mlrun 1.10.0rc10__tar.gz → 1.10.0rc12__tar.gz

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/Makefile

@@ -195,13 +195,13 @@ endif
 install-complete-requirements: ## Install all requirements needed for development and testing
 	$(MLRUN_PYTHON_VENV_PIP_INSTALL) --upgrade $(MLRUN_PIP_NO_CACHE_FLAG) pip~=$(MLRUN_PIP_VERSION)
 	$(eval MLRUN_PIP_INSTALL_FLAG := $(if $(and $(MLRUN_PYTHON_PACKAGE_INSTALLER),$(filter -m pip,$(MLRUN_PYTHON_PACKAGE_INSTALLER))),--ignore-requires-python,))
-	$(MLRUN_PYTHON_VENV_PIP_INSTALL) .[complete] $(MLRUN_PIP_INSTALL_FLAG)
+	$(MLRUN_PYTHON_VENV_PIP_INSTALL) .[complete,dev-postgres] $(MLRUN_PIP_INSTALL_FLAG)
 
 .PHONY: install-complete-kfp-requirements
 install-complete-kfp-requirements: ## Install all requirements needed for development and testing + KFP 1.8
 	$(MLRUN_PYTHON_VENV_PIP_INSTALL) --upgrade $(MLRUN_PIP_NO_CACHE_FLAG) pip~=$(MLRUN_PIP_VERSION)
 	$(eval MLRUN_PIP_INSTALL_FLAG := $(if $(and $(MLRUN_PYTHON_PACKAGE_INSTALLER),$(filter -m pip,$(MLRUN_PYTHON_PACKAGE_INSTALLER))),--ignore-requires-python,))
-	$(MLRUN_PYTHON_VENV_PIP_INSTALL) .[complete,kfp18] $(MLRUN_PIP_INSTALL_FLAG)
+	$(MLRUN_PYTHON_VENV_PIP_INSTALL) .[complete,kfp18,dev-postgres] $(MLRUN_PIP_INSTALL_FLAG)
 
 .PHONY: install-all-requirements
 install-all-requirements: ## Install all requirements needed for development and testing
@@ -580,6 +580,7 @@ test: clean ## Run mlrun tests
 	set -e ; \
 	COMMON_IGNORE_TEST_FLAGS=$$(echo "\
 	--ignore=tests/integration \
+	--ignore=server/py/services/api/tests/integration \
 	--ignore=tests/system \
 	--ignore=tests/rundb/test_httpdb.py \
 	--ignore=server/py/services/api/migrations \
@@ -629,6 +630,7 @@ test-integration-dockerized: build-test ## Run mlrun integration tests in docker
 		-v /var/run/docker.sock:/var/run/docker.sock \
 		-v $$COVERAGE_MOUNT_PATH:/mlrun/tests/coverage_reports \
 		-e RUN_COVERAGE=$(RUN_COVERAGE) \
+		--add-host=host.docker.internal:host-gateway \
 		$(MLRUN_TEST_IMAGE_NAME_TAGGED) make test-integration
 
 .PHONY: test-integration
@@ -644,6 +646,7 @@ test-integration: clean ## Run mlrun integration tests
 		--durations=100 \
 		-rf \
 		tests/integration \
+		server/py/services/api/tests/integration \
 		tests/rundb/test_httpdb.py && \
 	$(PRINT_COVERAGE_REPORT);
 

