def test_decorator_metadata(self):
"""Test @pipeline decorator with metadata."""
@pipeline(name='p1', description='description1')
def my_pipeline1(a: {'Schema':
{
'file_type': 'csv'
}} = 'good',
b: Integer() = 12):
pass
golden_meta = ComponentSpec(name='p1',
description='description1',
inputs=[])
golden_meta.inputs.append(
InputSpec(name='a',
type={'Schema': {
'file_type': 'csv'
}},
default='good',
optional=True))
golden_meta.inputs.append(
InputSpec(name='b',
type={
'Integer': {
'openapi_schema_validator': {
"type": "integer"
}
}
},
default="12",
optional=True))
pipeline_meta = _extract_pipeline_metadata(my_pipeline1)
self.assertEqual(pipeline_meta, golden_meta)
def test_decorator_metadata(self):
"""Test @pipeline decorator with metadata."""
@pipeline(name='p1', description='description1')
def my_pipeline1(a: {'Schema':
{
'file_type': 'csv'
}} = 'good',
b: Integer() = 12):
pass
golden_meta = PipelineMeta(name='p1', description='description1')
golden_meta.inputs.append(
ParameterMeta(name='a',
description='',
param_type={'Schema': {
'file_type': 'csv'
}},
default='good'))
golden_meta.inputs.append(
ParameterMeta(name='b',
description='',
param_type={
'Integer': {
'openapi_schema_validator': {
"type": "integer"
}
}
},
default=12))
pipeline_meta = _extract_pipeline_metadata(my_pipeline1)
self.assertEqual(pipeline_meta, golden_meta)
def _create_workflow(self,
pipeline_func: Callable,
pipeline_name: Text=None,
pipeline_description: Text=None,
params_list: List[dsl.PipelineParam]=None,
pipeline_conf: dsl.PipelineConf = None,
) -> List[Dict[Text, Any]]: # Tekton change, signature
""" Internal implementation of create_workflow."""
params_list = params_list or []
argspec = inspect.getfullargspec(pipeline_func)
# Create the arg list with no default values and call pipeline function.
# Assign type information to the PipelineParam
pipeline_meta = _extract_pipeline_metadata(pipeline_func)
pipeline_meta.name = pipeline_name or pipeline_meta.name
pipeline_meta.description = pipeline_description or pipeline_meta.description
pipeline_name = sanitize_k8s_name(pipeline_meta.name)
# Need to first clear the default value of dsl.PipelineParams. Otherwise, it
# will be resolved immediately in place when being to each component.
default_param_values = {}
for param in params_list:
default_param_values[param.name] = param.value
param.value = None
# Currently only allow specifying pipeline params at one place.
if params_list and pipeline_meta.inputs:
raise ValueError('Either specify pipeline params in the pipeline function, or in "params_list", but not both.')
args_list = []
for arg_name in argspec.args:
arg_type = None
for input in pipeline_meta.inputs or []:
if arg_name == input.name:
arg_type = input.type
break
args_list.append(dsl.PipelineParam(sanitize_k8s_name(arg_name, True), param_type=arg_type))
with dsl.Pipeline(pipeline_name) as dsl_pipeline:
pipeline_func(*args_list)
pipeline_conf = pipeline_conf or dsl_pipeline.conf # Configuration passed to the compiler is overriding. Unfortunately, it's not trivial to detect whether the dsl_pipeline.conf was ever modified.
self._validate_exit_handler(dsl_pipeline)
self._sanitize_and_inject_artifact(dsl_pipeline, pipeline_conf)
# Fill in the default values.
args_list_with_defaults = []
if pipeline_meta.inputs:
args_list_with_defaults = [dsl.PipelineParam(sanitize_k8s_name(arg_name, True))
for arg_name in argspec.args]
if argspec.defaults:
for arg, default in zip(reversed(args_list_with_defaults), reversed(argspec.defaults)):
arg.value = default.value if isinstance(default, dsl.PipelineParam) else default
elif params_list:
# Or, if args are provided by params_list, fill in pipeline_meta.
for param in params_list:
param.value = default_param_values[param.name]
args_list_with_defaults = params_list
pipeline_meta.inputs = [
InputSpec(
name=param.name,
type=param.param_type,
default=param.value) for param in params_list]
op_transformers = [add_pod_env]
op_transformers.extend(pipeline_conf.op_transformers)
workflow = self._create_pipeline_workflow(
args_list_with_defaults,
dsl_pipeline,
op_transformers,
pipeline_conf,
)
from ._data_passing_rewriter import fix_big_data_passing
workflow = fix_big_data_passing(workflow)
import json
pipeline = [item for item in workflow if item["kind"] == "Pipeline"][0] # Tekton change
pipeline.setdefault('metadata', {}).setdefault('annotations', {})['pipelines.kubeflow.org/pipeline_spec'] = json.dumps(pipeline_meta.to_dict(), sort_keys=True)
return workflow
def _create_workflow(
self,
pipeline_func: Callable,
pipeline_name: Text = None,
pipeline_description: Text = None,
params_list: List[dsl.PipelineParam] = None,
pipeline_conf: dsl.PipelineConf = None,
) -> Dict[Text, Any]:
""" Internal implementation of create_workflow."""
