mlrun 1.7.0rc26__py3-none-any.whl → 1.7.0rc31__py3-none-any.whl

mlrun/serving/routers.py

@@ -1030,74 +1030,90 @@ def _init_endpoint_record(
         function_uri=graph_server.function_uri, versioned_model=versioned_model_name
     ).uid
 
-    # If model endpoint object was found in DB, skip the creation process.
     try:
-        mlrun.get_run_db().get_model_endpoint(project=project, endpoint_id=endpoint_uid)
-
+        model_ep = mlrun.get_run_db().get_model_endpoint(
+            project=project, endpoint_id=endpoint_uid
+        )
     except mlrun.errors.MLRunNotFoundError:
-        logger.info("Creating a new model endpoint record", endpoint_id=endpoint_uid)
+        model_ep = None
+    except mlrun.errors.MLRunBadRequestError as err:
+        logger.debug(
+            f"Cant reach to model endpoints store, due to  : {err}",
+        )
+        return
 
-        try:
-            # Get the children model endpoints ids
-            children_uids = []
-            for _, c in voting_ensemble.routes.items():
-                if hasattr(c, "endpoint_uid"):
-                    children_uids.append(c.endpoint_uid)
-
-            model_endpoint = mlrun.common.schemas.ModelEndpoint(
-                metadata=mlrun.common.schemas.ModelEndpointMetadata(
-                    project=project, uid=endpoint_uid
-                ),
-                spec=mlrun.common.schemas.ModelEndpointSpec(
-                    function_uri=graph_server.function_uri,
-                    model=versioned_model_name,
-                    model_class=voting_ensemble.__class__.__name__,
-                    stream_path=config.model_endpoint_monitoring.store_prefixes.default.format(
-                        project=project, kind="stream"
-                    ),
-                    active=True,
-                    monitoring_mode=mlrun.common.schemas.model_monitoring.ModelMonitoringMode.enabled
-                    if voting_ensemble.context.server.track_models
-                    else mlrun.common.schemas.model_monitoring.ModelMonitoringMode.disabled,
-                ),
-                status=mlrun.common.schemas.ModelEndpointStatus(
-                    children=list(voting_ensemble.routes.keys()),
-                    endpoint_type=mlrun.common.schemas.model_monitoring.EndpointType.ROUTER,
-                    children_uids=children_uids,
+    if voting_ensemble.context.server.track_models and not model_ep:
+        logger.info("Creating a new model endpoint record", endpoint_id=endpoint_uid)
+        # Get the children model endpoints ids
+        children_uids = []
+        for _, c in voting_ensemble.routes.items():
+            if hasattr(c, "endpoint_uid"):
+                children_uids.append(c.endpoint_uid)
+        model_endpoint = mlrun.common.schemas.ModelEndpoint(
+            metadata=mlrun.common.schemas.ModelEndpointMetadata(
+                project=project, uid=endpoint_uid
+            ),
+            spec=mlrun.common.schemas.ModelEndpointSpec(
+                function_uri=graph_server.function_uri,
+                model=versioned_model_name,
+                model_class=voting_ensemble.__class__.__name__,
+                stream_path=config.model_endpoint_monitoring.store_prefixes.default.format(
+                    project=project, kind="stream"
                 ),
-            )
+                active=True,
+                monitoring_mode=mlrun.common.schemas.model_monitoring.ModelMonitoringMode.enabled,
+            ),
+            status=mlrun.common.schemas.ModelEndpointStatus(
+                children=list(voting_ensemble.routes.keys()),
+                endpoint_type=mlrun.common.schemas.model_monitoring.EndpointType.ROUTER,
+                children_uids=children_uids,
+            ),
+        )
 
-            db = mlrun.get_run_db()
+        db = mlrun.get_run_db()
+
+        db.create_model_endpoint(
+            project=project,
+            endpoint_id=model_endpoint.metadata.uid,
+            model_endpoint=model_endpoint.dict(),
+        )
 
