async def _train_nlu_with_validated_data(
file_importer: TrainingDataImporter,
output: Text,
train_path: Optional[Text] = None,
fixed_model_name: Optional[Text] = None,
persist_nlu_training_data: bool = False,
additional_arguments: Optional[Dict] = None,
) -> Optional[Text]:
"""Train NLU with validated training and config data."""
import rasa.nlu.train
if additional_arguments is None:
additional_arguments = {}
with ExitStack() as stack:
if train_path:
# If the train path was provided, do nothing on exit.
_train_path = train_path
else:
# Otherwise, create a temp train path and clean it up on exit.
_train_path = stack.enter_context(
TempDirectoryPath(tempfile.mkdtemp()))
config = await file_importer.get_config()
print_color("Training NLU model...",
color=rasa.shared.utils.io.bcolors.OKBLUE)
async with telemetry.track_model_training(file_importer,
model_type="nlu"):
await rasa.nlu.train(
config,
file_importer,
_train_path,
fixed_model_name="nlu",
persist_nlu_training_data=persist_nlu_training_data,
**additional_arguments,
)
print_color("NLU model training completed.",
color=rasa.shared.utils.io.bcolors.OKBLUE)
if train_path is None:
# Only NLU was trained
new_fingerprint = await model.model_fingerprint(file_importer)
return model.package_model(
fingerprint=new_fingerprint,
output_directory=output,
train_path=_train_path,
fixed_model_name=fixed_model_name,
model_prefix="nlu-",
)
return _train_path
async def _train_core_with_validated_data(
file_importer: TrainingDataImporter,
output: Text,
train_path: Optional[Text] = None,
fixed_model_name: Optional[Text] = None,
additional_arguments: Optional[Dict] = None,
interpreter: Optional[Interpreter] = None,
) -> Optional[Text]:
"""Train Core with validated training and config data."""
import rasa.core.train
with ExitStack() as stack:
if train_path:
# If the train path was provided, do nothing on exit.
_train_path = train_path
else:
# Otherwise, create a temp train path and clean it up on exit.
_train_path = stack.enter_context(
TempDirectoryPath(tempfile.mkdtemp()))
# normal (not compare) training
print_color("Training Core model...",
color=rasa.shared.utils.io.bcolors.OKBLUE)
domain, config = await asyncio.gather(file_importer.get_domain(),
file_importer.get_config())
async with telemetry.track_model_training(file_importer,
model_type="core"):
await rasa.core.train(
domain_file=domain,
training_resource=file_importer,
output_path=os.path.join(_train_path,
DEFAULT_CORE_SUBDIRECTORY_NAME),
policy_config=config,
additional_arguments=additional_arguments,
interpreter=interpreter,
)
print_color("Core model training completed.",
color=rasa.shared.utils.io.bcolors.OKBLUE)
if train_path is None:
# Only Core was trained.
new_fingerprint = await model.model_fingerprint(file_importer)
return model.package_model(
fingerprint=new_fingerprint,
output_directory=output,
train_path=_train_path,
fixed_model_name=fixed_model_name,
model_prefix="core-",
)
return _train_path
async def _do_training(
file_importer: TrainingDataImporter,
output_path: Text,
train_path: Text,
fingerprint_comparison_result: Optional[
FingerprintComparisonResult] = None,
fixed_model_name: Optional[Text] = None,
persist_nlu_training_data: bool = False,
core_additional_arguments: Optional[Dict] = None,
nlu_additional_arguments: Optional[Dict] = None,
old_model_zip_path: Optional[Text] = None,
):
if not fingerprint_comparison_result:
fingerprint_comparison_result = FingerprintComparisonResult()
interpreter_path = None
if fingerprint_comparison_result.should_retrain_nlu():
model_path = await _train_nlu_with_validated_data(
file_importer,
output=output_path,
train_path=train_path,
fixed_model_name=fixed_model_name,
persist_nlu_training_data=persist_nlu_training_data,
additional_arguments=nlu_additional_arguments,
)
interpreter_path = os.path.join(model_path,
DEFAULT_NLU_SUBDIRECTORY_NAME)
else:
print_color(
"NLU data/configuration did not change. No need to retrain NLU model.",
color=rasa.shared.utils.io.bcolors.OKBLUE,
)
if fingerprint_comparison_result.should_retrain_core():
await _train_core_with_validated_data(
file_importer,
output=output_path,
train_path=train_path,
fixed_model_name=fixed_model_name,
additional_arguments=core_additional_arguments,
interpreter=_load_interpreter(interpreter_path)
or _interpreter_from_previous_model(old_model_zip_path),
)
elif fingerprint_comparison_result.should_retrain_nlg():
print_color(
"Core stories/configuration did not change. "
"Only the templates section has been changed. A new model with "
"the updated templates will be created.",
color=rasa.shared.utils.io.bcolors.OKBLUE,
)
await model.update_model_with_new_domain(file_importer, train_path)
else:
print_color(
"Core stories/configuration did not change. No need to retrain Core model.",
color=rasa.shared.utils.io.bcolors.OKBLUE,
)
async def _train_nlu_with_validated_data(
file_importer: TrainingDataImporter,
output: Text,
train_path: Optional[Text] = None,
fixed_model_name: Optional[Text] = None,
persist_nlu_training_data: bool = False,
retrain_nlu: Union[bool, List[Text]] = True,
additional_arguments: Optional[Dict] = None,
) -> Optional[Text]:
"""Train NLU with validated training and config data."""