{mlrun-1.10.0rc10/mlrun.egg-info → mlrun-1.10.0rc12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mlrun
-Version: 1.10.0rc10
+Version: 1.10.0rc12
 Summary: Tracking and config of machine learning runs
 Home-page: https://github.com/mlrun/mlrun
 Author: Yaron Haviv
@@ -31,7 +31,7 @@ Requires-Dist: ipython~=8.10
 Requires-Dist: nuclio-jupyter~=0.11.1
 Requires-Dist: numpy<1.27.0,>=1.26.4
 Requires-Dist: pandas<2.2,>=1.2
-Requires-Dist: pyarrow<17,>=10.0
+Requires-Dist: pyarrow<18,>=10.0
 Requires-Dist: pyyaml<7,>=6.0.2
 Requires-Dist: requests~=2.32
 Requires-Dist: tabulate~=0.8.6
@@ -44,15 +44,15 @@ Requires-Dist: semver~=3.0
 Requires-Dist: dependency-injector~=4.41
 Requires-Dist: fsspec<2024.7,>=2023.9.2
 Requires-Dist: v3iofs~=0.1.17
-Requires-Dist: storey~=1.10.2
+Requires-Dist: storey~=1.10.7
 Requires-Dist: inflection~=0.5.0
 Requires-Dist: python-dotenv~=1.0
 Requires-Dist: setuptools>=75.2
 Requires-Dist: deprecated~=1.2
 Requires-Dist: jinja2>=3.1.6,~=3.1
 Requires-Dist: orjson<4,>=3.9.15
-Requires-Dist: mlrun-pipelines-kfp-common~=0.5.6
-Requires-Dist: mlrun-pipelines-kfp-v1-8~=0.5.4
+Requires-Dist: mlrun-pipelines-kfp-common~=0.5.8
+Requires-Dist: mlrun-pipelines-kfp-v1-8~=0.5.7
 Requires-Dist: docstring_parser~=0.16
 Requires-Dist: aiosmtplib~=3.0
 Provides-Extra: s3
@@ -101,6 +101,10 @@ Provides-Extra: tdengine
 Requires-Dist: taos-ws-py==0.3.2; extra == "tdengine"
 Provides-Extra: snowflake
 Requires-Dist: snowflake-connector-python~=3.7; extra == "snowflake"
+Provides-Extra: openai
+Requires-Dist: openai~=1.88; extra == "openai"
+Provides-Extra: dev-postgres
+Requires-Dist: pytest-mock-resources[postgres]~=2.12; extra == "dev-postgres"
 Provides-Extra: kfp18
 Requires-Dist: mlrun_pipelines_kfp_v1_8[kfp]>=0.5.0; python_version < "3.11" and extra == "kfp18"
 Provides-Extra: api
@@ -120,7 +124,7 @@ Requires-Dist: timelength~=1.1; extra == "api"
 Requires-Dist: memray~=1.12; sys_platform != "win32" and extra == "api"
 Requires-Dist: aiosmtplib~=3.0; extra == "api"
 Requires-Dist: pydantic<2,>=1; extra == "api"
-Requires-Dist: mlrun-pipelines-kfp-v1-8~=0.5.4; extra == "api"
+Requires-Dist: mlrun-pipelines-kfp-v1-8~=0.5.7; extra == "api"
 Requires-Dist: grpcio~=1.70.0; extra == "api"
 Provides-Extra: all
 Requires-Dist: adlfs==2023.9.0; extra == "all"
@@ -144,6 +148,7 @@ Requires-Dist: graphviz~=0.20.0; extra == "all"
 Requires-Dist: kafka-python~=2.1.0; extra == "all"
 Requires-Dist: mlflow~=2.22; extra == "all"
 Requires-Dist: msrest~=0.6.21; extra == "all"
+Requires-Dist: openai~=1.88; extra == "all"
 Requires-Dist: oss2==2.18.1; extra == "all"
 Requires-Dist: ossfs==2023.12.0; extra == "all"
 Requires-Dist: plotly~=5.23; extra == "all"
@@ -175,6 +180,7 @@ Requires-Dist: graphviz~=0.20.0; extra == "complete"
 Requires-Dist: kafka-python~=2.1.0; extra == "complete"
 Requires-Dist: mlflow~=2.22; extra == "complete"
 Requires-Dist: msrest~=0.6.21; extra == "complete"
+Requires-Dist: openai~=1.88; extra == "complete"
 Requires-Dist: oss2==2.18.1; extra == "complete"
 Requires-Dist: ossfs==2023.12.0; extra == "complete"
 Requires-Dist: plotly~=5.23; extra == "complete"
@@ -214,9 +220,10 @@ Requires-Dist: igz-mgmt~=0.4.1; extra == "complete-api"
 Requires-Dist: kafka-python~=2.1.0; extra == "complete-api"
 Requires-Dist: memray~=1.12; sys_platform != "win32" and extra == "complete-api"
 Requires-Dist: mlflow~=2.22; extra == "complete-api"
-Requires-Dist: mlrun-pipelines-kfp-v1-8~=0.5.4; extra == "complete-api"
+Requires-Dist: mlrun-pipelines-kfp-v1-8~=0.5.7; extra == "complete-api"
 Requires-Dist: msrest~=0.6.21; extra == "complete-api"
 Requires-Dist: objgraph~=3.6; extra == "complete-api"
+Requires-Dist: openai~=1.88; extra == "complete-api"
 Requires-Dist: oss2==2.18.1; extra == "complete-api"
 Requires-Dist: ossfs==2023.12.0; extra == "complete-api"
 Requires-Dist: plotly~=5.23; extra == "complete-api"

