def package_model(
fingerprint: Fingerprint,
output_directory: Text,
train_path: Text,
fixed_model_name: Optional[Text] = None,
model_prefix: Text = "",
) -> Text:
"""
Compress a trained model.
Args:
fingerprint: fingerprint of the model
output_directory: path to the directory in which the model should be stored
train_path: path to uncompressed model
fixed_model_name: name of the compressed model file
model_prefix: prefix of the compressed model file
Returns: path to 'tar.gz' model file
"""
output_directory = create_output_path(
output_directory, prefix=model_prefix, fixed_name=fixed_model_name
)
create_package_rasa(train_path, output_directory, fingerprint)
print_success(
"Your Rasa model is trained and saved at '{}'.".format(
os.path.abspath(output_directory)
)
)
return output_directory
def train_nlu(config: Text, nlu_data: Text, output: Text,
train_path: Optional[Text]) -> Optional["Interpreter"]:
"""Trains a NLU model.
Args:
config: Path to the config file for NLU.
nlu_data: Path to the NLU training data.
output: Output path.
train_path: If `None` the model will be trained in a temporary
directory, otherwise in the provided directory.
Returns:
If `train_path` is given it returns the path to the model archive,
otherwise the path to the directory with the trained model files.
"""
import rasa_nlu
_train_path = train_path or tempfile.mkdtemp()
_, nlu_model, _ = rasa_nlu.train(config, nlu_data, _train_path,
project="",
fixed_model_name="nlu")
if not train_path:
nlu_data = data.get_nlu_directory(nlu_data)
output_path = create_output_path(output, prefix="nlu-")
new_fingerprint = model.model_fingerprint(config, nlu_data=nlu_data)
model.create_package_rasa(_train_path, output_path, new_fingerprint)
print_success("Your Rasa NLU model is trained and saved at '{}'."
"".format(output_path))
return nlu_model
def print_train_or_instructions(args: argparse.Namespace, path: Text) -> None:
import questionary
print_success("Finished creating project structure.")
should_train = questionary.confirm(
"Do you want to train an initial model? 💪🏽").skip_if(args.no_prompt,
default=True)
if should_train:
print_success("Training an initial model...")
config = os.path.join(path, DEFAULT_CONFIG_PATH)
training_files = os.path.join(path, DEFAULT_DATA_PATH)
domain = os.path.join(path, DEFAULT_DOMAIN_PATH)
output = os.path.join(path, create_output_path())
args.model = rasa.train(domain, config, training_files, output)
print_run_or_instructions(args, path)
else:
print_success(
"No problem 👍🏼. You can also train a model later by going "
"to the project directory and running 'rasa train'."
"".format(path))
def create_model_path(model_name, path_to_model):
parent_dir = os.path.abspath(os.path.join(path_to_model, os.pardir))
if model_name is not None:
if not model_name.endswith(".tar.gz"):
model_name += ".tar.gz"
output_path = os.path.join(parent_dir, model_name)
else:
output_path = create_output_path(parent_dir, prefix="nlu-")
return output_path
def train_project(path: Text) -> Optional[Text]:
print_success("Training an initial model...")
config = os.path.join(path, DEFAULT_CONFIG_PATH)
training_files = os.path.join(path, DEFAULT_DATA_PATH)
domain = os.path.join(path, DEFAULT_DOMAIN_PATH)
output = os.path.join(path, create_output_path())
model = rasa.train(domain, config, training_files, output)
return model
def train_nlu(config: Text, nlu_data: Text, output: Text,
train_path: Optional[Text]) -> Optional[Text]:
"""Trains a NLU model.
Args:
config: Path to the config file for NLU.
nlu_data: Path to the NLU training data.
output: Output path.
train_path: If `None` the model will be trained in a temporary
directory, otherwise in the provided directory.
Returns:
If `train_path` is given it returns the path to the model archive,
otherwise the path to the directory with the trained model files.