import rasa.nlu.train
if additional_arguments is None:
additional_arguments = {}
with ExitStack() as stack:
if train_path:
# If the train path was provided, do nothing on exit.
_train_path = train_path
else:
# Otherwise, create a temp train path and clean it up on exit.
_train_path = stack.enter_context(TempDirectoryPath(tempfile.mkdtemp()))
# bf mod
config = await file_importer.get_nlu_config(retrain_nlu)
async with telemetry.track_model_training(file_importer, model_type="nlu"):
for lang in config:
if config[lang]:
print_color(
"Start training <{}> NLU model ...".format(lang),
color=rasa.shared.utils.io.bcolors.OKBLUE,
)
await rasa.nlu.train(
config[lang],
file_importer,
_train_path,
fixed_model_name="nlu-{}".format(lang),
persist_nlu_training_data=persist_nlu_training_data,
**additional_arguments,
)
else:
print_color(
"NLU data for language <{}> didn't change, skipping training...".format(
lang
),
color=rasa.shared.utils.io.bcolors.OKBLUE,
)
# /bf mod
print_color(
"NLU model training completed.", color=rasa.shared.utils.io.bcolors.OKBLUE
)
if train_path is None:
# Only NLU was trained
new_fingerprint = await model.model_fingerprint(file_importer)
return model.package_model(
fingerprint=new_fingerprint,
output_directory=output,
train_path=_train_path,
fixed_model_name=fixed_model_name,
model_prefix="nlu-",
)
return _train_path
async def _train_async_internal(
file_importer: TrainingDataImporter,
train_path: Text,
output_path: Text,
force_training: bool,
fixed_model_name: Optional[Text],
persist_nlu_training_data: bool,
core_additional_arguments: Optional[Dict] = None,
nlu_additional_arguments: Optional[Dict] = None,
) -> Optional[Text]:
"""Trains a Rasa model (Core and NLU). Use only from `train_async`.
Args:
file_importer: `TrainingDataImporter` which supplies the training data.
train_path: Directory in which to train the model.
output_path: Output path.
force_training: If `True` retrain model even if data has not changed.
fixed_model_name: Name of model to be stored.
persist_nlu_training_data: `True` if the NLU training data should be persisted
with the model.
core_additional_arguments: Additional training parameters for core training.
nlu_additional_arguments: Additional training parameters forwarded to training
method of each NLU component.
Returns:
Path of the trained model archive.
"""
stories, nlu_data = await asyncio.gather(
file_importer.get_stories(), file_importer.get_nlu_data()
)
# if stories.is_empty() and nlu_data.can_train_nlu_model():
# print_error(
# "No training data given. Please provide stories and NLU data in "
# "order to train a Rasa model using the '--data' argument."
# )
# return
# if stories.is_empty():
# print_warning("No stories present. Just a Rasa NLU model will be trained.")
# return await _train_nlu_with_validated_data(
# file_importer,
# output=output_path,
# fixed_model_name=fixed_model_name,
# persist_nlu_training_data=persist_nlu_training_data,
# additional_arguments=nlu_additional_arguments,
# )
# if nlu_data.can_train_nlu_model():
# print_warning("No NLU data present. Just a Rasa Core model will be trained.")
# return await _train_core_with_validated_data(
# file_importer,
# output=output_path,
# fixed_model_name=fixed_model_name,
# additional_arguments=core_additional_arguments,
# )
new_fingerprint = await model.model_fingerprint(file_importer)
old_model = model.get_latest_model(output_path)
if not force_training:
fingerprint_comparison = model.should_retrain(
new_fingerprint, old_model, train_path
)
else:
fingerprint_comparison = FingerprintComparisonResult(force_training=True)
# bf mod >
if fingerprint_comparison.nlu == True: # replace True with list of all langs
fingerprint_comparison.nlu = list(new_fingerprint.get("nlu-config", {}).keys())
domain = await file_importer.get_domain()
core_untrainable = domain.is_empty() or stories.is_empty()
nlu_untrainable = [l for l, d in nlu_data.items() if d.is_empty()]
fingerprint_comparison.core = fingerprint_comparison.core and not core_untrainable
fingerprint_comparison.nlu = [
l for l in fingerprint_comparison.nlu if l not in nlu_untrainable
]
if core_untrainable:
print_color(
"Skipping Core training since domain or stories are empty.",
color=rasa.shared.utils.io.bcolors.OKBLUE,
)
for lang in nlu_untrainable:
print_color(
"No NLU data found for language <{}>, skipping training...".format(lang),
color=rasa.shared.utils.io.bcolors.OKBLUE,
)
# </ bf mod
if fingerprint_comparison.is_training_required():
async with telemetry.track_model_training(file_importer, model_type="rasa"):
await _do_training(
file_importer,
output_path=output_path,
train_path=train_path,
fingerprint_comparison_result=fingerprint_comparison,
fixed_model_name=fixed_model_name,
persist_nlu_training_data=persist_nlu_training_data,
core_additional_arguments=core_additional_arguments,
nlu_additional_arguments=nlu_additional_arguments,
old_model_zip_path=old_model,
)
return model.package_model(
fingerprint=new_fingerprint,
output_directory=output_path,
train_path=train_path,
fixed_model_name=fixed_model_name,
)
print_success(
"Nothing changed. You can use the old model stored at '{}'."
"".format(os.path.abspath(old_model))
)
return old_model