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/dependencies.py

@@ -75,6 +75,7 @@ def extra_requirements() -> dict[str, list[str]]:
         "alibaba-oss": ["ossfs==2023.12.0", "oss2==2.18.1"],
         "tdengine": ["taos-ws-py==0.3.2"],
         "snowflake": ["snowflake-connector-python~=3.7"],
+        "openai": ["openai~=1.88"],
     }
 
     api_deps = list(
@@ -82,6 +83,7 @@ def extra_requirements() -> dict[str, list[str]]:
     )
     extras_require.update(
         {
+            "dev-postgres": ["pytest-mock-resources[postgres]~=2.12"],
             "kfp18": ["mlrun_pipelines_kfp_v1_8[kfp]>=0.5.0; python_version < '3.11'"],
             # TODO uncomment when KFP 1.8 support is removed
             # "kfp2": ["mlrun_pipelines_kfp_v2[kfp]>=0.5.0 ; python_version >= '3.11'"],

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/dev-requirements.txt

@@ -11,7 +11,8 @@ pytest-asyncio~=0.21.2
 pytest-alembic~=0.11.0
 pytest-httpserver~=1.0
 pytest-timeout~=2.0
-pytest-mock-resources[mysql,postgres]~=2.12
+pytest-mock-resources[mysql]~=2.12
+testcontainers[k3s]~=4.10
 aioresponses~=0.7
 requests-mock~=1.8
 httpx~=0.27.0
@@ -19,6 +20,7 @@ deepdiff~=7.0
 hypothesis[numpy]~=6.103
 pytest-rerunfailures~=14.0
 pytest-forked~=1.6
+tiktoken~=0.9.0
 
 # system tests
 matplotlib~=3.5

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/dockerfiles/mlrun-api/requirements.txt

@@ -17,5 +17,5 @@ memray~=1.12; sys_platform != 'win32'
 aiosmtplib~=3.0
 # until https://github.com/fastapi/fastapi/issues/10360 is solved
 pydantic>=1,<2
-mlrun-pipelines-kfp-v1-8~=0.5.4
+mlrun-pipelines-kfp-v1-8~=0.5.7
 grpcio~=1.70.0

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/extras-requirements.txt

@@ -52,3 +52,4 @@ dask~=2024.12.1; python_version >= "3.11"
 distributed~=2024.12.1; python_version >= "3.11"
 taos-ws-py==0.3.2
 snowflake-connector-python~=3.7
+openai~=1.88

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/__init__.py

@@ -32,7 +32,7 @@ from typing import Optional
 import dotenv
 
 from .config import config as mlconf
-from .datastore import DataItem, store_manager
+from .datastore import DataItem, ModelProvider, store_manager
 from .db import get_run_db
 from .errors import MLRunInvalidArgumentError, MLRunNotFoundError
 from .execution import MLClientCtx
@@ -55,6 +55,7 @@ from .run import (
     code_to_function,
     function_to_module,
     get_dataitem,
+    get_model_provider,
     get_object,
     get_or_create_ctx,
     get_pipeline,

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/__main__.py

@@ -261,7 +261,13 @@ def run(
     config = environ.get("MLRUN_EXEC_CONFIG")
     if from_env and config:
         config = json.loads(config)
-        runobj = RunTemplate.from_dict(config)
+        # If run is a retry we need to maintain the run status therefore using RunObject instead of RunTemplate
+        retry_count = config.get("status", {}).get("retry_count")
+        if retry_count:
+            logger.info(f"Retrying run - attempt: {retry_count + 1}")
+            runobj = mlrun.RunObject.from_dict(config)
+        else:
+            runobj = RunTemplate.from_dict(config)
     elif task:
         obj = get_object(task)
         task = yaml.load(obj, Loader=yaml.FullLoader)

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/artifacts/base.py

@@ -839,9 +839,7 @@ def get_artifact_meta(artifact):
         artifact = artifact.artifact_url
 
     if mlrun.datastore.is_store_uri(artifact):
-        artifact_spec, target = mlrun.datastore.store_manager.get_store_artifact(
-            artifact
-        )
+        artifact_spec, _ = mlrun.datastore.store_manager.get_store_artifact(artifact)
 
     elif artifact.lower().endswith(".yaml"):
         data = mlrun.datastore.store_manager.object(url=artifact).get()
@@ -942,3 +940,11 @@ def fill_artifact_object_hash(object_dict, iteration=None, producer_id=None):
             object_dict["spec"][key] = value
 
     return uid
+
+
+def verify_target_path(artifact: Artifact):
+    if not artifact.get_target_path():
+        raise mlrun.errors.MLRunInvalidArgumentError(
+            f"artifact {artifact.uri} "
+            f"does not have a valid/persistent offline target"
+        )

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/artifacts/dataset.py

@@ -26,7 +26,7 @@ import mlrun.datastore
 import mlrun.utils.helpers
 from mlrun.config import config as mlconf
 
-from .base import Artifact, ArtifactSpec, StorePrefix
+from .base import Artifact, ArtifactSpec, StorePrefix, verify_target_path
 
 default_preview_rows_length = 20
 max_preview_columns = mlconf.artifacts.datasets.max_preview_columns
@@ -424,6 +424,7 @@ def update_dataset_meta(
         artifact_spec = artifact
     elif mlrun.datastore.is_store_uri(artifact):
         artifact_spec, _ = mlrun.datastore.store_manager.get_store_artifact(artifact)
+        verify_target_path(artifact_spec)
     else:
         raise ValueError("model path must be a model store object/URL/DataItem")
 

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/artifacts/llm_prompt.py

@@ -127,7 +127,7 @@ class LLMPromptArtifact(Artifact):
         if self.spec._model_artifact:
             return self.spec._model_artifact
         if self.spec.model_uri:
-            self.spec._model_artifact, target = (
+            self.spec._model_artifact, _ = (
                 mlrun.datastore.store_manager.get_store_artifact(self.spec.model_uri)
             )
             return self.spec._model_artifact

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/artifacts/manager.py

@@ -413,8 +413,8 @@ class ArtifactManager:
         self.artifact_db.del_artifact(
             key=item.db_key,
             project=item.project,
-            tag=item.tag,
             tree=item.tree,
+            uid=item.uid,
             iter=item.iter,
             deletion_strategy=deletion_strategy,
             secrets=secrets,

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/artifacts/model.py

@@ -26,7 +26,7 @@ from ..data_types import InferOptions, get_infer_interface
 from ..features import Feature
 from ..model import ObjectList
 from ..utils import StorePrefix, is_relative_path
-from .base import Artifact, ArtifactSpec, upload_extra_data
+from .base import Artifact, ArtifactSpec, upload_extra_data, verify_target_path
 
 model_spec_filename = "model_spec.yaml"
 MODEL_OPTIONAL_SUFFIXES = [".tar.gz", ".pkl", ".bin", ".pickle"]
@@ -493,7 +493,6 @@ def get_model(
     :returns: model filename, model artifact object, extra data dict
 
     """
-    # TODO support LLMPromptArtifact
     model_file = ""
     model_spec = None
     extra_dataitems = {}
@@ -518,6 +517,7 @@ def get_model(
             model_spec, target = mlrun.datastore.store_manager.get_store_artifact(
                 model_dir
             )
+            verify_target_path(model_spec)
         else:
             model_spec, target = model_dir, model_dir.get_target_path()
         if not model_spec or model_spec.kind != "model":

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/common/constants.py

@@ -27,6 +27,10 @@ DASK_LABEL_PREFIX = "dask.org/"
 NUCLIO_LABEL_PREFIX = "nuclio.io/"
 RESERVED_TAG_NAME_LATEST = "latest"
 
+JOB_TYPE_WORKFLOW_RUNNER = "workflow-runner"
+JOB_TYPE_PROJECT_LOADER = "project-loader"
+JOB_TYPE_RERUN_WORKFLOW_RUNNER = "rerun-workflow-runner"
+
 
 class MLRunInternalLabels:
     ### dask
@@ -62,6 +66,7 @@ class MLRunInternalLabels:
     scrape_metrics = f"{MLRUN_LABEL_PREFIX}scrape-metrics"
     tag = f"{MLRUN_LABEL_PREFIX}tag"
     uid = f"{MLRUN_LABEL_PREFIX}uid"
+    retry = f"{MLRUN_LABEL_PREFIX}retry-attempt"
     username = f"{MLRUN_LABEL_PREFIX}username"
     username_domain = f"{MLRUN_LABEL_PREFIX}username_domain"
     task_name = f"{MLRUN_LABEL_PREFIX}task-name"
@@ -76,7 +81,9 @@ class MLRunInternalLabels:
     kind = "kind"
     component = "component"
     mlrun_type = "mlrun__type"
+    rerun_of = "rerun-of"
     original_workflow_id = "original-workflow-id"
+    workflow_id = "workflow-id"
 
     owner = "owner"
     v3io_user = "v3io_user"
@@ -102,3 +109,8 @@ class MLRunInternalLabels:
 class DeployStatusTextKind(mlrun.common.types.StrEnum):
     logs = "logs"
     events = "events"
+
+
+class WorkflowSubmitMode(mlrun.common.types.StrEnum):
+    direct = "direct"  # call KFP retry API directly
+    rerun = "rerun"  # launch a RerunRunner function

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/common/runtimes/constants.py

@@ -139,6 +139,7 @@ class RunStates:
     aborted = "aborted"
     aborting = "aborting"
     skipped = "skipped"
+    pending_retry = "pendingRetry"
 
     @staticmethod
     def all():
@@ -152,6 +153,7 @@ class RunStates:
             RunStates.aborted,
             RunStates.aborting,
             RunStates.skipped,
+            RunStates.pending_retry,
         ]
 
     @staticmethod
@@ -168,6 +170,7 @@ class RunStates:
         return [
             RunStates.error,
             RunStates.aborted,
+            RunStates.pending_retry,
         ]
 
     @staticmethod
@@ -185,12 +188,18 @@ class RunStates:
     def non_terminal_states():
         return list(set(RunStates.all()) - set(RunStates.terminal_states()))
 
+    @staticmethod
+    def terminal_or_error_states():
+        return list(
+            set(RunStates.terminal_states())
+            | set(RunStates.error_and_abortion_states())
+        )
+
     @staticmethod
     def not_allowed_for_deletion_states():
         return [
             RunStates.running,
             RunStates.pending,
-            # TODO: add aborting state once we have it
         ]
 
     @staticmethod

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/common/schemas/model_monitoring/__init__.py

