Execution

zenml.execution

Step and pipeline execution.

Modules

pipeline

Pipeline execution.

Modules

dynamic

Dynamic pipeline execution.

Modules

outputs

Dynamic pipeline execution outputs.

Classes

ArtifactFuture(wrapped: Future[StepRunOutputs], invocation_id: str, index: int)

Bases: _BaseStepRunFuture

Future for a step run output artifact.

Initialize the future.

Parameters:

Name	Type	Description	Default
wrapped	Future[StepRunOutputs]	The wrapped future object.	required
invocation_id	str	The invocation ID of the step run.	required
index	int	The index of the output artifact.	required

Source code in src/zenml/execution/pipeline/dynamic/outputs.py

def __init__(
    self, wrapped: Future[StepRunOutputs], invocation_id: str, index: int
) -> None:
    """Initialize the future.

    Args:
        wrapped: The wrapped future object.
        invocation_id: The invocation ID of the step run.
        index: The index of the output artifact.
    """
    super().__init__(wrapped=wrapped, invocation_id=invocation_id)
    self._index = index

Functions

load(disable_cache: bool = False) -> Any

Load the step run output artifact data.

Parameters:

Name	Type	Description	Default
disable_cache	bool	Whether to disable the artifact cache.	False

Returns:

Type	Description
Any	The step run output artifact data.

Source code in src/zenml/execution/pipeline/dynamic/outputs.py

def load(self, disable_cache: bool = False) -> Any:
    """Load the step run output artifact data.

    Args:
        disable_cache: Whether to disable the artifact cache.

    Returns:
        The step run output artifact data.
    """
    return self.result().load(disable_cache=disable_cache)

result() -> OutputArtifact

Get the output artifact this future represents.

Raises:

Type	Description
RuntimeError	If the future returned an invalid output.

Returns:

Type	Description
OutputArtifact	The output artifact.

Source code in src/zenml/execution/pipeline/dynamic/outputs.py

def result(self) -> OutputArtifact:
    """Get the output artifact this future represents.

    Raises:
        RuntimeError: If the future returned an invalid output.

    Returns:
        The output artifact.
    """
    result = self._wrapped.result()
    if isinstance(result, OutputArtifact):
        return result
    elif isinstance(result, tuple):
        return result[self._index]
    else:
        raise RuntimeError(
            f"Step {self._invocation_id} returned an invalid output: "
            f"{result}."
        )

MapResultsFuture(futures: List[StepRunOutputsFuture])

Future that represents the results of a step.map/product(...) call.

Initialize the map results future.

Parameters:

Name	Type	Description	Default
futures	List[StepRunOutputsFuture]	The step run futures.	required

Source code in src/zenml/execution/pipeline/dynamic/outputs.py

def __init__(self, futures: List[StepRunOutputsFuture]) -> None:
    """Initialize the map results future.

    Args:
        futures: The step run futures.
    """
    self.futures = futures

Functions

result() -> List[StepRunOutputs]

Get the step run outputs this future represents.

Returns:

Type	Description
List[StepRunOutputs]	The step run outputs.

Source code in src/zenml/execution/pipeline/dynamic/outputs.py

def result(self) -> List[StepRunOutputs]:
    """Get the step run outputs this future represents.

    Returns:
        The step run outputs.
    """
    return [future.result() for future in self.futures]

unpack() -> Tuple[List[ArtifactFuture], ...]

Unpack the map results future.

This method can be used to get lists of artifact futures that represent the outputs of all the step runs that are part of this map result.

Example:

from zenml import pipeline, step

@step
def create_int_list() -> list[int]:
    return [1, 2]

@step
def do_something(a: int) -> Tuple[int, int]:
    return a * 2, a * 3

@pipeline
def map_pipeline():
    int_list = create_int_list()
    results = do_something.map(a=int_list)
    double, triple = results.unpack()

    # [future.load() for future in double] will return [2, 4]
    # [future.load() for future in triple] will return [3, 6]

Returns:

Type	Description
Tuple[List[ArtifactFuture], ...]	The unpacked map results.

Source code in src/zenml/execution/pipeline/dynamic/outputs.py

def unpack(self) -> Tuple[List[ArtifactFuture], ...]:
    """Unpack the map results future.

    This method can be used to get lists of artifact futures that represent
    the outputs of all the step runs that are part of this map result.

    Example:
    ```python
    from zenml import pipeline, step

    @step
    def create_int_list() -> list[int]:
        return [1, 2]

    @step
    def do_something(a: int) -> Tuple[int, int]:
        return a * 2, a * 3

    @pipeline
    def map_pipeline():
        int_list = create_int_list()
        results = do_something.map(a=int_list)
        double, triple = results.unpack()

        # [future.load() for future in double] will return [2, 4]
        # [future.load() for future in triple] will return [3, 6]
    ```

    Returns:
        The unpacked map results.
    """
    return tuple(map(list, zip(*self.futures)))

OutputArtifact

Bases: ArtifactVersionResponse

Dynamic step run output artifact.

StepRunOutputsFuture(wrapped: Future[StepRunOutputs], invocation_id: str, output_keys: List[str])

Bases: _BaseStepRunFuture

Future for a step run output.

