zenml-nightly 0.70.0.dev20241125__py3-none-any.whl → 0.70.0.dev20241201__py3-none-any.whl

zenml/models/v2/core/pipeline_run.py

@@ -237,6 +237,10 @@ class PipelineRunResponseMetadata(WorkspaceScopedResponseMetadata):
         default=False,
         description="Whether a template can be created from this run.",
     )
+    step_substitutions: Dict[str, Dict[str, str]] = Field(
+        title="Substitutions used in the step runs of this pipeline run.",
+        default_factory=dict,
+    )
 
 
 class PipelineRunResponseResources(WorkspaceScopedResponseResources):
@@ -546,6 +550,15 @@ class PipelineRunResponse(
         """
         return self.get_metadata().is_templatable
 
+    @property
+    def step_substitutions(self) -> Dict[str, Dict[str, str]]:
+        """The `step_substitutions` property.
+
+        Returns:
+            the value of the property.
+        """
+        return self.get_metadata().step_substitutions
+
     @property
     def model_version(self) -> Optional[ModelVersionResponse]:
         """The `model_version` property.
@@ -722,6 +735,7 @@ class PipelineRunFilter(WorkspaceScopedTaggableFilter):
             PipelineDeploymentSchema,
             PipelineRunSchema,
             PipelineSchema,
+            RunMetadataResourceSchema,
             RunMetadataSchema,
             ScheduleSchema,
             StackComponentSchema,
@@ -897,10 +911,12 @@ class PipelineRunFilter(WorkspaceScopedTaggableFilter):
 
             for key, value in self.run_metadata.items():
                 additional_filter = and_(
-                    RunMetadataSchema.resource_id == PipelineRunSchema.id,
-                    RunMetadataSchema.resource_type
+                    RunMetadataResourceSchema.resource_id
+                    == PipelineRunSchema.id,
+                    RunMetadataResourceSchema.resource_type
                     == MetadataResourceTypes.PIPELINE_RUN,
-                    RunMetadataSchema.key == key,
+                    RunMetadataResourceSchema.run_metadata_id
+                    == RunMetadataSchema.id,
                     self.generate_custom_query_conditions_for_column(
                         value=value,
                         table=RunMetadataSchema,

zenml/models/v2/core/run_metadata.py

@@ -13,16 +13,16 @@
 #  permissions and limitations under the License.
 """Models representing run metadata."""
 
-from typing import Dict, Optional
+from typing import Dict, List, Optional
 from uuid import UUID
 
-from pydantic import Field
+from pydantic import Field, model_validator
 
-from zenml.enums import MetadataResourceTypes
 from zenml.metadata.metadata_types import MetadataType, MetadataTypeEnum
 from zenml.models.v2.base.scoped import (
     WorkspaceScopedRequest,
 )
+from zenml.models.v2.misc.run_metadata import RunMetadataResource
 
 # ------------------ Request Model ------------------
 
@@ -30,14 +30,12 @@ from zenml.models.v2.base.scoped import (
 class RunMetadataRequest(WorkspaceScopedRequest):
     """Request model for run metadata."""
 
-    resource_id: UUID = Field(
-        title="The ID of the resource that this metadata belongs to.",
-    )
-    resource_type: MetadataResourceTypes = Field(
-        title="The type of the resource that this metadata belongs to.",
+    resources: List[RunMetadataResource] = Field(
+        title="The list of resources that this metadata belongs to."
     )
     stack_component_id: Optional[UUID] = Field(
-        title="The ID of the stack component that this metadata belongs to."
+        title="The ID of the stack component that this metadata belongs to.",
+        default=None,
     )
     values: Dict[str, "MetadataType"] = Field(
         title="The metadata to be created.",
@@ -45,3 +43,26 @@ class RunMetadataRequest(WorkspaceScopedRequest):
     types: Dict[str, "MetadataTypeEnum"] = Field(
         title="The types of the metadata to be created.",
     )
+    publisher_step_id: Optional[UUID] = Field(
+        title="The ID of the step execution that published this metadata.",
+        default=None,
+    )
+
+    @model_validator(mode="after")
+    def validate_values_keys(self) -> "RunMetadataRequest":
+        """Validates if the keys in the metadata are properly defined.
+
+        Returns:
+            self
+
+        Raises:
+            ValueError: if one of the key in the metadata contains `:`
+        """
+        invalid_keys = [key for key in self.values.keys() if ":" in key]
+        if invalid_keys:
+            raise ValueError(
+                "You can not use colons (`:`) in the key names when you "
+                "are creating metadata for your ZenML objects. Please change "
+                f"the following keys: {invalid_keys}"
+            )
+        return self

zenml/models/v2/core/step_run.py

@@ -142,7 +142,7 @@ class StepRunRequest(WorkspaceScopedRequest):
 class StepRunUpdate(BaseModel):
     """Update model for step runs."""
 
