mlrun 1.6.0rc26__py3-none-any.whl → 1.6.3rc1__py3-none-any.whl

mlrun/artifacts/manager.py

@@ -132,6 +132,12 @@ class ArtifactManager:
         #  ModelArtifact is a directory.
         if isinstance(item, ModelArtifact):
             return
+        # Could happen in the import artifact scenario - that path is None.
+        if item.target_path:
+            return
+        #  in DatasetArtifact
+        if hasattr(item, "df") and item.df is not None:
+            return
         parsed_url = urlparse(path)
         schema = parsed_url.scheme
         #  we are not checking remote paths yet.

mlrun/artifacts/model.py

@@ -13,8 +13,9 @@
 # limitations under the License.
 import tempfile
 from os import path
-from typing import List
+from typing import Any
 
+import pandas as pd
 import yaml
 from deprecated import deprecated
 
@@ -68,8 +69,8 @@ class ModelArtifactSpec(ArtifactSpec):
         model_file=None,
         metrics=None,
         paraemeters=None,
-        inputs: List[Feature] = None,
-        outputs: List[Feature] = None,
+        inputs: list[Feature] = None,
+        outputs: list[Feature] = None,
         framework=None,
         algorithm=None,
         feature_vector=None,
@@ -91,8 +92,8 @@ class ModelArtifactSpec(ArtifactSpec):
         self.model_file = model_file
         self.metrics = metrics or {}
         self.parameters = paraemeters or {}
-        self.inputs: List[Feature] = inputs or []
-        self.outputs: List[Feature] = outputs or []
+        self.inputs: list[Feature] = inputs or []
+        self.outputs: list[Feature] = outputs or []
         self.framework = framework
         self.algorithm = algorithm
         self.feature_vector = feature_vector
@@ -101,21 +102,21 @@ class ModelArtifactSpec(ArtifactSpec):
         self.model_target_file = model_target_file
 
     @property
-    def inputs(self) -> List[Feature]:
+    def inputs(self) -> list[Feature]:
         """input feature list"""
         return self._inputs
 
     @inputs.setter
-    def inputs(self, inputs: List[Feature]):
+    def inputs(self, inputs: list[Feature]):
         self._inputs = ObjectList.from_list(Feature, inputs)
 
     @property
-    def outputs(self) -> List[Feature]:
+    def outputs(self) -> list[Feature]:
         """output feature list"""
         return self._outputs
 
     @outputs.setter
-    def outputs(self, outputs: List[Feature]):
+    def outputs(self, outputs: list[Feature]):
         self._outputs = ObjectList.from_list(Feature, outputs)
 
 
@@ -175,22 +176,22 @@ class ModelArtifact(Artifact):
         self._spec = self._verify_dict(spec, "spec", ModelArtifactSpec)
 
     @property
-    def inputs(self) -> List[Feature]:
+    def inputs(self) -> list[Feature]:
         """input feature list"""
         return self.spec.inputs
 
     @inputs.setter
-    def inputs(self, inputs: List[Feature]):
+    def inputs(self, inputs: list[Feature]):
         """input feature list"""
         self.spec.inputs = inputs
 
     @property
-    def outputs(self) -> List[Feature]:
+    def outputs(self) -> list[Feature]:
         """input feature list"""
         return self.spec.outputs
 
     @outputs.setter
-    def outputs(self, outputs: List[Feature]):
+    def outputs(self, outputs: list[Feature]):
         """input feature list"""
         self.spec.outputs = outputs
 
@@ -260,6 +261,7 @@ class ModelArtifact(Artifact):
         """
         subset = df
         inferer = get_infer_interface(subset)
+        numeric_columns = self._extract_numeric_features(df)
         if label_columns:
             if not isinstance(label_columns, list):
                 label_columns = [label_columns]
@@ -273,9 +275,13 @@ class ModelArtifact(Artifact):
             )
         if with_stats:
             self.spec.feature_stats = inferer.get_stats(
-                df, options=InferOptions.Histogram, num_bins=num_bins
+                df[numeric_columns], options=InferOptions.Histogram, num_bins=num_bins
             )
 