Initialize the future.

Parameters:

Name	Type	Description	Default
wrapped	Future[StepRunOutputs]	The wrapped future object.	required
invocation_id	str	The invocation ID of the step run.	required
output_keys	List[str]	The output keys of the step run.	required

Source code in src/zenml/execution/pipeline/dynamic/outputs.py

def __init__(
    self,
    wrapped: Future[StepRunOutputs],
    invocation_id: str,
    output_keys: List[str],
) -> None:
    """Initialize the future.

    Args:
        wrapped: The wrapped future object.
        invocation_id: The invocation ID of the step run.
        output_keys: The output keys of the step run.
    """
    super().__init__(wrapped=wrapped, invocation_id=invocation_id)
    self._output_keys = output_keys

Functions

artifacts() -> StepRunOutputs

Get the step run output artifacts.

Returns:

Type	Description
StepRunOutputs	The step run output artifacts.

Source code in src/zenml/execution/pipeline/dynamic/outputs.py

def artifacts(self) -> StepRunOutputs:
    """Get the step run output artifacts.

    Returns:
        The step run output artifacts.
    """
    return self._wrapped.result()

get_artifact(key: str) -> ArtifactFuture

Get an artifact future by key.

Parameters:

Name	Type	Description	Default
key	str	The key of the artifact future.	required

Raises:

Type	Description
KeyError	If no artifact for the given name exists.

Returns:

Type	Description
ArtifactFuture	The artifact future.

Source code in src/zenml/execution/pipeline/dynamic/outputs.py

def get_artifact(self, key: str) -> ArtifactFuture:
    """Get an artifact future by key.

    Args:
        key: The key of the artifact future.

    Raises:
        KeyError: If no artifact for the given name exists.

    Returns:
        The artifact future.
    """
    if key not in self._output_keys:
        raise KeyError(
            f"Step run {self._invocation_id} does not have an output with "
            f"the name: {key}."
        )

    return ArtifactFuture(
        wrapped=self._wrapped,
        invocation_id=self._invocation_id,
        index=self._output_keys.index(key),
    )

load(disable_cache: bool = False) -> Any

Get the step run output artifact data.

Parameters:

Name	Type	Description	Default
disable_cache	bool	Whether to disable the artifact cache.	False

Raises:

Type	Description
ValueError	If the step run output is invalid.

Returns:

Type	Description
Any	The step run output artifact data.

Source code in src/zenml/execution/pipeline/dynamic/outputs.py

def load(self, disable_cache: bool = False) -> Any:
    """Get the step run output artifact data.

    Args:
        disable_cache: Whether to disable the artifact cache.

    Raises:
        ValueError: If the step run output is invalid.

    Returns:
        The step run output artifact data.
    """
    result = self.artifacts()

    if result is None:
        return None
    elif isinstance(result, ArtifactVersionResponse):
        return result.load(disable_cache=disable_cache)
    elif isinstance(result, tuple):
        return tuple(
            item.load(disable_cache=disable_cache) for item in result
        )
    else:
        raise ValueError(f"Invalid step run output: {result}")

result() -> StepRunOutputs

Get the step run outputs this future represents.

Returns:

Type	Description
StepRunOutputs	The step run outputs.

Source code in src/zenml/execution/pipeline/dynamic/outputs.py

def result(self) -> StepRunOutputs:
    """Get the step run outputs this future represents.

    Returns:
        The step run outputs.
    """
    return self._wrapped.result()

Functions

run_context

Dynamic pipeline run context.

Classes

DynamicPipelineRunContext(pipeline: DynamicPipeline, snapshot: PipelineSnapshotResponse, run: PipelineRunResponse, runner: DynamicPipelineRunner)

Bases: BaseContext

Dynamic pipeline run context.

Initialize the dynamic pipeline run context.

Parameters:

Name	Type	Description	Default
pipeline	DynamicPipeline	The dynamic pipeline that is being executed.	required
snapshot	PipelineSnapshotResponse	The snapshot of the pipeline.	required
run	PipelineRunResponse	The pipeline run.	required
runner	DynamicPipelineRunner	The dynamic pipeline runner.	required

Source code in src/zenml/execution/pipeline/dynamic/run_context.py

def __init__(
    self,
    pipeline: "DynamicPipeline",
    snapshot: "PipelineSnapshotResponse",
    run: "PipelineRunResponse",
    runner: "DynamicPipelineRunner",
) -> None:
    """Initialize the dynamic pipeline run context.

    Args:
        pipeline: The dynamic pipeline that is being executed.
        snapshot: The snapshot of the pipeline.
        run: The pipeline run.
        runner: The dynamic pipeline runner.
    """
    super().__init__()
    self._pipeline = pipeline
    self._snapshot = snapshot
    self._run = run
    self._runner = runner

Attributes

pipeline: DynamicPipeline property

The pipeline that is being executed.

Returns:

Type	Description
DynamicPipeline	The pipeline that is being executed.

run: PipelineRunResponse property

The pipeline run.