+        # Update model endpoint children type
+        for model_endpoint in children_uids:
+            current_endpoint = db.get_model_endpoint(
+                project=project, endpoint_id=model_endpoint
+            )
+            current_endpoint.status.endpoint_type = (
+                mlrun.common.schemas.model_monitoring.EndpointType.LEAF_EP
+            )
             db.create_model_endpoint(
                 project=project,
-                endpoint_id=model_endpoint.metadata.uid,
-                model_endpoint=model_endpoint.dict(),
-            )
-
-            # Update model endpoint children type
-            for model_endpoint in children_uids:
-                current_endpoint = db.get_model_endpoint(
-                    project=project, endpoint_id=model_endpoint
-                )
-                current_endpoint.status.endpoint_type = (
-                    mlrun.common.schemas.model_monitoring.EndpointType.LEAF_EP
-                )
-                db.create_model_endpoint(
-                    project=project,
-                    endpoint_id=model_endpoint,
-                    model_endpoint=current_endpoint,
-                )
-
-        except Exception as exc:
-            logger.warning(
-                "Failed creating model endpoint record",
-                exc=err_to_str(exc),
-                traceback=traceback.format_exc(),
+                endpoint_id=model_endpoint,
+                model_endpoint=current_endpoint,
             )
-
-    except Exception as e:
-        logger.error("Failed to retrieve model endpoint object", exc=err_to_str(e))
+    elif (
+        model_ep
+        and (
+            model_ep.spec.monitoring_mode
+            == mlrun.common.schemas.model_monitoring.ModelMonitoringMode.enabled
+        )
+        != voting_ensemble.context.server.track_models
+    ):
+        monitoring_mode = (
+            mlrun.common.schemas.model_monitoring.ModelMonitoringMode.enabled
+            if voting_ensemble.context.server.track_models
+            else mlrun.common.schemas.model_monitoring.ModelMonitoringMode.disabled
+        )
+        db = mlrun.get_run_db()
+        db.patch_model_endpoint(
+            project=project,
+            endpoint_id=endpoint_uid,
+            attributes={"monitoring_mode": monitoring_mode},
+        )
+        logger.debug(
+            f"Updating model endpoint monitoring_mode to {monitoring_mode}",
+            endpoint_id=endpoint_uid,
+        )
 
     return endpoint_uid
 

mlrun/serving/server.py

@@ -390,6 +390,7 @@ def v2_serving_handler(context, event, get_body=False):
         "kafka",
         "kafka-cluster",
         "v3ioStream",
+        "v3io-stream",
     ):
         event.path = "/"
 

mlrun/serving/v2_serving.py

@@ -531,7 +531,9 @@ def _init_endpoint_record(
     if model.model_path and model.model_path.startswith("store://"):
         # Enrich the model server with the model artifact metadata
         model.get_model()
-        model.version = model.model_spec.tag
+        if not model.version:
+            # Enrich the model version with the model artifact tag
+            model.version = model.model_spec.tag
         model.labels = model.model_spec.labels
         versioned_model_name = f"{model.name}:{model.version}"
     else:
@@ -548,6 +550,11 @@ def _init_endpoint_record(
         )
     except mlrun.errors.MLRunNotFoundError:
         model_ep = None
+    except mlrun.errors.MLRunBadRequestError as err:
+        logger.debug(
+            f"Cant reach to model endpoints store, due to  : {err}",
+        )
+        return
 
     if model.context.server.track_models and not model_ep:
         logger.debug("Creating a new model endpoint record", endpoint_id=uid)

mlrun/utils/helpers.py

@@ -109,10 +109,13 @@ def get_artifact_target(item: dict, project=None):
     db_key = item["spec"].get("db_key")
     project_str = project or item["metadata"].get("project")
     tree = item["metadata"].get("tree")
+    tag = item["metadata"].get("tag")
 
     kind = item.get("kind")
     if kind in ["dataset", "model", "artifact"] and db_key:
         target = f"{DB_SCHEMA}://{StorePrefix.Artifact}/{project_str}/{db_key}"
+        if tag:
+            target = f"{target}:{tag}"
         if tree:
             target = f"{target}@{tree}"
         return target
@@ -149,7 +152,7 @@ if is_ipython and config.nest_asyncio_enabled in ["1", "True"]:
     nest_asyncio.apply()
 