+    @staticmethod
+    def _extract_numeric_features(df: pd.DataFrame) -> list[Any]:
+        return [col for col in df.columns if pd.api.types.is_numeric_dtype(df[col])]
+
     @property
     def is_dir(self):
         return True
@@ -445,8 +451,8 @@ class LegacyModelArtifact(LegacyArtifact):
         self.model_file = model_file
         self.parameters = parameters or {}
         self.metrics = metrics or {}
-        self.inputs: List[Feature] = inputs or []
-        self.outputs: List[Feature] = outputs or []
+        self.inputs: list[Feature] = inputs or []
+        self.outputs: list[Feature] = outputs or []
         self.extra_data = extra_data or {}
         self.framework = framework
         self.algorithm = algorithm
@@ -456,21 +462,21 @@ class LegacyModelArtifact(LegacyArtifact):
         self.model_target_file = model_target_file
 
     @property
-    def inputs(self) -> List[Feature]:
+    def inputs(self) -> list[Feature]:
         """input feature list"""
         return self._inputs
 
     @inputs.setter
-    def inputs(self, inputs: List[Feature]):
+    def inputs(self, inputs: list[Feature]):
         self._inputs = ObjectList.from_list(Feature, inputs)
 
     @property
-    def outputs(self) -> List[Feature]:
+    def outputs(self) -> list[Feature]:
         """output feature list"""
         return self._outputs
 
     @outputs.setter
-    def outputs(self, outputs: List[Feature]):
+    def outputs(self, outputs: list[Feature]):
         self._outputs = ObjectList.from_list(Feature, outputs)
 
     def infer_from_df(self, df, label_columns=None, with_stats=True, num_bins=None):
@@ -642,8 +648,8 @@ def update_model(
     parameters: dict = None,
     metrics: dict = None,
     extra_data: dict = None,
-    inputs: List[Feature] = None,
-    outputs: List[Feature] = None,
+    inputs: list[Feature] = None,
+    outputs: list[Feature] = None,
     feature_vector: str = None,
     feature_weights: list = None,
     key_prefix: str = "",

mlrun/common/db/sql_session.py

@@ -63,9 +63,12 @@ def _init_engine(dsn=None):
         max_overflow = config.httpdb.db.connections_pool_max_overflow
         if max_overflow is None:
             max_overflow = config.httpdb.max_workers
+
         kwargs = {
             "pool_size": pool_size,
             "max_overflow": max_overflow,
+            "pool_pre_ping": config.httpdb.db.connections_pool_pre_ping,
+            "pool_recycle": config.httpdb.db.connections_pool_recycle,
         }
     engine = create_engine(dsn, **kwargs)
     _engines[dsn] = engine

mlrun/common/model_monitoring/helpers.py

@@ -82,13 +82,15 @@ def parse_monitoring_stream_path(
         if application_name is None:
             stream_uri = (
                 mlrun.mlconf.model_endpoint_monitoring.default_http_sink.format(
-                    project=project
+                    project=project, namespace=mlrun.mlconf.namespace
                 )
             )
         else:
             stream_uri = (
                 mlrun.mlconf.model_endpoint_monitoring.default_http_sink_app.format(
-                    project=project, application_name=application_name
+                    project=project,
+                    application_name=application_name,
+                    namespace=mlrun.mlconf.namespace,
                 )
             )
     return stream_uri

mlrun/common/schemas/__init__.py

@@ -43,6 +43,7 @@ from .clusterization_spec import (
     ClusterizationSpec,
     WaitForChiefToReachOnlineStateFeatureFlag,
 )
+from .common import ImageBuilder
 from .constants import (
     APIStates,
     ClusterizationRole,
@@ -113,6 +114,7 @@ from .model_monitoring import (
     EventFieldType,
     EventKeyMetrics,
     Features,
+    FeatureSetFeatures,
     FeatureValues,
     GrafanaColumn,
     GrafanaDataPoint,