Returns:

Type	Description
PipelineRunResponse	The pipeline run.

runner: DynamicPipelineRunner property

The runner executing the pipeline.

Returns:

Type	Description
DynamicPipelineRunner	The runner executing the pipeline.

snapshot: PipelineSnapshotResponse property

The snapshot of the pipeline.

Returns:

Type	Description
PipelineSnapshotResponse	The snapshot of the pipeline.

Functions

Modules

runner

Dynamic pipeline runner.

Classes

DynamicPipelineRunner(snapshot: PipelineSnapshotResponse, run: Optional[PipelineRunResponse])

Dynamic pipeline runner.

Initialize the dynamic pipeline runner.

Parameters:

Name	Type	Description	Default
snapshot	PipelineSnapshotResponse	The snapshot of the pipeline.	required
run	Optional[PipelineRunResponse]	The pipeline run.	required

Raises:

Type	Description
RuntimeError	If the snapshot has no associated stack.

Source code in src/zenml/execution/pipeline/dynamic/runner.py

def __init__(
    self,
    snapshot: "PipelineSnapshotResponse",
    run: Optional["PipelineRunResponse"],
) -> None:
    """Initialize the dynamic pipeline runner.

    Args:
        snapshot: The snapshot of the pipeline.
        run: The pipeline run.

    Raises:
        RuntimeError: If the snapshot has no associated stack.
    """
    if not snapshot.stack:
        raise RuntimeError("Missing stack for snapshot.")

    if (
        snapshot.pipeline_configuration.execution_mode
        != ExecutionMode.STOP_ON_FAILURE
    ):
        logger.warning(
            "Only the `%s` execution mode is supported for "
            "dynamic pipelines right now. "
            "The execution mode `%s` will be ignored.",
            ExecutionMode.STOP_ON_FAILURE,
            snapshot.pipeline_configuration.execution_mode,
        )

    self._snapshot = snapshot
    self._run = run
    # TODO: make this configurable
    self._executor = ThreadPoolExecutor(max_workers=10)
    self._pipeline: Optional["DynamicPipeline"] = None
    self._orchestrator = Stack.from_model(snapshot.stack).orchestrator
    self._orchestrator_run_id = (
        self._orchestrator.get_orchestrator_run_id()
    )
    self._futures: List[StepRunOutputsFuture] = []

Attributes

pipeline: DynamicPipeline property

The pipeline that the runner is executing.

Raises:

Type	Description
RuntimeError	If the pipeline can't be loaded.

Returns:

Type	Description
DynamicPipeline	The pipeline that the runner is executing.

Functions

await_all_step_run_futures() -> None

Await all step run output futures.

Source code in src/zenml/execution/pipeline/dynamic/runner.py

def await_all_step_run_futures(self) -> None:
    """Await all step run output futures."""
    for future in self._futures:
        future._wait()
    self._futures = []

launch_step(step: BaseStep, id: Optional[str], args: Tuple[Any, ...], kwargs: Dict[str, Any], after: Union[StepRunFuture, Sequence[StepRunFuture], None] = None, concurrent: bool = False) -> Union[StepRunOutputs, StepRunOutputsFuture]

launch_step(
    step: BaseStep,
    id: Optional[str],
    args: Tuple[Any, ...],
    kwargs: Dict[str, Any],
    after: Union[
        StepRunFuture, Sequence[StepRunFuture], None
    ] = None,
    concurrent: Literal[False] = False,
) -> StepRunOutputs

launch_step(
    step: BaseStep,
    id: Optional[str],
    args: Tuple[Any, ...],
    kwargs: Dict[str, Any],
    after: Union[
        StepRunFuture, Sequence[StepRunFuture], None
    ] = None,
    concurrent: Literal[True] = True,
) -> StepRunOutputsFuture

Launch a step.

Parameters:

Name	Type	Description	Default
step	BaseStep	The step to launch.	required
id	Optional[str]	The invocation ID of the step.	required
args	Tuple[Any, ...]	The arguments for the step function.	required
kwargs	Dict[str, Any]	The keyword arguments for the step function.	required
after	Union[StepRunFuture, Sequence[StepRunFuture], None]	The step run output futures to wait for.	None
concurrent	bool	Whether to launch the step concurrently.	False

Returns:

Type	Description
Union[StepRunOutputs, StepRunOutputsFuture]	The step run outputs or a future for the step run outputs.

Source code in src/zenml/execution/pipeline/dynamic/runner.py

def launch_step(
    self,
    step: "BaseStep",
    id: Optional[str],
    args: Tuple[Any, ...],
    kwargs: Dict[str, Any],
    after: Union["StepRunFuture", Sequence["StepRunFuture"], None] = None,
    concurrent: bool = False,
) -> Union[StepRunOutputs, "StepRunOutputsFuture"]:
    """Launch a step.

    Args:
        step: The step to launch.
        id: The invocation ID of the step.
        args: The arguments for the step function.
        kwargs: The keyword arguments for the step function.
        after: The step run output futures to wait for.
        concurrent: Whether to launch the step concurrently.