-    outputs: Dict[str, UUID] = Field(
+    outputs: Dict[str, List[UUID]] = Field(
         title="The IDs of the output artifact versions of the step run.",
         default={},
     )
@@ -594,6 +594,7 @@ class StepRunFilter(WorkspaceScopedFilter):
         from zenml.zen_stores.schemas import (
             ModelSchema,
             ModelVersionSchema,
+            RunMetadataResourceSchema,
             RunMetadataSchema,
             StepRunSchema,
         )
@@ -612,10 +613,11 @@ class StepRunFilter(WorkspaceScopedFilter):
 
             for key, value in self.run_metadata.items():
                 additional_filter = and_(
-                    RunMetadataSchema.resource_id == StepRunSchema.id,
-                    RunMetadataSchema.resource_type
+                    RunMetadataResourceSchema.resource_id == StepRunSchema.id,
+                    RunMetadataResourceSchema.resource_type
                     == MetadataResourceTypes.STEP_RUN,
-                    RunMetadataSchema.key == key,
+                    RunMetadataResourceSchema.run_metadata_id
+                    == RunMetadataSchema.id,
                     self.generate_custom_query_conditions_for_column(
                         value=value,
                         table=RunMetadataSchema,

zenml/models/v2/misc/run_metadata.py

@@ -0,0 +1,38 @@
+#  Copyright (c) ZenML GmbH 2024. All Rights Reserved.
+#
+#  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:
+#
+#       https://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.
+"""Utility classes for modeling run metadata."""
+
+from datetime import datetime
+from uuid import UUID
+
+from pydantic import BaseModel, Field
+
+from zenml.enums import MetadataResourceTypes
+from zenml.metadata.metadata_types import MetadataType
+
+
+class RunMetadataResource(BaseModel):
+    """Utility class to help identify resources to tag metadata to."""
+
+    id: UUID = Field(title="The ID of the resource.")
+    type: MetadataResourceTypes = Field(title="The type of the resource.")
+
+
+class RunMetadataEntry(BaseModel):
+    """Utility class to sort/list run metadata entries."""
+
+    value: MetadataType = Field(title="The value for the run metadata entry")
+    created: datetime = Field(
+        title="The timestamp when this resource was created."
+    )

zenml/orchestrators/input_utils.py

@@ -20,7 +20,7 @@ from zenml.client import Client
 from zenml.config.step_configurations import Step
 from zenml.enums import ArtifactSaveType, StepRunInputArtifactType
 from zenml.exceptions import InputResolutionError
-from zenml.utils import pagination_utils
+from zenml.utils import pagination_utils, string_utils
 
 if TYPE_CHECKING:
     from zenml.models import PipelineRunResponse
@@ -53,7 +53,8 @@ def resolve_step_inputs(
     current_run_steps = {
         run_step.name: run_step
         for run_step in pagination_utils.depaginate(
-            Client().list_run_steps, pipeline_run_id=pipeline_run.id
+            Client().list_run_steps,
+            pipeline_run_id=pipeline_run.id,
         )
     }
 
@@ -66,11 +67,23 @@ def resolve_step_inputs(
                 f"No step `{input_.step_name}` found in current run."
             )
 
+        # Try to get the substitutions from the pipeline run first, as we
+        # already have a hydrated version of that. In the unlikely case
+        # that the pipeline run is outdated, we fetch it from the step
+        # run instead which will costs us one hydration call.
+        substitutions = (
+            pipeline_run.step_substitutions.get(step_run.name)
+            or step_run.config.substitutions
+        )
+        output_name = string_utils.format_name_template(
+            input_.output_name, substitutions=substitutions
+        )
+
         try:
-            outputs = step_run.outputs[input_.output_name]
+            outputs = step_run.outputs[output_name]
         except KeyError:
             raise InputResolutionError(
-                f"No step output `{input_.output_name}` found for step "
+                f"No step output `{output_name}` found for step "
                 f"`{input_.step_name}`."
             )
 
@@ -83,12 +96,12 @@ def resolve_step_inputs(
             # This should never happen, there can only be a single regular step
             # output for a name
             raise InputResolutionError(
-                f"Too many step outputs for output `{input_.output_name}` of "
+                f"Too many step outputs for output `{output_name}` of "
                 f"step `{input_.step_name}`."
             )
         elif len(step_outputs) == 0:
             raise InputResolutionError(
-                f"No step output `{input_.output_name}` found for step "
+                f"No step output `{output_name}` found for step "
                 f"`{input_.step_name}`."
             )
 

zenml/orchestrators/publish_utils.py

@@ -21,6 +21,7 @@ from zenml.enums import ExecutionStatus, MetadataResourceTypes
 from zenml.models import (
     PipelineRunResponse,
     PipelineRunUpdate,
+    RunMetadataResource,
     StepRunResponse,
     StepRunUpdate,
 )
@@ -32,7 +33,7 @@ if TYPE_CHECKING:
 
 
 def publish_successful_step_run(
-    step_run_id: "UUID", output_artifact_ids: Dict[str, "UUID"]
+    step_run_id: "UUID", output_artifact_ids: Dict[str, List["UUID"]]
 ) -> "StepRunResponse":
     """Publishes a successful step run.
 
@@ -129,8 +130,11 @@ def publish_pipeline_run_metadata(
     for stack_component_id, metadata in pipeline_run_metadata.items():
         client.create_run_metadata(
             metadata=metadata,
-            resource_id=pipeline_run_id,
-            resource_type=MetadataResourceTypes.PIPELINE_RUN,
+            resources=[
+                RunMetadataResource(
+                    id=pipeline_run_id, type=MetadataResourceTypes.PIPELINE_RUN
+                )
+            ],
             stack_component_id=stack_component_id,
         )
 
@@ -150,7 +154,10 @@ def publish_step_run_metadata(
     for stack_component_id, metadata in step_run_metadata.items():
         client.create_run_metadata(
             metadata=metadata,
-            resource_id=step_run_id,
-            resource_type=MetadataResourceTypes.STEP_RUN,
+            resources=[
+                RunMetadataResource(
+                    id=step_run_id, type=MetadataResourceTypes.STEP_RUN
+                )
+            ],
             stack_component_id=stack_component_id,
         )

zenml/orchestrators/step_launcher.py

@@ -309,8 +309,12 @@ class StepLauncher:
             The created or existing pipeline run,
             and a boolean indicating whether the run was created or reused.
         """
-        run_name = orchestrator_utils.get_run_name(
-            run_name_template=self._deployment.run_name_template
+        start_time = datetime.utcnow()
+        run_name = string_utils.format_name_template(
+            name_template=self._deployment.run_name_template,
+            substitutions=self._deployment.pipeline_configuration._get_full_substitutions(
+                start_time
+            ),
         )
 
         logger.debug("Creating pipeline run %s", run_name)
@@ -329,7 +333,7 @@ class StepLauncher:
             ),
             status=ExecutionStatus.RUNNING,
             orchestrator_environment=get_run_environment_dict(),
-            start_time=datetime.utcnow(),
+            start_time=start_time,
             tags=self._deployment.pipeline_configuration.tags,
         )
         return client.zen_store.get_or_create_run(pipeline_run)

zenml/orchestrators/step_run_utils.py

@@ -309,6 +309,9 @@ def create_cached_step_runs(
         for invocation_id in cache_candidates:
             visited_invocations.add(invocation_id)
 
+            # Make sure the request factory has the most up to date pipeline
+            # run to avoid hydration calls
+            request_factory.pipeline_run = pipeline_run
             try:
                 step_run_request = request_factory.create_request(
                     invocation_id
@@ -354,13 +357,16 @@ def create_cached_step_runs(
 
 
 def get_or_create_model_version_for_pipeline_run(
-    model: "Model", pipeline_run: PipelineRunResponse
+    model: "Model",
+    pipeline_run: PipelineRunResponse,
+    substitutions: Dict[str, str],
 ) -> Tuple[ModelVersionResponse, bool]:
     """Get or create a model version as part of a pipeline run.
 
     Args:
         model: The model to get or create.
         pipeline_run: The pipeline run for which the model should be created.
+        substitutions: Substitutions to apply to the model version name.
 
     Returns:
         The model version and a boolean indicating whether it was newly created
@@ -374,12 +380,14 @@ def get_or_create_model_version_for_pipeline_run(
         return model._get_model_version(), False
     elif model.version:
         if isinstance(model.version, str):
-            start_time = pipeline_run.start_time or datetime.utcnow()
             model.version = string_utils.format_name_template(
                 model.version,
-                date=start_time.strftime("%Y_%m_%d"),
-                time=start_time.strftime("%H_%M_%S_%f"),
+                substitutions=substitutions,
             )
+        model.name = string_utils.format_name_template(
+            model.name,
+            substitutions=substitutions,
+        )
 
         return (
             model._get_or_create_model_version(),
@@ -460,7 +468,9 @@ def prepare_pipeline_run_model_version(
         model_version = pipeline_run.model_version
     elif config_model := pipeline_run.config.model:
         model_version, _ = get_or_create_model_version_for_pipeline_run(
-            model=config_model, pipeline_run=pipeline_run
+            model=config_model,
+            pipeline_run=pipeline_run,
+            substitutions=pipeline_run.config.substitutions,
         )
         pipeline_run = Client().zen_store.update_run(
             run_id=pipeline_run.id,
@@ -492,7 +502,9 @@ def prepare_step_run_model_version(
         model_version = step_run.model_version
     elif config_model := step_run.config.model:
         model_version, created = get_or_create_model_version_for_pipeline_run(
-            model=config_model, pipeline_run=pipeline_run
+            model=config_model,
+            pipeline_run=pipeline_run,
+            substitutions=step_run.config.substitutions,
         )
         step_run = Client().zen_store.update_run_step(
             step_run_id=step_run.id,
@@ -518,10 +530,15 @@ def log_model_version_dashboard_url(
     Args:
         model_version: The model version for which to log the dashboard URL.
     """
-    from zenml.utils.cloud_utils import try_get_model_version_url
+    from zenml.utils.dashboard_utils import get_model_version_url
 
-    if model_version_url_logs := try_get_model_version_url(model_version):
-        logger.info(model_version_url_logs)
+    if model_version_url := get_model_version_url(model_version.id):
+        logger.info(
+            "Dashboard URL for Model Version `%s (%s)`:\n%s",
+            model_version.model.name,
+            model_version.name,
+            model_version_url,
+        )
     else:
         logger.info(
             "Models can be viewed in the dashboard using ZenML Pro. Sign up "

zenml/orchestrators/step_runner.py

@@ -56,7 +56,7 @@ from zenml.steps.utils import (
     parse_return_type_annotations,
     resolve_type_annotation,
 )
-from zenml.utils import materializer_utils, source_utils
+from zenml.utils import materializer_utils, source_utils, string_utils
 from zenml.utils.typing_utils import get_origin, is_union
 
 if TYPE_CHECKING:
@@ -152,6 +152,15 @@ class StepRunner:
                 func=step_instance.entrypoint
             )
 
+            self._evaluate_artifact_names_in_collections(
+                step_run,
+                output_annotations,
+                [
+                    output_artifact_uris,
+                    output_materializers,
+                ],
+            )
+
             self._stack.prepare_step_run(info=step_run_info)
 
             # Initialize the step context singleton
@@ -257,7 +266,9 @@ class StepRunner:
 
             # Update the status and output artifacts of the step run.
             output_artifact_ids = {
-                output_name: artifact.id
+                output_name: [
+                    artifact.id,
+                ]
                 for output_name, artifact in output_artifacts.items()
             }
             publish_successful_step_run(
@@ -265,6 +276,32 @@ class StepRunner:
                 output_artifact_ids=output_artifact_ids,
             )
 
+    def _evaluate_artifact_names_in_collections(
+        self,
+        step_run: "StepRunResponse",
+        output_annotations: Dict[str, OutputSignature],
+        collections: List[Dict[str, Any]],
+    ) -> None:
+        """Evaluates the artifact names in the collections.
+
+        Args:
+            step_run: The step run.
+            output_annotations: The output annotations of the step function
+                (also evaluated).
+            collections: The collections to evaluate.
+        """
+        collections.append(output_annotations)
+        for k, v in list(output_annotations.items()):
+            name = k
+            if v.artifact_config and v.artifact_config.name:
+                name = string_utils.format_name_template(
+                    v.artifact_config.name,
+                    substitutions=step_run.config.substitutions,
+                )
+
+            for d in collections:
+                d[name] = d.pop(k)
+
     def _load_step(self) -> "BaseStep":
         """Load the step instance.
 
@@ -400,7 +437,7 @@ class StepRunner:
                 **artifact.get_hydrated_version().model_dump()
             )
 
-        if data_type is Any or is_union(get_origin(data_type)):
+        if data_type in (None, Any) or is_union(get_origin(data_type)):
             # Entrypoint function does not define a specific type for the input,
             # we use the datatype of the stored artifact
             data_type = source_utils.load(artifact.data_type)

zenml/orchestrators/utils.py

@@ -32,7 +32,6 @@ from zenml.constants import (
 from zenml.enums import AuthScheme, StackComponentType, StoreType
 from zenml.logger import get_logger
 from zenml.stack import StackComponent
-from zenml.utils.string_utils import format_name_template
 
 logger = get_logger(__name__)
 
@@ -40,7 +39,9 @@ if TYPE_CHECKING:
     from zenml.artifact_stores.base_artifact_store import BaseArtifactStore
 
 
-def get_orchestrator_run_name(pipeline_name: str) -> str:
+def get_orchestrator_run_name(
+    pipeline_name: str, max_length: Optional[int] = None
+) -> str:
     """Gets an orchestrator run name.
 
     This run name is not the same as the ZenML run name but can instead be
@@ -48,11 +49,31 @@ def get_orchestrator_run_name(pipeline_name: str) -> str:
 
     Args:
         pipeline_name: Name of the pipeline that will run.
+        max_length: Maximum length of the generated name.
+
+    Raises:
+        ValueError: If the max length is below 8 characters.
 
     Returns:
         The orchestrator run name.
     """
-    return f"{pipeline_name}_{random.Random().getrandbits(128):032x}"
+    suffix_length = 32
+    pipeline_name = f"{pipeline_name}_"
+
+    if max_length:
+        if max_length < 8:
+            raise ValueError(
+                "Maximum length for orchestrator run name must be 8 or above."
+            )
+
+        # Make sure we always have a certain suffix to guarantee no overlap
+        # with other runs
+        suffix_length = min(32, max(8, max_length - len(pipeline_name)))
+        pipeline_name = pipeline_name[: (max_length - suffix_length)]
+
+    suffix = "".join(random.choices("0123456789abcdef", k=suffix_length))
+
+    return f"{pipeline_name}{suffix}"
 
 
 def is_setting_enabled(
@@ -174,26 +195,6 @@ def get_config_environment_vars(
     return environment_vars
 
 
-def get_run_name(run_name_template: str) -> str:
-    """Fill out the run name template to get a complete run name.
-
-    Args:
-        run_name_template: The run name template to fill out.
-
-    Raises:
-        ValueError: If the run name is empty.
-
-    Returns:
-        The run name derived from the template.
-    """
-    run_name = format_name_template(run_name_template)
-
-    if run_name == "":
-        raise ValueError("Empty run names are not allowed.")
-
-    return run_name
-
-
 class register_artifact_store_filesystem:
     """Context manager for the artifact_store/filesystem_registry dependency.
 

zenml/pipelines/pipeline_decorator.py

@@ -55,6 +55,7 @@ def pipeline(
     on_failure: Optional["HookSpecification"] = None,
     on_success: Optional["HookSpecification"] = None,
     model: Optional["Model"] = None,
+    substitutions: Optional[Dict[str, str]] = None,
 ) -> Callable[["F"], "Pipeline"]: ...
 
 
@@ -71,6 +72,7 @@ def pipeline(
     on_failure: Optional["HookSpecification"] = None,
     on_success: Optional["HookSpecification"] = None,
     model: Optional["Model"] = None,
+    substitutions: Optional[Dict[str, str]] = None,
 ) -> Union["Pipeline", Callable[["F"], "Pipeline"]]:
     """Decorator to create a pipeline.
 
@@ -91,6 +93,7 @@ def pipeline(
             function with no arguments, or a source path to such a function
             (e.g. `module.my_function`).
         model: configuration of the model in the Model Control Plane.
+        substitutions: Extra placeholders to use in the name templates.
 
     Returns:
         A pipeline instance.
@@ -111,6 +114,7 @@ def pipeline(
             on_success=on_success,
             model=model,
             entrypoint=func,
+            substitutions=substitutions,
         )
 
         p.__doc__ = func.__doc__