mlrun/common/schemas/common.py

@@ -0,0 +1,40 @@
+# Copyright 2023 Iguazio
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+import typing
+
+import pydantic
+
+
+class ImageBuilder(pydantic.BaseModel):
+    functionSourceCode: typing.Optional[str] = None
+    codeEntryType: typing.Optional[str] = None
+    codeEntryAttributes: typing.Optional[str] = None
+    source: typing.Optional[str] = None
+    code_origin: typing.Optional[str] = None
+    origin_filename: typing.Optional[str] = None
+    image: typing.Optional[str] = None
+    base_image: typing.Optional[str] = None
+    commands: typing.Optional[list] = None
+    extra: typing.Optional[str] = None
+    extra_args: typing.Optional[dict] = None
+    builder_env: typing.Optional[dict] = None
+    secret: typing.Optional[str] = None
+    registry: typing.Optional[str] = None
+    load_source_on_run: typing.Optional[bool] = None
+    with_mlrun: typing.Optional[bool] = None
+    auto_build: typing.Optional[bool] = None
+    build_pod: typing.Optional[str] = None
+    requirements: typing.Optional[list] = None
+    source_code_target_dir: typing.Optional[str] = None

mlrun/common/schemas/model_monitoring/__init__.py

@@ -22,6 +22,7 @@ from .constants import (
     EventFieldType,
     EventKeyMetrics,
     EventLiveStats,
+    FeatureSetFeatures,
     FileTargetKind,
     FunctionURI,
     ModelEndpointTarget,

mlrun/common/schemas/model_monitoring/constants.py

@@ -77,6 +77,26 @@ class EventFieldType:
     SAMPLE_PARQUET_PATH = "sample_parquet_path"
 
 
+class MonitoringStrEnum(StrEnum):
+    @classmethod
+    def list(cls):
+        return list(map(lambda c: c.value, cls))
+
+
+class FeatureSetFeatures(MonitoringStrEnum):
+    LATENCY = EventFieldType.LATENCY
+    ERROR_COUNT = EventFieldType.ERROR_COUNT
+    METRICS = EventFieldType.METRICS
+
+    @classmethod
+    def time_stamp(cls):
+        return EventFieldType.TIMESTAMP
+
+    @classmethod
+    def entity(cls):
+        return EventFieldType.ENDPOINT_ID
+
+
 class ApplicationEvent:
     APPLICATION_NAME = "application_name"
     CURRENT_STATS = "current_stats"
@@ -89,7 +109,7 @@ class ApplicationEvent:
     OUTPUT_STREAM_URI = "output_stream_uri"
 
 
-class WriterEvent(StrEnum):
+class WriterEvent(MonitoringStrEnum):
     APPLICATION_NAME = "application_name"
     ENDPOINT_ID = "endpoint_id"
     START_INFER_TIME = "start_infer_time"
@@ -101,10 +121,6 @@ class WriterEvent(StrEnum):
     RESULT_EXTRA_DATA = "result_extra_data"
     CURRENT_STATS = "current_stats"
 
-    @classmethod
-    def list(cls):
-        return list(map(lambda c: c.value, cls))
-
 
 class EventLiveStats:
     LATENCY_AVG_5M = "latency_avg_5m"

mlrun/common/schemas/project.py

@@ -19,6 +19,7 @@ import pydantic
 
 import mlrun.common.types
 
+from .common import ImageBuilder
 from .object import ObjectKind, ObjectStatus
 
 
@@ -85,6 +86,7 @@ class ProjectSpec(pydantic.BaseModel):
     desired_state: typing.Optional[ProjectDesiredState] = ProjectDesiredState.online
     custom_packagers: typing.Optional[typing.List[typing.Tuple[str, bool]]] = None
     default_image: typing.Optional[str] = None
+    build: typing.Optional[ImageBuilder] = None
 