    Returns:
        The step run outputs or a future for the step run outputs.
    """
    step = step.copy()
    compiled_step = compile_dynamic_step_invocation(
        snapshot=self._snapshot,
        pipeline=self.pipeline,
        step=step,
        id=id,
        inputs=convert_to_keyword_arguments(step.entrypoint, args, kwargs),
        after=after,
    )

    def _launch() -> StepRunOutputs:
        step_run = launch_step(
            snapshot=self._snapshot,
            step=compiled_step,
            orchestrator_run_id=self._orchestrator_run_id,
            retry=_should_retry_locally(
                compiled_step,
                self._snapshot.pipeline_configuration.docker_settings,
            ),
        )
        return _load_step_run_outputs(step_run.id)

    if concurrent:
        ctx = contextvars.copy_context()
        future = self._executor.submit(ctx.run, _launch)
        step_run_future = StepRunOutputsFuture(
            wrapped=future,
            invocation_id=compiled_step.spec.invocation_id,
            output_keys=list(compiled_step.config.outputs),
        )
        self._futures.append(step_run_future)
        return step_run_future
    else:
        return _launch()

map(step: BaseStep, args: Tuple[Any, ...], kwargs: Dict[str, Any], after: Union[StepRunFuture, Sequence[StepRunFuture], None] = None, product: bool = False) -> MapResultsFuture

Map over step inputs.

Parameters:

Name	Type	Description	Default
step	BaseStep	The step to run.	required
args	Tuple[Any, ...]	The arguments for the step function.	required
kwargs	Dict[str, Any]	The keyword arguments for the step function.	required
after	Union[StepRunFuture, Sequence[StepRunFuture], None]	The step run output futures to wait for before executing the steps.	None
product	bool	Whether to produce a cartesian product of the mapped inputs.	False

Returns:

Type	Description
MapResultsFuture	A future that represents the map results.

Source code in src/zenml/execution/pipeline/dynamic/runner.py

def map(
    self,
    step: "BaseStep",
    args: Tuple[Any, ...],
    kwargs: Dict[str, Any],
    after: Union["StepRunFuture", Sequence["StepRunFuture"], None] = None,
    product: bool = False,
) -> "MapResultsFuture":
    """Map over step inputs.

    Args:
        step: The step to run.
        args: The arguments for the step function.
        kwargs: The keyword arguments for the step function.
        after: The step run output futures to wait for before executing the
            steps.
        product: Whether to produce a cartesian product of the mapped
            inputs.

    Returns:
        A future that represents the map results.
    """
    kwargs = convert_to_keyword_arguments(step.entrypoint, args, kwargs)
    kwargs = await_step_inputs(kwargs)
    step_inputs = expand_mapped_inputs(kwargs, product=product)

    step_run_futures = [
        self.launch_step(
            step,
            id=None,
            args=(),
            kwargs=inputs,
            after=after,
            concurrent=True,
        )
        for inputs in step_inputs
    ]

    return MapResultsFuture(futures=step_run_futures)

run_pipeline() -> None

Run the pipeline.

Source code in src/zenml/execution/pipeline/dynamic/runner.py

def run_pipeline(self) -> None:
    """Run the pipeline."""
    with setup_pipeline_logging(
        source="orchestrator",
        snapshot=self._snapshot,
    ) as logs_request:
        if self._run:
            run = Client().zen_store.update_run(
                run_id=self._run.id,
                run_update=PipelineRunUpdate(
                    orchestrator_run_id=self._orchestrator_run_id,
                    add_logs=[logs_request] if logs_request else None,
                ),
            )
        else:
            run = create_placeholder_run(
                snapshot=self._snapshot,
                orchestrator_run_id=self._orchestrator_run_id,
                logs=logs_request,
            )

        with InMemoryArtifactCache():
            with DynamicPipelineRunContext(
                pipeline=self.pipeline,
                run=run,
                snapshot=self._snapshot,
                runner=self,
            ):
                self._orchestrator.run_init_hook(snapshot=self._snapshot)
                try:
                    # TODO: step logging isn't threadsafe
                    # TODO: what should be allowed as pipeline returns?
                    #  (artifacts, json serializable, anything?)
                    #  how do we show it in the UI?
                    params = self.pipeline.configuration.parameters or {}
                    self.pipeline._call_entrypoint(**params)
                    # The pipeline function finished successfully, but some
                    # steps might still be running. We now wait for all of
                    # them and raise any exceptions that occurred.
                    self.await_all_step_run_futures()
                except:
                    publish_failed_pipeline_run(run.id)
                    logger.error(
                        "Pipeline run failed. All in-progress step runs "
                        "will still finish executing."
                    )
                    raise
                finally:
                    self._orchestrator.run_cleanup_hook(
                        snapshot=self._snapshot
                    )
                    self._executor.shutdown(wait=True, cancel_futures=True)

                publish_successful_pipeline_run(run.id)

Functions

await_step_inputs(inputs: Dict[str, Any]) -> Dict[str, Any]

Await the inputs of a step.

Parameters:

Name	Type	Description	Default
inputs	Dict[str, Any]	The inputs of the step.	required

Raises:

Type	Description
RuntimeError	If a step run future with multiple output artifacts is passed as an input.

