_path, error_message).json()
+        results = []
+        for item in response:
+            results.append(mlrun.common.schemas.AlertTemplate(**item))
+        return results
+
 
 def _as_json(obj):
     fn = getattr(obj, "to_json", None)