     class Config:
         extra = pydantic.Extra.allow

mlrun/config.py

@@ -109,7 +109,10 @@ default_config = {
         "runs": {
             # deleting runs is a heavy operation that includes deleting runtime resources, therefore we do it in chunks
             "batch_delete_runs_chunk_size": 10,
-        }
+        },
+        "resources": {
+            "delete_crd_resources_timeout": "5 minutes",
+        },
     },
     # the grace period (in seconds) that will be given to runtime resources (after they're in terminal state)
     # before deleting them (4 hours)
@@ -285,6 +288,12 @@ default_config = {
         "state": "online",
         "retry_api_call_on_exception": "enabled",
         "http_connection_timeout_keep_alive": 11,
+        # http client used by httpdb
+        "http": {
+            # when True, the client will verify the server's TLS
+            # set to False for backwards compatibility.
+            "verify": False,
+        },
         "db": {
             "commit_retry_timeout": 30,
             "commit_retry_interval": 3,
@@ -303,7 +312,11 @@ default_config = {
                 # default is 16MB, max 1G, for more info https://dev.mysql.com/doc/refman/8.0/en/packet-too-large.html
                 "max_allowed_packet": 64000000,  # 64MB
             },
-            # None will set this to be equal to the httpdb.max_workers
+            # tests connections for liveness upon each checkout
+            "connections_pool_pre_ping": True,
+            # this setting causes the pool to recycle connections after the given number of seconds has passed
+            "connections_pool_recycle": 60 * 60,
+            # None defaults to httpdb.max_workers
             "connections_pool_size": None,
             "connections_pool_max_overflow": None,
             # below is a db-specific configuration
@@ -408,6 +421,8 @@ default_config = {
             "iguazio_access_key": "",
             "iguazio_list_projects_default_page_size": 200,
             "iguazio_client_job_cache_ttl": "20 minutes",
+            "nuclio_project_deletion_verification_timeout": "300 seconds",
+            "nuclio_project_deletion_verification_interval": "5 seconds",
         },
         # The API needs to know what is its k8s svc url so it could enrich it in the jobs it creates
         "api_url": "",
@@ -429,7 +444,7 @@ default_config = {
             # pip install <requirement_specifier>, e.g. mlrun==0.5.4, mlrun~=0.5,
             # git+https://github.com/mlrun/mlrun@development. by default uses the version
             "mlrun_version_specifier": "",
-            "kaniko_image": "gcr.io/kaniko-project/executor:v1.8.0",  # kaniko builder image
+            "kaniko_image": "gcr.io/kaniko-project/executor:v1.21.1",  # kaniko builder image
             "kaniko_init_container_image": "alpine:3.18",
             # image for kaniko init container when docker registry is ECR
             "kaniko_aws_cli_image": "amazon/aws-cli:2.7.10",
@@ -476,8 +491,8 @@ default_config = {
         "offline_storage_path": "model-endpoints/{kind}",
         # Default http path that points to the monitoring stream nuclio function. Will be used as a stream path
         # when the user is working in CE environment and has not provided any stream path.
-        "default_http_sink": "http://nuclio-{project}-model-monitoring-stream.mlrun.svc.cluster.local:8080",
-        "default_http_sink_app": "http://nuclio-{project}-{application_name}.mlrun.svc.cluster.local:8080",
+        "default_http_sink": "http://nuclio-{project}-model-monitoring-stream.{namespace}.svc.cluster.local:8080",
+        "default_http_sink_app": "http://nuclio-{project}-{application_name}.{namespace}.svc.cluster.local:8080",
         "batch_processing_function_branch": "master",
         "parquet_batching_max_events": 10_000,
         "parquet_batching_timeout_secs": timedelta(minutes=1).total_seconds(),
@@ -596,8 +611,9 @@ default_config = {
     },
     "workflows": {
         "default_workflow_runner_name": "workflow-runner-{}",
-        # Default timeout seconds for retrieving workflow id after execution:
-        "timeouts": {"local": 120, "kfp": 30, "remote": 30},
+        # Default timeout seconds for retrieving workflow id after execution
+        # Remote workflow timeout is the maximum between remote and the inner engine timeout
+        "timeouts": {"local": 120, "kfp": 60, "remote": 60 * 5},
     },
     "log_collector": {
         "address": "localhost:8282",
@@ -949,10 +965,10 @@ class Config:
             with_gpu = (
                 with_gpu_requests if requirement == "requests" else with_gpu_limits
             )
-            resources[
-                requirement
-            ] = self.get_default_function_pod_requirement_resources(
-                requirement, with_gpu
+            resources[requirement] = (
+                self.get_default_function_pod_requirement_resources(
+                    requirement, with_gpu
+                )
             )
         return resources
 
@@ -1146,11 +1162,12 @@ class Config:
 
         return storage_options
 
-    def is_explicit_ack(self) -> bool:
+    def is_explicit_ack(self, version=None) -> bool:
+        if not version:
+            version = self.nuclio_version
         return self.httpdb.nuclio.explicit_ack == "enabled" and (
-            not self.nuclio_version
-            or semver.VersionInfo.parse(self.nuclio_version)
-            >= semver.VersionInfo.parse("1.12.10")
+            not version
+            or semver.VersionInfo.parse(version) >= semver.VersionInfo.parse("1.12.10")
         )
 