Returns:

Type	Description
Dict[str, Any]	The awaited inputs.

Source code in src/zenml/execution/pipeline/dynamic/runner.py

def await_step_inputs(inputs: Dict[str, Any]) -> Dict[str, Any]:
    """Await the inputs of a step.

    Args:
        inputs: The inputs of the step.

    Raises:
        RuntimeError: If a step run future with multiple output artifacts is
            passed as an input.

    Returns:
        The awaited inputs.
    """
    result = {}
    for key, value in inputs.items():
        if isinstance(value, MapResultsFuture):
            value = value.futures

        if (
            isinstance(value, Sequence)
            and value
            and all(isinstance(item, StepRunOutputsFuture) for item in value)
        ):
            if any(len(item._output_keys) != 1 for item in value):
                raise RuntimeError(
                    f"Invalid step input `{key}`: Passing a future that refers "
                    "to multiple output artifacts as an input to another step "
                    "is not allowed."
                )
            value = [item.artifacts() for item in value]
        elif isinstance(value, StepRunOutputsFuture):
            if len(value._output_keys) != 1:
                raise RuntimeError(
                    f"Invalid step input `{key}`: Passing a future that refers "
                    "to multiple output artifacts as an input to another step "
                    "is not allowed."
                )
            value = value.artifacts()

        if (
            isinstance(value, Sequence)
            and value
            and all(isinstance(item, ArtifactFuture) for item in value)
        ):
            value = [item.result() for item in value]

        if isinstance(value, ArtifactFuture):
            value = value.result()

        result[key] = value

    return result

compile_dynamic_step_invocation(snapshot: PipelineSnapshotResponse, pipeline: DynamicPipeline, step: BaseStep, inputs: Dict[str, Any], after: Union[StepRunFuture, ArtifactFuture, Sequence[Union[StepRunFuture, ArtifactFuture]], None] = None, id: Optional[str] = None) -> Step

Compile a dynamic step invocation.

Parameters:

Name	Type	Description	Default
snapshot	PipelineSnapshotResponse	The snapshot.	required
pipeline	DynamicPipeline	The dynamic pipeline.	required
step	BaseStep	The step to compile.	required
id	Optional[str]	Custom invocation ID.	None
inputs	Dict[str, Any]	The inputs for the step function.	required
after	Union[StepRunFuture, ArtifactFuture, Sequence[Union[StepRunFuture, ArtifactFuture]], None]	The step run output futures to wait for.	None

Returns:

Type	Description
Step	The compiled step.

Source code in src/zenml/execution/pipeline/dynamic/runner.py

def compile_dynamic_step_invocation(
    snapshot: "PipelineSnapshotResponse",
    pipeline: "DynamicPipeline",
    step: "BaseStep",
    inputs: Dict[str, Any],
    after: Union[
        "StepRunFuture",
        "ArtifactFuture",
        Sequence[Union["StepRunFuture", "ArtifactFuture"]],
        None,
    ] = None,
    id: Optional[str] = None,
) -> "Step":
    """Compile a dynamic step invocation.

    Args:
        snapshot: The snapshot.
        pipeline: The dynamic pipeline.
        step: The step to compile.
        id: Custom invocation ID.
        inputs: The inputs for the step function.
        after: The step run output futures to wait for.

    Returns:
        The compiled step.
    """
    upstream_steps = set()

    if isinstance(after, _BaseStepRunFuture):
        after._wait()
        upstream_steps.add(after.invocation_id)
    elif isinstance(after, MapResultsFuture):
        for future in after:
            future._wait()
            upstream_steps.add(future.invocation_id)
    elif isinstance(after, Sequence):
        for item in after:
            if isinstance(item, _BaseStepRunFuture):
                item._wait()
                upstream_steps.add(item.invocation_id)
            elif isinstance(item, MapResultsFuture):
                for future in item:
                    future._wait()
                    upstream_steps.add(future.invocation_id)

    inputs = await_step_inputs(inputs)

    for value in inputs.values():
        if isinstance(value, OutputArtifact):
            upstream_steps.add(value.step_name)

        if (
            isinstance(value, Sequence)
            and value
            and all(isinstance(item, OutputArtifact) for item in value)
        ):
            upstream_steps.update(item.step_name for item in value)

    default_parameters = {
        key: value
        for key, value in convert_to_keyword_arguments(
            step.entrypoint, (), inputs, apply_defaults=True
        ).items()
        if key not in inputs
    }

    input_artifacts = {}
    external_artifacts = {}
    for name, value in inputs.items():
        if isinstance(value, OutputArtifact):
            input_artifacts[name] = [
                StepArtifact(
                    invocation_id=value.step_name,
                    output_name=value.output_name,
                    annotation=OutputSignature(resolved_annotation=Any),
                    pipeline=pipeline,
                    chunk_index=value.chunk_index,
                    chunk_size=value.chunk_size,
                )
            ]
        elif (
            isinstance(value, list)
            and value
            and all(isinstance(item, OutputArtifact) for item in value)
        ):
            input_artifacts[name] = [
                StepArtifact(
                    invocation_id=item.step_name,
                    output_name=item.output_name,
                    annotation=OutputSignature(resolved_annotation=Any),
                    pipeline=pipeline,
                    chunk_index=item.chunk_index,
                    chunk_size=item.chunk_size,
                )
                for item in value
            ]
        elif isinstance(value, (ArtifactVersionResponse, ExternalArtifact)):
            external_artifacts[name] = value
        else:
            # TODO: should some of these be parameters?
            external_artifacts[name] = ExternalArtifact(value=value)

    if template := get_config_template(snapshot, step, pipeline):
        step._configuration = template.config.model_copy(
            update={"template": template.spec.invocation_id}
        )

    invocation_id = pipeline.add_step_invocation(
        step=step,
        custom_id=id,
        allow_id_suffix=not id,
        input_artifacts=input_artifacts,
        external_artifacts=external_artifacts,
        upstream_steps=upstream_steps,
        default_parameters=default_parameters,
        parameters={},
        model_artifacts_or_metadata={},
        client_lazy_loaders={},
    )

    return Compiler()._compile_step_invocation(
        invocation=pipeline.invocations[invocation_id],
        stack=Client().active_stack,
        step_config=None,
        pipeline=pipeline,
    )

convert_to_keyword_arguments(func: Callable[..., Any], args: Tuple[Any, ...], kwargs: Dict[str, Any], apply_defaults: bool = False) -> Dict[str, Any]

Convert function arguments to keyword arguments.

Parameters:

Name	Type	Description	Default
func	Callable[..., Any]	The function to convert the arguments to keyword arguments for.	required
args	Tuple[Any, ...]	The arguments to convert to keyword arguments.	required
kwargs	Dict[str, Any]	The keyword arguments to convert to keyword arguments.	required
apply_defaults	bool	Whether to apply the function default values.	False

Returns:

Type	Description
Dict[str, Any]	The keyword arguments.

Source code in src/zenml/execution/pipeline/dynamic/runner.py

def convert_to_keyword_arguments(
    func: Callable[..., Any],
    args: Tuple[Any, ...],
    kwargs: Dict[str, Any],
    apply_defaults: bool = False,
) -> Dict[str, Any]:
    """Convert function arguments to keyword arguments.

    Args:
        func: The function to convert the arguments to keyword arguments for.
        args: The arguments to convert to keyword arguments.
        kwargs: The keyword arguments to convert to keyword arguments.
        apply_defaults: Whether to apply the function default values.

    Returns:
        The keyword arguments.
    """
    signature = inspect.signature(func, follow_wrapped=True)
    bound_args = signature.bind_partial(*args, **kwargs)
    if apply_defaults:
        bound_args.apply_defaults()

    return bound_args.arguments

expand_mapped_inputs(inputs: Dict[str, Any], product: bool = False) -> List[Dict[str, Any]]

Find the mapped and unmapped inputs of a step.

Parameters:

Name	Type	Description	Default
inputs	Dict[str, Any]	The step function inputs.	required
product	bool	Whether to produce a cartesian product of the mapped inputs.	False

Raises:

Type	Description
RuntimeError	If no mapped inputs are found or the input combinations are not valid.

Returns:

Type	Description
List[Dict[str, Any]]	The step inputs.

Source code in src/zenml/execution/pipeline/dynamic/runner.py

def expand_mapped_inputs(
    inputs: Dict[str, Any],
    product: bool = False,
) -> List[Dict[str, Any]]:
    """Find the mapped and unmapped inputs of a step.

    Args:
        inputs: The step function inputs.
        product: Whether to produce a cartesian product of the mapped inputs.

    Raises:
        RuntimeError: If no mapped inputs are found or the input combinations
            are not valid.

    Returns:
        The step inputs.
    """
    static_inputs: Dict[str, Any] = {}
    mapped_input_names: List[str] = []
    mapped_inputs: List[Tuple[OutputArtifact, ...]] = []

    for key, value in inputs.items():
        if isinstance(value, _Unmapped):
            static_inputs[key] = value.value
        elif isinstance(value, OutputArtifact):
            if value.item_count is None:
                static_inputs[key] = value
            elif value.item_count == 0:
                raise RuntimeError(
                    f"Artifact `{value.id}` has 0 items and cannot be mapped "
                    "over. Wrap it with the `unmapped(...)` function to pass "
                    "the artifact without mapping over it."
                )
            else:
                mapped_input_names.append(key)
                mapped_inputs.append(
                    tuple(
                        value.model_copy(
                            update={"chunk_index": i, "chunk_size": 1}
                        )
                        for i in range(value.item_count)
                    )
                )
        elif (
            isinstance(value, ArtifactVersionResponse)
            and value.item_count is not None
        ):
            static_inputs[key] = value
            logger.warning(
                "Received sequence-like artifact for step input `%s`. Mapping "
                "over artifacts that are not step output artifacts is "
                "currently not supported, and the complete artifact will be "
                "passed to all steps. If you want to silence this warning, "
                "wrap your input with the `unmapped(...)` function.",
                key,
            )
        elif isinstance(value, Sequence):
            logger.warning(
                "Received sequence-like data for step input `%s`. Mapping over "
                "data that is not a step output artifact is currently not "
                "supported, and the complete data will be passed to all steps. "
                "If you want to silence this warning, wrap your input with the "
                "`unmapped(...)` function.",
                key,
            )
            static_inputs[key] = value
        else:
            static_inputs[key] = value