"""
import rasa.nlu.train
config = get_valid_config(config, CONFIG_MANDATORY_KEYS_NLU)
if not train_path:
# training NLU only hence the training files still have to be selected
skill_imports = SkillSelector.load(config)
nlu_data_directory = data.get_nlu_directory(nlu_data, skill_imports)
else:
nlu_data_directory = nlu_data
if not os.listdir(nlu_data_directory):
print_error(
"No NLU data given. Please provide NLU data in order to train "
"a Rasa NLU model.")
return
_train_path = train_path or tempfile.mkdtemp()
print_color("Start training NLU model ...", color=bcolors.OKBLUE)
_, nlu_model, _ = rasa.nlu.train(config,
nlu_data_directory,
_train_path,
fixed_model_name="nlu")
print_color("Done.", color=bcolors.OKBLUE)
if not train_path:
output_path = create_output_path(output, prefix="nlu-")
new_fingerprint = model.model_fingerprint(config,
nlu_data=nlu_data_directory)
model.create_package_rasa(_train_path, output_path, new_fingerprint)
print_success(
"Your Rasa NLU model is trained and saved at '{}'.".format(
output_path))
return output_path
return _train_path
async def _train_core_with_validated_data(
domain: Domain,
config: Text,
story_directory: Text,
output: Text,
train_path: Optional[Text] = None,
fixed_model_name: Optional[Text] = None,
uncompress: bool = False,
kwargs: Optional[Dict] = None,
) -> Optional[Text]:
"""Train Core with validated training and config data."""
import rasa.core.train
if not os.listdir(story_directory):
print_error(
"No dialogue data given. Please provide dialogue data in order to "
"train a Rasa Core model.")
return
_train_path = train_path or tempfile.mkdtemp()
# normal (not compare) training
print_color("Start training dialogue model ...", color=bcolors.OKBLUE)
await rasa.core.train(
domain_file=domain,
stories_file=story_directory,
output_path=os.path.join(_train_path, "core"),
policy_config=config,
kwargs=kwargs,
)
print_color("Done.", color=bcolors.OKBLUE)
if not train_path:
# Only Core was trained.
output_path = create_output_path(output,
prefix="core-",
fixed_name=fixed_model_name)
new_fingerprint = model.model_fingerprint(config,
domain,
stories=story_directory)
model.create_package_rasa(_train_path, output_path, new_fingerprint)
if uncompress:
output_path = decompress(output_path)
print_success(
"Your Rasa Core model is trained and saved at '{}'.".format(
output_path))
return output_path
return _train_path
async def train_core_async(
domain: Text,
config: Text,
stories: Text,
output: Text,
train_path: Optional[Text] = None,
kwargs: Optional[Dict] = None,
) -> Optional[Text]:
"""Trains a Core model.
Args:
domain: Path to the domain file.
config: Path to the config file for Core.
stories: Path to the Core training data.
output: Output path.
train_path: If `None` the model will be trained in a temporary
directory, otherwise in the provided directory.
kwargs: Additional training parameters.
Returns:
If `train_path` is given it returns the path to the model archive,
otherwise the path to the directory with the trained model files.
"""
import rasa.core.train
config = get_valid_config(config, CONFIG_MANDATORY_KEYS_CORE)
_train_path = train_path or tempfile.mkdtemp()
# normal (not compare) training
core_model = await rasa.core.train(
domain_file=domain,
stories_file=data.get_core_directory(stories),
output_path=os.path.join(_train_path, "core"),
policy_config=config,
kwargs=kwargs,
)
if not train_path:
# Only Core was trained.
stories = data.get_core_directory(stories)
output_path = create_output_path(output, prefix="core-")
new_fingerprint = model.model_fingerprint(config,
domain,
stories=stories)
model.create_package_rasa(_train_path, output_path, new_fingerprint)
print_success(
"Your Rasa Core model is trained and saved at '{}'.".format(
output_path))
return core_model
def _package_model(
new_fingerprint: Fingerprint,
output_path: Text,
train_path: Text,
fixed_model_name: Optional[Text] = None,
model_prefix: Text = "",
):
output_path = create_output_path(output_path,
prefix=model_prefix,
fixed_name=fixed_model_name)
model.create_package_rasa(train_path, output_path, new_fingerprint)
print_success("Your Rasa model is trained and saved at '{}'.".format(
os.path.abspath(output_path)))
return output_path
def _train_nlu_with_validated_data(
config: Text,
nlu_data_directory: Text,
output: Text,
train_path: Optional[Text] = None,
fixed_model_name: Optional[Text] = None,
uncompress: bool = False,
) -> Optional[Text]:
"""Train NLU with validated training and config data."""
import rasa.nlu.train
if not os.listdir(nlu_data_directory):
print_error(
"No NLU data given. Please provide NLU data in order to train "
"a Rasa NLU model.")