 
@@ -1334,12 +1351,21 @@ def read_env(env=None, prefix=env_prefix):
         if igz_domain:
             config["ui_url"] = f"https://mlrun-ui.{igz_domain}"
 
-    if config.get("log_level"):
+    if log_level := config.get("log_level"):
         import mlrun.utils.logger
 
         # logger created (because of imports mess) before the config is loaded (in tests), therefore we're changing its
         # level manually
-        mlrun.utils.logger.set_logger_level(config["log_level"])
+        mlrun.utils.logger.set_logger_level(log_level)
+
+    if log_formatter_name := config.get("log_formatter"):
+        import mlrun.utils.logger
+
+        log_formatter = mlrun.utils.create_formatter_instance(
+            mlrun.utils.FormatterKinds(log_formatter_name)
+        )
+        mlrun.utils.logger.get_handler("default").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.
     _convert_resources_to_str(config)

mlrun/data_types/data_types.py

@@ -41,6 +41,7 @@ class ValueType(str, Enum):
     BYTES = "bytes"
     STRING = "str"
     DATETIME = "datetime"
+    LIST = "List"
     BYTES_LIST = "List[bytes]"
     STRING_LIST = "List[string]"
     INT32_LIST = "List[int32]"
@@ -48,6 +49,7 @@ class ValueType(str, Enum):
     DOUBLE_LIST = "List[float]"
     FLOAT_LIST = "List[float32]"
     BOOL_LIST = "List[bool]"
+    Tuple = "Tuple"
 
 
 def pd_schema_to_value_type(value):
@@ -102,6 +104,8 @@ def python_type_to_value_type(value_type):
         "datetime64[ns]": ValueType.INT64,
         "datetime64[ns, tz]": ValueType.INT64,
         "category": ValueType.STRING,
+        "list": ValueType.LIST,
+        "tuple": ValueType.Tuple,
     }
 
     if type_name in type_map:

mlrun/datastore/azure_blob.py

@@ -175,9 +175,9 @@ class AzureBlobStore(DataStore):
 
         if "client_secret" in st or "client_id" in st or "tenant_id" in st:
             res[f"spark.hadoop.fs.azure.account.auth.type.{host}"] = "OAuth"
-            res[
-                f"spark.hadoop.fs.azure.account.oauth.provider.type.{host}"
-            ] = "org.apache.hadoop.fs.azurebfs.oauth2.ClientCredsTokenProvider"
+            res[f"spark.hadoop.fs.azure.account.oauth.provider.type.{host}"] = (
+                "org.apache.hadoop.fs.azurebfs.oauth2.ClientCredsTokenProvider"
+            )
             if "client_id" in st:
                 res[f"spark.hadoop.fs.azure.account.oauth2.client.id.{host}"] = st[
                     "client_id"
@@ -188,14 +188,14 @@ class AzureBlobStore(DataStore):
                 ]
             if "tenant_id" in st:
                 tenant_id = st["tenant_id"]
-                res[
-                    f"spark.hadoop.fs.azure.account.oauth2.client.endpoint.{host}"
-                ] = f"https://login.microsoftonline.com/{tenant_id}/oauth2/token"
+                res[f"spark.hadoop.fs.azure.account.oauth2.client.endpoint.{host}"] = (
+                    f"https://login.microsoftonline.com/{tenant_id}/oauth2/token"
+                )
 
         if "sas_token" in st:
             res[f"spark.hadoop.fs.azure.account.auth.type.{host}"] = "SAS"
-            res[
-                f"spark.hadoop.fs.azure.sas.token.provider.type.{host}"
-            ] = "org.apache.hadoop.fs.azurebfs.sas.FixedSASTokenProvider"
+            res[f"spark.hadoop.fs.azure.sas.token.provider.type.{host}"] = (
+                "org.apache.hadoop.fs.azurebfs.sas.FixedSASTokenProvider"
+            )
             res[f"spark.hadoop.fs.azure.sas.fixed.token.{host}"] = st["sas_token"]
         return res

mlrun/datastore/base.py

@@ -27,6 +27,7 @@ import requests
 import urllib3
 from deprecated import deprecated
 