    if len(mapped_inputs) == 0:
        raise RuntimeError(
            "No inputs to map over found. When calling `.map(...)` or "
            "`.product(...)` on a step, you need to pass at least one "
            "sequence-like step output of a previous step as input."
        )

    step_inputs = []

    if product:
        for input_combination in itertools.product(*mapped_inputs):
            all_inputs = copy.deepcopy(static_inputs)
            for name, value in zip(mapped_input_names, input_combination):
                all_inputs[name] = value
            step_inputs.append(all_inputs)
    else:
        item_counts = [len(inputs) for inputs in mapped_inputs]
        if not all(count == item_counts[0] for count in item_counts):
            raise RuntimeError(
                f"All mapped input artifacts must have the same "
                "item counts, but you passed artifacts with item counts "
                f"{item_counts}. If you want "
                "to pass sequence-like artifacts without mapping over "
                "them, wrap them with the `unmapped(...)` function."
            )

        for i in range(item_counts[0]):
            all_inputs = copy.deepcopy(static_inputs)
            for name, artifact in zip(
                mapped_input_names,
                [artifact_list[i] for artifact_list in mapped_inputs],
            ):
                all_inputs[name] = artifact
            step_inputs.append(all_inputs)

    return step_inputs

get_config_template(snapshot: PipelineSnapshotResponse, step: BaseStep, pipeline: DynamicPipeline) -> Optional[Step]

Get the config template for a step executed in a dynamic pipeline.

Parameters:

Name	Type	Description	Default
snapshot	PipelineSnapshotResponse	The snapshot of the pipeline.	required
step	BaseStep	The step to get the config template for.	required
pipeline	DynamicPipeline	The dynamic pipeline that the step is being executed in.	required

Returns:

Type	Description
Optional[Step]	The config template for the step.

Source code in src/zenml/execution/pipeline/dynamic/runner.py

def get_config_template(
    snapshot: "PipelineSnapshotResponse",
    step: "BaseStep",
    pipeline: "DynamicPipeline",
) -> Optional["Step"]:
    """Get the config template for a step executed in a dynamic pipeline.

    Args:
        snapshot: The snapshot of the pipeline.
        step: The step to get the config template for.
        pipeline: The dynamic pipeline that the step is being executed in.

    Returns:
        The config template for the step.
    """
    for index, step_ in enumerate(pipeline.depends_on):
        if step_._static_id == step._static_id:
            break
    else:
        return None

    return list(snapshot.step_configurations.values())[index]

get_step_runtime(step_config: StepConfiguration, pipeline_docker_settings: DockerSettings) -> StepRuntime

Determine if a step should be run in process.

Parameters:

Name	Type	Description	Default
step_config	StepConfiguration	The step configuration.	required
pipeline_docker_settings	DockerSettings	The Docker settings of the parent pipeline.	required

Returns:

Type	Description
StepRuntime	The runtime for the step.

Source code in src/zenml/execution/pipeline/dynamic/runner.py

def get_step_runtime(
    step_config: "StepConfiguration",
    pipeline_docker_settings: "DockerSettings",
) -> StepRuntime:
    """Determine if a step should be run in process.

    Args:
        step_config: The step configuration.
        pipeline_docker_settings: The Docker settings of the parent pipeline.

    Returns:
        The runtime for the step.
    """
    if step_config.step_operator:
        return StepRuntime.ISOLATED

    if not Client().active_stack.orchestrator.can_run_isolated_steps:
        return StepRuntime.INLINE

    runtime = step_config.runtime

    if runtime is None:
        if not step_config.resource_settings.empty:
            runtime = StepRuntime.ISOLATED
        elif step_config.docker_settings != pipeline_docker_settings:
            runtime = StepRuntime.ISOLATED
        else:
            runtime = StepRuntime.INLINE

    return runtime

Modules

utils

Dynamic pipeline execution utilities.

Functions

unmapped(value: T) -> _Unmapped[T]

Helper function to pass an input without mapping over it.

Wrap any step input with this function and then pass it to step.map(...) to pass the full value to all steps.

Parameters:

Name	Type	Description	Default
value	T	The value to wrap.	required

Returns:

Type	Description
_Unmapped[T]	The wrapped value.

Source code in src/zenml/execution/pipeline/dynamic/utils.py

def unmapped(value: T) -> _Unmapped[T]:
    """Helper function to pass an input without mapping over it.

    Wrap any step input with this function and then pass it to `step.map(...)`
    to pass the full value to all steps.

    Args:
        value: The value to wrap.

    Returns:
        The wrapped value.
    """
    return _Unmapped(value)

utils

Pipeline execution utilities.

Classes Functions

prevent_pipeline_execution() -> Generator[None, None, None]

Context manager to prevent pipeline execution.

Yields:

Type	Description
None	None.

Source code in src/zenml/execution/pipeline/utils.py

@contextmanager
def prevent_pipeline_execution() -> Generator[None, None, None]:
    """Context manager to prevent pipeline execution.

    Yields:
        None.
    """
    token = _prevent_pipeline_execution.set(True)
    try:
        yield
    finally:
        _prevent_pipeline_execution.reset(token)

should_prevent_pipeline_execution() -> bool

Whether to prevent pipeline execution.

Returns:

Type	Description
bool	Whether to prevent pipeline execution.

Source code in src/zenml/execution/pipeline/utils.py

def should_prevent_pipeline_execution() -> bool:
    """Whether to prevent pipeline execution.

    Returns:
        Whether to prevent pipeline execution.
    """
    return _prevent_pipeline_execution.get()

submit_pipeline(snapshot: PipelineSnapshotResponse, stack: Stack, placeholder_run: Optional[PipelineRunResponse] = None) -> None

Submit a snapshot for execution.

Parameters:

Name	Type	Description	Default
snapshot	PipelineSnapshotResponse	The snapshot to submit.	required
stack	Stack	The stack on which to submit the snapshot.	required
placeholder_run	Optional[PipelineRunResponse]	An optional placeholder run for the snapshot.	None

noqa: DAR401

Raises: BaseException: Any exception that happened while submitting or running (in case it happens synchronously) the pipeline.

Source code in src/zenml/execution/pipeline/utils.py

def submit_pipeline(
    snapshot: "PipelineSnapshotResponse",
    stack: "Stack",
    placeholder_run: Optional["PipelineRunResponse"] = None,
) -> None:
    """Submit a snapshot for execution.

    Args:
        snapshot: The snapshot to submit.
        stack: The stack on which to submit the snapshot.
        placeholder_run: An optional placeholder run for the snapshot.

    # noqa: DAR401
    Raises:
        BaseException: Any exception that happened while submitting or running
            (in case it happens synchronously) the pipeline.
    """
    # Prevent execution of nested pipelines which might lead to
    # unexpected behavior
    with prevent_pipeline_execution():
        try:
            stack.prepare_pipeline_submission(snapshot=snapshot)
            stack.submit_pipeline(
                snapshot=snapshot,
                placeholder_run=placeholder_run,
            )
        except RunMonitoringError as e:
            # Don't mark the run as failed if the error happened during
            # monitoring of the run.
            raise e.original_exception from None
        except BaseException as e:
            if (
                placeholder_run
                and not Client()
                .get_pipeline_run(placeholder_run.id, hydrate=False)
                .status.is_finished
            ):
                # We failed during/before the submission of the run, so we mark
                # the run as failed if it's still in an unfinished state.
                publish_failed_pipeline_run(placeholder_run.id)

            raise e

step

Step execution.

Modules

utils

Step execution utilities.

Classes Functions

launch_step(snapshot: PipelineSnapshotResponse, step: Step, orchestrator_run_id: str, retry: bool = False) -> StepRunResponse

Launch a step.

Parameters:

Name	Type	Description	Default
snapshot	PipelineSnapshotResponse	The snapshot.	required
step	Step	The step to run.	required
orchestrator_run_id	str	The orchestrator run ID.	required
retry	bool	Whether to retry the step if it fails.	False

Raises:

Type	Description
RunStoppedException	If the run was stopped.
BaseException	If the step failed all retries.

Returns:

Type	Description
StepRunResponse	The step run response.

Source code in src/zenml/execution/step/utils.py

def launch_step(
    snapshot: "PipelineSnapshotResponse",
    step: "Step",
    orchestrator_run_id: str,
    retry: bool = False,
) -> StepRunResponse:
    """Launch a step.

    Args:
        snapshot: The snapshot.
        step: The step to run.
        orchestrator_run_id: The orchestrator run ID.
        retry: Whether to retry the step if it fails.

    Raises:
        RunStoppedException: If the run was stopped.
        BaseException: If the step failed all retries.

    Returns:
        The step run response.
    """

    def _launch_without_retry() -> StepRunResponse:
        launcher = StepLauncher(
            snapshot=snapshot,
            step=step,
            orchestrator_run_id=orchestrator_run_id,
        )
        return launcher.launch()

    if not retry:
        step_run = _launch_without_retry()
    else:
        retries = 0
        retry_config = step.config.retry
        max_retries = retry_config.max_retries if retry_config else 0
        delay = retry_config.delay if retry_config else 0
        backoff = retry_config.backoff if retry_config else 1

        while retries <= max_retries:
            try:
                step_run = _launch_without_retry()
            except RunStoppedException:
                # Don't retry if the run was stopped
                raise
            except BaseException:
                retries += 1
                if retries <= max_retries:
                    logger.info(
                        "Sleeping for %d seconds before retrying step `%s`.",
                        delay,
                        step.config.name,
                    )
                    time.sleep(delay)
                    delay *= backoff
                else:
                    if max_retries > 0:
                        logger.error(
                            "Failed to run step `%s` after %d retries.",
                            step.config.name,
                            max_retries,
                        )
                    raise
            else:
                break

    return step_run