return
_train_path = train_path or tempfile.mkdtemp()
print_color("Start training NLU model ...", color=bcolors.OKBLUE)
_, nlu_model, _ = rasa.nlu.train(config,
nlu_data_directory,
_train_path,
fixed_model_name="nlu")
print_color("Done.", color=bcolors.OKBLUE)
if not train_path:
# Only NLU was trained
output_path = create_output_path(output,
prefix="nlu-",
fixed_name=fixed_model_name)
new_fingerprint = model.model_fingerprint(config,
nlu_data=nlu_data_directory)
model.create_package_rasa(_train_path, output_path, new_fingerprint)
if uncompress:
output_path = decompress(output_path)
print_success(
"Your Rasa NLU model is trained and saved at '{}'.".format(
output_path))
return output_path
return _train_path
def print_train_or_instructions(args: argparse.Namespace, path: Text) -> None:
print_success("Your bot is ready to go!")
should_train = questionary.confirm("Do you want me to train an initial "
"model for the bot? 💪🏽").ask()
if should_train:
config = os.path.join(path, DEFAULT_CONFIG_PATH)
training_files = os.path.join(path, DEFAULT_DATA_PATH)
domain = os.path.join(path, DEFAULT_DOMAIN_PATH)
output = os.path.join(path, create_output_path())
args.model = rasa.train(domain, config, training_files, output)
print_run_or_instructions(args, path)
else:
print_success("No problem 👍🏼. You can also train me later by going "
"to the project directory and running 'rasa train'."
"".format(path))
async def train_core_async(domain: Text, config: Text, stories: Text,
output: Text,
train_path: Optional[Text]) -> Optional[Text]:
"""Trains a Core model.
Args:
domain: Path to the domain file.
config: Path to the config file for Core.
stories: Path to the Core training data.
output: Output path.
train_path: If `None` the model will be trained in a temporary
directory, otherwise in the provided directory.
Returns:
If `train_path` is given it returns the path to the model archive,
otherwise the path to the directory with the trained model files.
"""
import rasa_core.train
# normal (not compare) training
core_model = await rasa_core.train(domain_file=domain,
stories_file=stories,
output_path=os.path.join(
train_path, "core"),
policy_config=config)
if not train_path:
# Only Core was trained.
stories = data.get_core_directory(stories)
output_path = create_output_path(output, prefix="core-")
new_fingerprint = model.model_fingerprint(config,
domain,
stories=stories)
model.create_package_rasa(train_path, output_path, new_fingerprint)
print_success("Your Rasa Core model is trained and saved at '{}'."
"".format(output_path))
return core_model
async def train_async(domain: Text,
config: Text,
training_files: Union[Text, List[Text]],
output: Text = DEFAULT_MODELS_PATH,
force_training: bool = False) -> Optional[Text]:
"""Trains a Rasa model (Core and NLU).
Args:
domain: Path to the domain file.
config: Path to the config for Core and NLU.
training_files: Paths to the training data for Core and NLU.
output: Output path.
force_training: If `True` retrain model even if data has not changed.
Returns:
Path of the trained model archive.
"""
train_path = tempfile.mkdtemp()
old_model = model.get_latest_model(output)
retrain_core = True
retrain_nlu = True
story_directory, nlu_data_directory = data.get_core_nlu_directories(
training_files)
new_fingerprint = model.model_fingerprint(config, domain,
nlu_data_directory,
story_directory)
if not force_training and old_model:
unpacked = model.unpack_model(old_model)
old_core, old_nlu = model.get_model_subdirectories(unpacked)
last_fingerprint = model.fingerprint_from_path(unpacked)
if not model.core_fingerprint_changed(last_fingerprint,
new_fingerprint):
target_path = os.path.join(train_path, "core")
retrain_core = not model.merge_model(old_core, target_path)
if not model.nlu_fingerprint_changed(last_fingerprint, new_fingerprint):
target_path = os.path.join(train_path, "nlu")
retrain_nlu = not model.merge_model(old_nlu, target_path)
if force_training or retrain_core:
await train_core_async(domain, config, story_directory,
output, train_path)
else:
print("Dialogue data / configuration did not change. "
"No need to retrain dialogue model.")
if force_training or retrain_nlu:
train_nlu(config, nlu_data_directory, output, train_path)
else:
print("NLU data / configuration did not change. "
"No need to retrain NLU model.")