+import mlrun.config
 import mlrun.errors
 from mlrun.errors import err_to_str
 from mlrun.utils import StorePrefix, is_ipython, logger
@@ -34,10 +35,6 @@ from mlrun.utils import StorePrefix, is_ipython, logger
 from .store_resources import is_store_uri, parse_store_uri
 from .utils import filter_df_start_end_time, select_columns_from_df
 
-verify_ssl = False
-if not verify_ssl:
-    urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
-
 
 class FileStats:
     def __init__(self, size, modified, content_type=None):
@@ -643,45 +640,6 @@ def basic_auth_header(user, password):
     return {"Authorization": authstr}
 
 
-def http_get(url, headers=None, auth=None):
-    try:
-        response = requests.get(url, headers=headers, auth=auth, verify=verify_ssl)
-    except OSError as exc:
-        raise OSError(f"error: cannot connect to {url}: {err_to_str(exc)}")
-
-    mlrun.errors.raise_for_status(response)
-
-    return response.content
-
-
-def http_head(url, headers=None, auth=None):
-    try:
-        response = requests.head(url, headers=headers, auth=auth, verify=verify_ssl)
-    except OSError as exc:
-        raise OSError(f"error: cannot connect to {url}: {err_to_str(exc)}")
-
-    mlrun.errors.raise_for_status(response)
-
-    return response.headers
-
-
-def http_put(url, data, headers=None, auth=None, session=None):
-    try:
-        put_api = session.put if session else requests.put
-        response = put_api(
-            url, data=data, headers=headers, auth=auth, verify=verify_ssl
-        )
-    except OSError as exc:
-        raise OSError(f"error: cannot connect to {url}: {err_to_str(exc)}") from exc
-
-    mlrun.errors.raise_for_status(response)
-
-
-def http_upload(url, file_path, headers=None, auth=None):
-    with open(file_path, "rb") as data:
-        http_put(url, data, headers, auth)
-
-
 class HttpStore(DataStore):
     def __init__(self, parent, schema, name, endpoint="", secrets: dict = None):
         super().__init__(parent, name, schema, endpoint, secrets)
@@ -709,7 +667,7 @@ class HttpStore(DataStore):
         raise ValueError("unimplemented")
 
     def get(self, key, size=None, offset=0):
-        data = http_get(self.url + self._join(key), self._headers, self.auth)
+        data = self._http_get(self.url + self._join(key), self._headers, self.auth)
         if offset:
             data = data[offset:]
         if size:
@@ -729,6 +687,26 @@ class HttpStore(DataStore):
                 f"schema as it is not secure and is not recommended."
             )
 
+    def _http_get(
+        self,
+        url,
+        headers=None,
+        auth=None,
+    ):
+        # import here to prevent import cycle
+        from mlrun.config import config as mlconf
+
+        verify_ssl = mlconf.httpdb.http.verify
+        try:
+            if not verify_ssl:
+                urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+            response = requests.get(url, headers=headers, auth=auth, verify=verify_ssl)
+        except OSError as exc:
+            raise OSError(f"error: cannot connect to {url}: {err_to_str(exc)}")
+
+        mlrun.errors.raise_for_status(response)
+        return response.content
+
 
 # This wrapper class is designed to extract the 'ds' schema and profile name from URL-formatted paths.
 # Within fsspec, the AbstractFileSystem::_strip_protocol() internal method is used to handle complete URL paths.

mlrun/datastore/datastore.py

@@ -182,16 +182,20 @@ class StoreManager:
                 url, project, allow_empty_resources, secrets
             )
 
-        store, subpath = self.get_or_create_store(url, secrets=secrets)
+        store, subpath = self.get_or_create_store(
+            url, secrets=secrets, project_name=project
+        )
         return DataItem(key, store, subpath, url, meta=meta, artifact_url=artifact_url)
 
-    def get_or_create_store(self, url, secrets: dict = None) -> (DataStore, str):
+    def get_or_create_store(
+        self, url, secrets: dict = None, project_name=""
+    ) -> (DataStore, str):
         schema, endpoint, parsed_url = parse_url(url)
         subpath = parsed_url.path
         store_key = f"{schema}://{endpoint}"
 
         if schema == "ds":
-            datastore_profile = datastore_profile_read(url)
+            datastore_profile = datastore_profile_read(url, project_name, secrets)
             if secrets and datastore_profile.secrets():
                 secrets = merge(secrets, datastore_profile.secrets())
             else: