in tfx/orchestration/kubeflow/v2/step_builder.py [0:0]
def build(self) -> Dict[str, pipeline_pb2.PipelineTaskSpec]:
"""Builds a pipeline PipelineTaskSpec given the node information.
Each TFX node maps one task spec and usually one component definition and
one executor spec. (with resolver node as an exception. See explaination
in the Returns section).
- Component definition includes interfaces of a node. For example, name
and type information of inputs/outputs/execution_properties.
- Task spec contains the topologies around the node. For example, the
dependency nodes, where to read the inputs and exec_properties (from another
task, from parent component or from a constant value). The task spec has the
name of the component definition it references. It is possible that a task
spec references an existing component definition that's built previously.
- Executor spec encodes how the node is actually executed. For example,
args to start a container, or query strings for resolvers. All executor spec
will be packed into deployment config proto.
During the build, all three parts mentioned above will be updated.
Returns:
A Dict mapping from node id to PipelineTaskSpec messages corresponding to
the node. For most of the cases, the dict contains a single element.
The only exception is when compiling latest blessed model resolver.
One DSL node will be split to two resolver specs to reflect the
two-phased query execution.
Raises:
NotImplementedError: When the node being built is an InfraValidator.
"""
# 1. Resolver tasks won't have input artifacts in the API proto. First we
# specialcase two resolver types we support.
if isinstance(self._node, resolver.Resolver):
return self._build_resolver_spec()
# 2. Build component spec.
component_def = pipeline_pb2.ComponentSpec()
task_spec = pipeline_pb2.PipelineTaskSpec()
executor_label = _EXECUTOR_LABEL_PATTERN.format(self._name)
component_def.executor_label = executor_label
# Conditionals
implicit_input_channels = {}
implicit_upstream_node_ids = set()
predicates = conditional.get_predicates(self._node)
if predicates:
implicit_keys_map = {
tfx_compiler_utils.implicit_channel_key(channel): key
for key, channel in self._inputs.items()
}
cel_predicates = []
for predicate in predicates:
for channel in predicate.dependent_channels():
implicit_key = tfx_compiler_utils.implicit_channel_key(channel)
if implicit_key not in implicit_keys_map:
# Store this channel and add it to the node inputs later.
implicit_input_channels[implicit_key] = channel
# Store the producer node and add it to the upstream nodes later.
implicit_upstream_node_ids.add(channel.producer_component_id)
placeholder_pb = predicate.encode_with_keys(
tfx_compiler_utils.build_channel_to_key_fn(implicit_keys_map))
cel_predicates.append(compiler_utils.placeholder_to_cel(placeholder_pb))
task_spec.trigger_policy.condition = ' && '.join(cel_predicates)
# Inputs
for name, input_channel in itertools.chain(self._inputs.items(),
implicit_input_channels.items()):
input_artifact_spec = compiler_utils.build_input_artifact_spec(
input_channel)
component_def.input_definitions.artifacts[name].CopyFrom(
input_artifact_spec)
# Outputs
for name, output_channel in self._outputs.items():
# Currently, we're working under the assumption that for tasks
# (those generated by BaseComponent), each channel contains a single
# artifact.
output_artifact_spec = compiler_utils.build_output_artifact_spec(
output_channel)
component_def.output_definitions.artifacts[name].CopyFrom(
output_artifact_spec)
# Exec properties
for name, value in self._exec_properties.items():
# value can be None for unprovided optional exec properties.
if value is None:
continue
parameter_type_spec = compiler_utils.build_parameter_type_spec(value)
component_def.input_definitions.parameters[name].CopyFrom(
parameter_type_spec)
if self._name not in self._component_defs:
self._component_defs[self._name] = component_def
else:
raise ValueError(f'Found duplicate component ids {self._name} while '
'building component definitions.')
# 3. Build task spec.
task_spec.task_info.name = self._name
dependency_ids = sorted({node.id for node in self._node.upstream_nodes}
| implicit_upstream_node_ids)
for name, input_channel in itertools.chain(self._inputs.items(),
implicit_input_channels.items()):
# TODO(b/169573945): Add support for vertex if requested.
if not isinstance(input_channel, Channel):
raise TypeError('Only single Channel is supported.')
if self._is_exit_handler:
logging.error('exit handler component doesn\'t take input artifact, '
'the input will be ignored.')
continue
# If the redirecting map is provided (usually for latest blessed model
# resolver, we'll need to redirect accordingly. Also, the upstream node
# list will be updated and replaced by the new producer id.
producer_id = input_channel.producer_component_id
output_key = input_channel.output_key
for k, v in self._channel_redirect_map.items():
if k[0] == producer_id and producer_id in dependency_ids:
dependency_ids.remove(producer_id)
dependency_ids.append(v[0])
producer_id = self._channel_redirect_map.get((producer_id, output_key),
(producer_id, output_key))[0]
output_key = self._channel_redirect_map.get((producer_id, output_key),
(producer_id, output_key))[1]
input_artifact_spec = pipeline_pb2.TaskInputsSpec.InputArtifactSpec()
input_artifact_spec.task_output_artifact.producer_task = producer_id
input_artifact_spec.task_output_artifact.output_artifact_key = output_key
task_spec.inputs.artifacts[name].CopyFrom(input_artifact_spec)
for name, value in self._exec_properties.items():
if value is None:
continue
if isinstance(value, data_types.RuntimeParameter):
parameter_utils.attach_parameter(value)
task_spec.inputs.parameters[name].component_input_parameter = value.name
elif isinstance(value, decorators.FinalStatusStr):
if not self._is_exit_handler:
logging.error('FinalStatusStr type is only allowed to use in exit'
' handler. The parameter is ignored.')
else:
task_spec.inputs.parameters[name].task_final_status.producer_task = (
compiler_utils.TFX_DAG_NAME)
else:
task_spec.inputs.parameters[name].CopyFrom(
pipeline_pb2.TaskInputsSpec.InputParameterSpec(
runtime_value=compiler_utils.value_converter(value)))
task_spec.component_ref.name = self._name
dependency_ids = sorted(dependency_ids)
for dependency in dependency_ids:
task_spec.dependent_tasks.append(dependency)
if self._enable_cache:
task_spec.caching_options.CopyFrom(
pipeline_pb2.PipelineTaskSpec.CachingOptions(
enable_cache=self._enable_cache))
if self._is_exit_handler:
task_spec.trigger_policy.strategy = (
pipeline_pb2.PipelineTaskSpec.TriggerPolicy
.ALL_UPSTREAM_TASKS_COMPLETED)
task_spec.dependent_tasks.append(compiler_utils.TFX_DAG_NAME)
# 4. Build the executor body for other common tasks.
executor = pipeline_pb2.PipelineDeploymentConfig.ExecutorSpec()
if isinstance(self._node, importer.Importer):
executor.importer.CopyFrom(self._build_importer_spec())
elif isinstance(self._node, components.FileBasedExampleGen):
executor.container.CopyFrom(self._build_file_based_example_gen_spec())
elif isinstance(self._node, (components.InfraValidator)):
raise NotImplementedError(
'The componet type "{}" is not supported'.format(type(self._node)))
else:
executor.container.CopyFrom(self._build_container_spec())
self._deployment_config.executors[executor_label].CopyFrom(executor)
return {self._name: task_spec}