params_list = params_list or []
argspec = inspect.getfullargspec(pipeline_func)
# Create the arg list with no default values and call pipeline function.
# Assign type information to the PipelineParam
pipeline_meta = _extract_pipeline_metadata(pipeline_func)
pipeline_meta.name = pipeline_name or pipeline_meta.name
pipeline_meta.description = pipeline_description or pipeline_meta.description
pipeline_name = sanitize_k8s_name(pipeline_meta.name)
# Need to first clear the default value of dsl.PipelineParams. Otherwise, it
# will be resolved immediately in place when being to each component.
default_param_values = {}
for param in params_list:
default_param_values[param.name] = param.value
param.value = None
# Currently only allow specifying pipeline params at one place.
if params_list and pipeline_meta.inputs:
raise ValueError(
'Either specify pipeline params in the pipeline function, or in "params_list", but not both.'
)
args_list = []
for arg_name in argspec.args:
arg_type = None
for input in pipeline_meta.inputs or []:
if arg_name == input.name:
arg_type = input.type
break
args_list.append(
dsl.PipelineParam(sanitize_k8s_name(arg_name, True),
param_type=arg_type))
with dsl.Pipeline(pipeline_name) as dsl_pipeline:
pipeline_func(*args_list)
# Configuration passed to the compiler is overriding. Unfortunately, it is
# not trivial to detect whether the dsl_pipeline.conf was ever modified.
pipeline_conf = pipeline_conf or dsl_pipeline.conf
self._validate_exit_handler(dsl_pipeline)
self._sanitize_and_inject_artifact(dsl_pipeline, pipeline_conf)
# Fill in the default values.
args_list_with_defaults = []
if pipeline_meta.inputs:
args_list_with_defaults = [
dsl.PipelineParam(sanitize_k8s_name(arg_name, True))
for arg_name in argspec.args
]
if argspec.defaults:
for arg, default in zip(reversed(args_list_with_defaults),
reversed(argspec.defaults)):
arg.value = default.value if isinstance(
default, dsl.PipelineParam) else default
elif params_list:
# Or, if args are provided by params_list, fill in pipeline_meta.
for param in params_list:
param.value = default_param_values[param.name]
args_list_with_defaults = params_list
pipeline_meta.inputs = [
InputSpec(name=param.name,
type=param.param_type,
default=param.value) for param in params_list
]
op_transformers = [add_pod_env]
# # By default adds telemetry instruments. Users can opt out toggling
# # allow_telemetry.
# # Also, TFX pipelines will be bypassed for pipeline compiled by tfx>0.21.4.
# if allow_telemetry:
# pod_labels = get_default_telemetry_labels()
# op_transformers.append(add_pod_labels(pod_labels))
op_transformers.extend(pipeline_conf.op_transformers)
workflow = self._create_pipeline_workflow(
args_list_with_defaults,
dsl_pipeline,
op_transformers,
pipeline_conf,
)
workflow = fix_big_data_passing(workflow)
workflow.setdefault('metadata', {}).setdefault('annotations', {})['pipelines.kubeflow.org/pipeline_spec'] = \
json.dumps(pipeline_meta.to_dict(), sort_keys=True)
# recursively strip empty structures, DANGER: this may remove necessary empty elements ?!
def remove_empty_elements(obj) -> dict:
if not isinstance(obj, (dict, list)):
return obj
if isinstance(obj, list):
return [remove_empty_elements(o) for o in obj if o != []]
return {
k: remove_empty_elements(v)
for k, v in obj.items() if v != []
}
workflow = remove_empty_elements(workflow)
return workflow
def _create_workflow(
self,
pipeline_func: Callable,
pipeline_name: Optional[Text] = None,
pipeline_description: Optional[Text] = None,
params_list: Optional[List[dsl.PipelineParam]] = None,
pipeline_conf: Optional[dsl.PipelineConf] = None,
) -> Dict[Text, Any]:
""" Internal implementation of create_workflow."""