@@ -54,6 +54,8 @@ from .grafana import (
     GrafanaTable,
 )
 from .model_endpoints import (
+    ApplicationMetricRecord,
+    ApplicationResultRecord,
     Features,
     FeatureValues,
     ModelEndpoint,

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/common/schemas/model_monitoring/functions.py

@@ -34,6 +34,7 @@ class FunctionSummary(BaseModel):
     type: FunctionsType
     name: str
     application_class: str
+    project_name: str
     updated_time: datetime
     status: Optional[str] = None
     base_period: Optional[int] = None
@@ -59,6 +60,7 @@ class FunctionSummary(BaseModel):
             else func_dict["spec"]["graph"]["steps"]["PushToMonitoringWriter"]["after"][
                 0
             ],
+            project_name=func_dict["metadata"]["project"],
             updated_time=func_dict["metadata"].get("updated"),
             status=func_dict["status"].get("state"),
             base_period=base_period,

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/common/schemas/model_monitoring/model_endpoints.py

@@ -14,7 +14,7 @@
 import abc
 import json
 from datetime import datetime
-from typing import Any, NamedTuple, Optional, TypeVar
+from typing import Any, Literal, NamedTuple, Optional, TypeVar
 from uuid import UUID
 
 from pydantic import validator  # use `validator` if you’re still on Pydantic v1
@@ -334,6 +334,24 @@ class ModelEndpointMonitoringMetricNoData(_ModelEndpointMonitoringMetricValuesBa
     data: bool = False
 
 
+class ApplicationBaseRecord(BaseModel):
+    type: Literal["metric", "result"]
+    time: datetime
+    value: float
+
+
+class ApplicationResultRecord(ApplicationBaseRecord):
+    kind: ResultKindApp
+    status: ResultStatusApp
+    result_name: str
+    type: Literal["result"] = "result"
+
+
+class ApplicationMetricRecord(ApplicationBaseRecord):
+    metric_name: str
+    type: Literal["metric"] = "metric"
+
+
 def _mapping_attributes(
     model_class: type[Model],
     flattened_dictionary: dict,

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/common/schemas/serving.py

@@ -26,6 +26,7 @@ class DeployResponse(BaseModel):
 
 class ModelRunnerStepData(StrEnum):
     MODELS = "models"
+    MODEL_TO_EXECUTION_MECHANISM = "execution_mechanism_by_model_name"
     MONITORING_DATA = "monitoring_data"
 
 

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/common/schemas/workflow.py

@@ -47,8 +47,9 @@ class WorkflowRequest(pydantic.v1.BaseModel):
 
 
 class RerunWorkflowRequest(pydantic.v1.BaseModel):
-    run_name: typing.Optional[str] = (None,)
-    run_id: typing.Optional[str] = (None,)
+    run_name: typing.Optional[str] = None
+    run_id: typing.Optional[str] = None
+    original_workflow_id: typing.Optional[str] = None
     notifications: typing.Optional[list[Notification]] = None
     workflow_runner_node_selector: typing.Optional[dict[str, str]] = None
 

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/config.py

@@ -120,6 +120,12 @@ default_config = {
             # max number of parallel abort run jobs in runs monitoring
             "concurrent_abort_stale_runs_workers": 10,
             "list_runs_time_period_in_days": 7,  # days
+            "retry": {
+                # periodic job for triggering retries interval in seconds
+                "interval": "30",
+                # runs limit to fetch for retrying
+                "fetch_runs_limit": 1000,
+            },
         },
         "projects": {
             "summaries": {
@@ -184,6 +190,9 @@ default_config = {
         "url": "",
     },
     "v3io_framesd": "http://framesd:8080",
+    "model_providers": {
+        "openai_default_model": "gpt-4",
+    },
     # default node selector to be applied to all functions - json string base64 encoded format
     "default_function_node_selector": "e30=",
     # default priority class to be applied to functions running on k8s cluster
@@ -270,6 +279,12 @@ default_config = {
                     "executing": "24h",
                 }
             },
+            "retry": {
+                "backoff": {
+                    "default_base_delay": "30s",
+                    "min_base_delay": "30s",
+                },
+            },
             # When the module is reloaded, the maximum depth recursion configuration for the recursive reload
             # function is used to prevent infinite loop
             "reload_max_recursion_depth": 100,
@@ -316,6 +331,7 @@ default_config = {
                     "project_summaries": "enabled",
                     "start_logs": "enabled",
                     "stop_logs": "enabled",
+                    "retry_jobs": "enabled",
                 },
             },
             "worker": {
@@ -539,7 +555,7 @@ default_config = {
         },
         "v3io_api": "",
         "v3io_framesd": "",
-        # If running from sdk and MLRUN_DBPATH is not set, the db will fallback to a nop db which will not preform any
+        # If running from sdk and MLRUN_DBPATH is not set, the db will fallback to a nop db which will not perform any
         # run db operations.
         "nop_db": {
             # if set to true, will raise an error for trying to use run db functionality
@@ -641,7 +657,7 @@ default_config = {
         "offline_storage_path": "model-endpoints/{kind}",
         "parquet_batching_max_events": 10_000,
         "parquet_batching_timeout_secs": timedelta(minutes=1).total_seconds(),
-        "model_endpoint_creation_check_period": "15",
+        "model_endpoint_creation_check_period": 15,
     },
     "secret_stores": {
         # Use only in testing scenarios (such as integration tests) to avoid using k8s for secrets (will use in-memory
@@ -1219,6 +1235,7 @@ class Config:
         """
         Get the default value for the ssl_redirect configuration.
         In Iguazio we always want to redirect to HTTPS, in other cases we don't.
+
         :return: True if we should redirect to HTTPS, False otherwise.
         """
         return self.is_running_on_iguazio()

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/datastore/__init__.py

@@ -14,6 +14,7 @@
 
 __all__ = [
     "DataItem",
+    "ModelProvider",
     "get_store_resource",
     "ParquetTarget",
     "CSVTarget",
@@ -32,12 +33,12 @@ __all__ = [
     "get_stream_pusher",
     "ConfigProfile",
     "VectorStoreCollection",
+    "store_manager",
 ]
 
 from urllib.parse import urlparse
 
 import fsspec
-from mergedeep import merge
 
 import mlrun.datastore.wasbfs
 from mlrun.datastore.datastore_profile import (
@@ -45,6 +46,7 @@ from mlrun.datastore.datastore_profile import (
     DatastoreProfileKafkaTarget,
     DatastoreProfileV3io,
 )
+from mlrun.datastore.model_provider.model_provider import ModelProvider
 from mlrun.platforms.iguazio import (
     HTTPOutputStream,
     KafkaOutputStream,

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/datastore/alibaba_oss.py

@@ -69,7 +69,7 @@ class OSSStore(DataStore):
             key=self._get_secret_or_env("ALIBABA_ACCESS_KEY_ID"),
             secret=self._get_secret_or_env("ALIBABA_SECRET_ACCESS_KEY"),
         )
-        return self._sanitize_storage_options(res)
+        return self._sanitize_options(res)
 
     def get_bucket_and_key(self, key):
         path = self._join(key)[1:]

{mlrun-1.10.0rc10 → mlrun-1.10.0rc12}/mlrun/datastore/azure_blob.py

@@ -67,7 +67,7 @@ class AzureBlobStore(DataStore):
                 or self._get_secret_or_env("AZURE_STORAGE_SAS_TOKEN"),
                 credential=self._get_secret_or_env("credential"),
             )
-            self._storage_options = self._sanitize_storage_options(res)
+            self._storage_options = self._sanitize_options(res)
         return self._storage_options
 
     @property
@@ -224,7 +224,7 @@ class AzureBlobStore(DataStore):
         path = self._convert_key_to_remote_path(key=path)
         super().rm(path=path, recursive=recursive, maxdepth=maxdepth)
 
-    def get_spark_options(self):
+    def get_spark_options(self, path=None):
         res = {}
         st = self.storage_options
         service = "blob"