 
-class run_keys:
+class RunKeys:
     input_path = "input_path"
     output_path = "output_path"
     inputs = "inputs"
@@ -160,6 +163,10 @@ class run_keys:
     secrets = "secret_sources"
 
 
+# for Backward compatibility
+run_keys = RunKeys
+
+
 def verify_field_regex(
     field_name,
     field_value,
@@ -812,7 +819,6 @@ def enrich_image_url(
     tag += resolve_image_tag_suffix(
         mlrun_version=mlrun_version, python_version=client_python_version
     )
-    registry = config.images_registry
 
     # it's an mlrun image if the repository is mlrun
     is_mlrun_image = image_url.startswith("mlrun/") or "/mlrun/" in image_url
@@ -820,6 +826,10 @@ def enrich_image_url(
     if is_mlrun_image and tag and ":" not in image_url:
         image_url = f"{image_url}:{tag}"
 
+    registry = (
+        config.images_registry if is_mlrun_image else config.vendor_images_registry
+    )
+
     enrich_registry = False
     # enrich registry only if images_to_enrich_registry provided
     # example: "^mlrun/*" means enrich only if the image repository is mlrun and registry is not specified (in which
@@ -1259,6 +1269,10 @@ def _fill_project_path_template(artifact_path, project):
     return artifact_path
 
 
+def to_non_empty_values_dict(input_dict: dict) -> dict:
+    return {key: value for key, value in input_dict.items() if value}
+
+
 def str_to_timestamp(time_str: str, now_time: Timestamp = None):
     """convert fixed/relative time string to Pandas Timestamp
 
@@ -1606,6 +1620,30 @@ def additional_filters_warning(additional_filters, class_name):
         )
 
 
+def merge_with_precedence(first_dict: dict, second_dict: dict) -> dict:
+    """
+    Merge two dictionaries with precedence given to keys from the second dictionary.
+
+    This function merges two dictionaries, `first_dict` and `second_dict`, where keys from `second_dict`
+    take precedence in case of conflicts. If both dictionaries contain the same key,
+    the value from `second_dict` will overwrite the value from `first_dict`.
+
+    Example:
+        >>> first_dict = {"key1": "value1", "key2": "value2"}
+        >>> second_dict = {"key2": "new_value2", "key3": "value3"}
+        >>> merge_with_precedence(first_dict, second_dict)
+        {'key1': 'value1', 'key2': 'new_value2', 'key3': 'value3'}
+
+    Note:
+    - The merge operation uses the ** operator in Python, which combines key-value pairs
+      from each dictionary. Later dictionaries take precedence when there are conflicting keys.
+    """
+    return {
+        **(first_dict or {}),
+        **(second_dict or {}),
+    }
+
+
 def validate_component_version_compatibility(
     component_name: typing.Literal["iguazio", "nuclio"], *min_versions: str
 ):
@@ -1663,6 +1701,12 @@ def format_alert_summary(
     return result
 
 
+def is_parquet_file(file_path, format_=None):
+    return (file_path and file_path.endswith((".parquet", ".pq"))) or (
+        format_ == "parquet"
+    )
+
+
 def _reload(module, max_recursion_depth):
     """Recursively reload modules."""
     if max_recursion_depth <= 0:

mlrun/utils/logger.py

@@ -13,8 +13,10 @@
 # limitations under the License.
 
 import logging
+import os
 import typing
 from enum import Enum
+from functools import cached_property
 from sys import stdout
 from traceback import format_exception
 from typing import IO, Optional, Union
@@ -92,6 +94,16 @@ class HumanReadableFormatter(_BaseFormatter):
 
 
 class HumanReadableExtendedFormatter(HumanReadableFormatter):
+    _colors = {
+        logging.NOTSET: "",
+        logging.DEBUG: "\x1b[34m",
+        logging.INFO: "\x1b[36m",
+        logging.WARNING: "\x1b[33m",
+        logging.ERROR: "\x1b[0;31m",
+        logging.CRITICAL: "\x1b[1;31m",
+    }
+    _color_reset = "\x1b[0m"
+
     def format(self, record) -> str:
         more = ""
         record_with = self._record_with(record)
@@ -113,12 +125,34 @@ class HumanReadableExtendedFormatter(HumanReadableFormatter):
                 [f"{key}: {_format_value(val)}" for key, val in record_with.items()]
             )
         return (
-            "> "
+            f"{self._get_message_color(record.levelno)}> "
             f"{self.formatTime(record, self.datefmt)} "
             f"[{record.name}:{record.levelname.lower()}] "
-            f"{record.getMessage()}{more}"
+            f"{record.getMessage()}{more}{self._get_color_reset()}"
         )
 
+    def _get_color_reset(self):
+        if not self._have_color_support:
+            return ""
+
+        return self._color_reset
+
+    def _get_message_color(self, levelno):
+        if not self._have_color_support:
+            return ""
+
+        return self._colors[levelno]
+
+    @cached_property
+    def _have_color_support(self):
+        if os.environ.get("PYCHARM_HOSTED"):
+            return True
+        if os.environ.get("NO_COLOR"):
+            return False
+        if os.environ.get("CLICOLOR_FORCE"):
+            return True
+        return stdout.isatty()
+
 
 class Logger:
     def __init__(

mlrun/utils/notifications/notification/base.py

@@ -28,6 +28,10 @@ class NotificationBase:
         self.name = name
         self.params = params or {}
 
+    @classmethod
+    def validate_params(cls, params):
+        pass
+
     @property
     def active(self) -> bool:
         return True

mlrun/utils/notifications/notification/git.py

@@ -30,6 +30,27 @@ class GitNotification(NotificationBase):
     API/Client notification for setting a rich run statuses git issue comment (github/gitlab)
     """
 
+    @classmethod
+    def validate_params(cls, params):
+        git_repo = params.get("repo", None)
+        git_issue = params.get("issue", None)
+        git_merge_request = params.get("merge_request", None)
+        token = (
+            params.get("token", None)
+            or params.get("GIT_TOKEN", None)
+            or params.get("GITHUB_TOKEN", None)
+        )
+        if not git_repo:
+            raise ValueError("Parameter 'repo' is required for GitNotification")
+
+        if not token:
+            raise ValueError("Parameter 'token' is required for GitNotification")
+
+        if not git_issue and not git_merge_request:
+            raise ValueError(
+                "At least one of 'issue' or 'merge_request' is required for GitNotification"
+            )
+
     async def push(
         self,
         message: str,

mlrun/utils/notifications/notification/slack.py

@@ -35,6 +35,14 @@ class SlackNotification(NotificationBase):
         "skipped": ":zzz:",
     }
 
+    @classmethod
+    def validate_params(cls, params):
+        webhook = params.get("webhook", None) or mlrun.get_secret_or_env(
+            "SLACK_WEBHOOK"
+        )
+        if not webhook:
+            raise ValueError("Parameter 'webhook' is required for SlackNotification")
+
     async def push(
         self,
         message: str,

mlrun/utils/notifications/notification/webhook.py

@@ -28,6 +28,12 @@ class WebhookNotification(NotificationBase):
     API/Client notification for sending run statuses in a http request
     """
 
+    @classmethod
+    def validate_params(cls, params):
+        url = params.get("url", None)
+        if not url:
+            raise ValueError("Parameter 'url' is required for WebhookNotification")
+
     async def push(
         self,
         message: str,
@@ -63,7 +69,7 @@ class WebhookNotification(NotificationBase):
             request_body["custom_html"] = custom_html
 
         if override_body:
-            request_body = override_body
+            request_body = self._serialize_runs_in_request_body(override_body, runs)
 
         # Specify the `verify_ssl` parameter value only for HTTPS urls.
         # The `ClientSession` allows using `ssl=None` for the default SSL check,
@@ -77,3 +83,37 @@ class WebhookNotification(NotificationBase):
                 url, headers=headers, json=request_body, ssl=verify_ssl
             )
             response.raise_for_status()
+
+    @staticmethod
+    def _serialize_runs_in_request_body(override_body, runs):
+        str_parsed_runs = ""
+        runs = runs or []
+
+        def parse_runs():
+            parsed_runs = []
+            for run in runs:
+                if hasattr(run, "to_dict"):
+                    run = run.to_dict()
+                if isinstance(run, dict):
+                    parsed_run = {
+                        "project": run["metadata"]["project"],
+                        "name": run["metadata"]["name"],
+                        "host": run["metadata"]["labels"]["host"],
+                        "status": {"state": run["status"]["state"]},
+                    }
+                    if run["status"].get("error", None):
+                        parsed_run["status"]["error"] = run["status"]["error"]
+                    elif run["status"].get("results", None):
+                        parsed_run["status"]["results"] = run["status"]["results"]
+                    parsed_runs.append(parsed_run)
+            return str(parsed_runs)
+
+        if isinstance(override_body, dict):
+            for key, value in override_body.items():
+                if "{{ runs }}" or "{{runs}}" in value:
+                    if not str_parsed_runs:
+                        str_parsed_runs = parse_runs()
+                    override_body[key] = value.replace(
+                        "{{ runs }}", str_parsed_runs
+                    ).replace("{{runs}}", str_parsed_runs)
+        return override_body

mlrun/utils/notifications/notification_pusher.py

@@ -397,7 +397,7 @@ class NotificationPusher(_NotificationPusherBase):
             try:
                 _run = db.list_runs(
                     project=run.metadata.project,
-                    labels=f"mlrun_constants.MLRunInternalLabels.runner_pod={_step.node_name}",
+                    labels=f"{mlrun_constants.MLRunInternalLabels.runner_pod}={_step.node_name}",
                 )[0]
             except IndexError:
                 _run = {
@@ -484,7 +484,7 @@ class NotificationPusher(_NotificationPusherBase):
     def _get_workflow_manifest(
         workflow_id: str,
     ) -> typing.Optional[mlrun_pipelines.models.PipelineManifest]:
-        kfp_client = mlrun_pipelines.utils.get_client(mlrun.mlconf)
+        kfp_client = mlrun_pipelines.utils.get_client(mlrun.mlconf.kfp_url)
 
         # arbitrary timeout of 5 seconds, the workflow should be done by now
         kfp_run = kfp_client.wait_for_run_completion(workflow_id, 5)

mlrun/utils/version/version.json

@@ -1,4 +1,4 @@
 {
-  "git_commit": "f9d693aaac742edd784874d3f949053e9a5881e4",
-  "version": "1.7.0-rc26"
+  "git_commit": "b63882a2db45e06db696edea855169cc921ff9f2",
+  "version": "1.7.0-rc31"
 }

{mlrun-1.7.0rc26.dist-info → mlrun-1.7.0rc31.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mlrun
-Version: 1.7.0rc26
+Version: 1.7.0rc31
 Summary: Tracking and config of machine learning runs
 Home-page: https://github.com/mlrun/mlrun
 Author: Yaron Haviv
@@ -28,17 +28,17 @@ Requires-Dist: aiohttp-retry ~=2.8
 Requires-Dist: click ~=8.1
 Requires-Dist: nest-asyncio ~=1.0
 Requires-Dist: ipython ~=8.10
-Requires-Dist: nuclio-jupyter ~=0.9.17
+Requires-Dist: nuclio-jupyter ~=0.10.3
 Requires-Dist: numpy <1.27.0,>=1.16.5
 Requires-Dist: pandas <2.2,>=1.2
 Requires-Dist: pyarrow <15,>=10.0
-Requires-Dist: pyyaml ~=5.1
+Requires-Dist: pyyaml <7,>=5.4.1
 Requires-Dist: requests ~=2.31
 Requires-Dist: tabulate ~=0.8.6
-Requires-Dist: v3io ~=0.6.4
+Requires-Dist: v3io ~=0.6.8
 Requires-Dist: pydantic <1.10.15,>=1.10.8
 Requires-Dist: mergedeep ~=1.3
-Requires-Dist: v3io-frames ~=0.10.12
+Requires-Dist: v3io-frames ~=0.10.14
 Requires-Dist: semver ~=3.0
 Requires-Dist: dependency-injector ~=4.41
 Requires-Dist: fsspec <2024.4,>=2023.9.2
@@ -46,12 +46,12 @@ Requires-Dist: v3iofs ~=0.1.17
 Requires-Dist: storey ~=1.7.20
 Requires-Dist: inflection ~=0.5.0
 Requires-Dist: python-dotenv ~=0.17.0
-Requires-Dist: setuptools ~=69.1
+Requires-Dist: setuptools ~=70.0
 Requires-Dist: deprecated ~=1.2
 Requires-Dist: jinja2 >=3.1.3,~=3.1
 Requires-Dist: orjson <4,>=3.9.15
-Requires-Dist: mlrun-pipelines-kfp-common ~=0.1.2
-Requires-Dist: mlrun-pipelines-kfp-v1-8 ~=0.1.2
+Requires-Dist: mlrun-pipelines-kfp-common ~=0.1.3
+Requires-Dist: mlrun-pipelines-kfp-v1-8 ~=0.1.3
 Provides-Extra: alibaba-oss
 Requires-Dist: ossfs ==2023.12.0 ; extra == 'alibaba-oss'
 Requires-Dist: oss2 ==2.18.1 ; extra == 'alibaba-oss'
@@ -81,6 +81,7 @@ Requires-Dist: plotly <5.12.0,~=5.4 ; extra == 'all'
 Requires-Dist: pyopenssl >=23 ; extra == 'all'
 Requires-Dist: redis ~=4.3 ; extra == 'all'
 Requires-Dist: s3fs <2024.4,>=2023.9.2 ; extra == 'all'
+Requires-Dist: snowflake-connector-python ~=3.7 ; extra == 'all'
 Requires-Dist: sqlalchemy ~=1.4 ; extra == 'all'
 Requires-Dist: taos-ws-py ~=0.3.2 ; extra == 'all'
 Provides-Extra: api
@@ -130,6 +131,7 @@ Requires-Dist: plotly <5.12.0,~=5.4 ; extra == 'complete'
 Requires-Dist: pyopenssl >=23 ; extra == 'complete'
 Requires-Dist: redis ~=4.3 ; extra == 'complete'
 Requires-Dist: s3fs <2024.4,>=2023.9.2 ; extra == 'complete'
+Requires-Dist: snowflake-connector-python ~=3.7 ; extra == 'complete'
 Requires-Dist: sqlalchemy ~=1.4 ; extra == 'complete'
 Requires-Dist: taos-ws-py ~=0.3.2 ; extra == 'complete'
 Provides-Extra: complete-api
@@ -164,6 +166,7 @@ Requires-Dist: pymysql ~=1.0 ; extra == 'complete-api'
 Requires-Dist: pyopenssl >=23 ; extra == 'complete-api'
 Requires-Dist: redis ~=4.3 ; extra == 'complete-api'
 Requires-Dist: s3fs <2024.4,>=2023.9.2 ; extra == 'complete-api'
+Requires-Dist: snowflake-connector-python ~=3.7 ; extra == 'complete-api'
 Requires-Dist: sqlalchemy ~=1.4 ; extra == 'complete-api'
 Requires-Dist: taos-ws-py ~=0.3.2 ; extra == 'complete-api'
 Requires-Dist: timelength ~=1.1 ; extra == 'complete-api'
@@ -196,6 +199,8 @@ Provides-Extra: s3
 Requires-Dist: boto3 <1.29.0,>=1.28.0 ; extra == 's3'
 Requires-Dist: aiobotocore <2.8,>=2.5.0 ; extra == 's3'
 Requires-Dist: s3fs <2024.4,>=2023.9.2 ; extra == 's3'
+Provides-Extra: snowflake
+Requires-Dist: snowflake-connector-python ~=3.7 ; extra == 'snowflake'
 Provides-Extra: sqlalchemy
 Requires-Dist: sqlalchemy ~=1.4 ; extra == 'sqlalchemy'
 Provides-Extra: tdengine