params_list = params_list or []
# Create the arg list with no default values and call pipeline function.
# Assign type information to the PipelineParam
pipeline_meta = _extract_pipeline_metadata(pipeline_func)
pipeline_meta.name = pipeline_name or pipeline_meta.name
pipeline_meta.description = pipeline_description or pipeline_meta.description
pipeline_name = sanitize_k8s_name(pipeline_meta.name)
# Need to first clear the default value of dsl.PipelineParams. Otherwise, it
# will be resolved immediately in place when being to each component.
default_param_values = OrderedDict()
if self._pipeline_root_param:
params_list.append(self._pipeline_root_param)
if self._pipeline_name_param:
params_list.append(self._pipeline_name_param)
for param in params_list:
default_param_values[param.name] = param.value
param.value = None
args_list = []
kwargs_dict = dict()
signature = inspect.signature(pipeline_func)
for arg_name, arg in signature.parameters.items():
arg_type = None
for input in pipeline_meta.inputs or []:
if arg_name == input.name:
arg_type = input.type
break
param = dsl.PipelineParam(sanitize_k8s_name(arg_name, True), param_type=arg_type)
if arg.kind == inspect.Parameter.KEYWORD_ONLY:
kwargs_dict[arg_name] = param
else:
args_list.append(param)
with dsl.Pipeline(pipeline_name) as dsl_pipeline:
pipeline_func(*args_list, **kwargs_dict)
pipeline_conf = pipeline_conf or dsl_pipeline.conf # Configuration passed to the compiler is overriding. Unfortunately, it's not trivial to detect whether the dsl_pipeline.conf was ever modified.
self._validate_exit_handler(dsl_pipeline)
self._sanitize_and_inject_artifact(dsl_pipeline, pipeline_conf)
# Fill in the default values by merging two param lists.
args_list_with_defaults = OrderedDict()
if pipeline_meta.inputs:
args_list_with_defaults = OrderedDict([
(sanitize_k8s_name(input_spec.name, True), input_spec.default)
for input_spec in pipeline_meta.inputs
])
if params_list:
# Or, if args are provided by params_list, fill in pipeline_meta.
for k, v in default_param_values.items():
args_list_with_defaults[k] = v
pipeline_meta.inputs = pipeline_meta.inputs or []
for param in params_list:
pipeline_meta.inputs.append(
InputSpec(
name=param.name,
type=param.param_type,
default=default_param_values[param.name]))
op_transformers = [add_pod_env]
pod_labels = {_SDK_VERSION_LABEL: kfp.__version__, _SDK_ENV_LABEL:_SDK_ENV_DEFAULT}
op_transformers.append(add_pod_labels(pod_labels))
op_transformers.extend(pipeline_conf.op_transformers)
if self._mode == dsl.PipelineExecutionMode.V2_COMPATIBLE:
# Add self._pipeline_name_param and self._pipeline_root_param to ops inputs
# if they don't exist already.
for op in dsl_pipeline.ops.values():
insert_pipeline_name_param = True
insert_pipeline_root_param = True
for param in op.inputs:
if param.name == self._pipeline_name_param.name:
insert_pipeline_name_param = False
elif param.name == self._pipeline_root_param.name:
insert_pipeline_root_param = False
if insert_pipeline_name_param:
op.inputs.append(self._pipeline_name_param)
if insert_pipeline_root_param:
op.inputs.append(self._pipeline_root_param)
workflow = self._create_pipeline_workflow(
args_list_with_defaults,
dsl_pipeline,
op_transformers,
pipeline_conf,
)
from ._data_passing_rewriter import fix_big_data_passing
workflow = fix_big_data_passing(workflow)
workflow = _data_passing_rewriter.add_pod_name_passing(
workflow, str(self._pipeline_root_param or None))
if pipeline_conf and pipeline_conf.data_passing_method != None:
workflow = pipeline_conf.data_passing_method(workflow)
metadata = workflow.setdefault('metadata', {})
annotations = metadata.setdefault('annotations', {})
labels = metadata.setdefault('labels', {})
annotations[_SDK_VERSION_LABEL] = kfp.__version__
annotations['pipelines.kubeflow.org/pipeline_compilation_time'] = datetime.datetime.now().isoformat()
annotations['pipelines.kubeflow.org/pipeline_spec'] = json.dumps(pipeline_meta.to_dict(), sort_keys=True)
if self._mode == dsl.PipelineExecutionMode.V2_COMPATIBLE:
annotations['pipelines.kubeflow.org/v2_pipeline'] = "true"
labels['pipelines.kubeflow.org/v2_pipeline'] = "true"
# Labels might be logged better than annotations so adding some information here as well
labels[_SDK_VERSION_LABEL] = kfp.__version__
return workflow