if retrain_core or retrain_nlu:
output = create_output_path(output)
model.create_package_rasa(train_path, output, new_fingerprint)
print("Train path: '{}'.".format(train_path))
print_success("Your bot is trained and ready to take for a spin!")
return output
else:
print("Nothing changed. You can use the old model stored at {}"
"".format(os.path.abspath(old_model)))
return old_model
async def train_async(
domain: Text,
config: Text,
training_files: Union[Text, List[Text]],
output: Text = DEFAULT_MODELS_PATH,
force_training: bool = False,
kwargs: Optional[Dict] = None,
) -> Optional[Text]:
"""Trains a Rasa model (Core and NLU).
Args:
domain: Path to the domain file.
config: Path to the config for Core and NLU.
training_files: Paths to the training data for Core and NLU.
output: Output path.
force_training: If `True` retrain model even if data has not changed.
kwargs: Additional training parameters.
Returns:
Path of the trained model archive.
"""
config = get_valid_config(config, CONFIG_MANDATORY_KEYS)
train_path = tempfile.mkdtemp()
old_model = model.get_latest_model(output)
retrain_core = True
retrain_nlu = True
story_directory, nlu_data_directory = data.get_core_nlu_directories(training_files)
new_fingerprint = model.model_fingerprint(
config, domain, nlu_data_directory, story_directory
)
dialogue_data_not_present = not os.listdir(story_directory)
nlu_data_not_present = not os.listdir(nlu_data_directory)
if dialogue_data_not_present and nlu_data_not_present:
print_error(
"No training data given. Please provide dialogue and NLU data in "
"order to train a Rasa model."
)
return
if dialogue_data_not_present:
print_warning(
"No dialogue data present. Just a Rasa NLU model will be trained."
)
return train_nlu(config, nlu_data_directory, output, None)
if nlu_data_not_present:
print_warning("No NLU data present. Just a Rasa Core model will be trained.")
return await train_core_async(
domain, config, story_directory, output, None, kwargs
)
if not force_training and old_model:
unpacked = model.unpack_model(old_model)
old_core, old_nlu = model.get_model_subdirectories(unpacked)
last_fingerprint = model.fingerprint_from_path(unpacked)
if not model.core_fingerprint_changed(last_fingerprint, new_fingerprint):
target_path = os.path.join(train_path, "core")
retrain_core = not model.merge_model(old_core, target_path)
if not model.nlu_fingerprint_changed(last_fingerprint, new_fingerprint):
target_path = os.path.join(train_path, "nlu")
retrain_nlu = not model.merge_model(old_nlu, target_path)
if force_training or retrain_core:
await train_core_async(
domain, config, story_directory, output, train_path, kwargs
)
else:
print (
"Dialogue data / configuration did not change. "
"No need to retrain dialogue model."
)
if force_training or retrain_nlu:
train_nlu(config, nlu_data_directory, output, train_path)
else:
print ("NLU data / configuration did not change. No need to retrain NLU model.")
if retrain_core or retrain_nlu:
output = create_output_path(output)
model.create_package_rasa(train_path, output, new_fingerprint)
print_success("Your bot is trained and ready to take for a spin!")
return output
else:
print_success(
"Nothing changed. You can use the old model stored at '{}'"
"".format(os.path.abspath(old_model))
)
return old_model
async def train_async(
domain: Optional,
config: Text,
training_files: Optional[Union[Text, List[Text]]],
output_path: Text = DEFAULT_MODELS_PATH,
force_training: bool = False,
fixed_model_name: Optional[Text] = None,
uncompress: bool = False,
kwargs: Optional[Dict] = None,
) -> Optional[Text]:
"""Trains a Rasa model (Core and NLU).
Args:
domain: Path to the domain file.
config: Path to the config for Core and NLU.
training_files: Paths to the training data for Core and NLU.
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.
uncompress: If `True` the model will not be compressed.
kwargs: Additional training parameters.
Returns:
Path of the trained model archive.
"""
config = get_valid_config(config, CONFIG_MANDATORY_KEYS)
train_path = tempfile.mkdtemp()
old_model = model.get_latest_model(output_path)
retrain_core = True
retrain_nlu = True
skill_imports = SkillSelector.load(config)
try:
domain = Domain.load(domain, skill_imports)
except InvalidDomain as e:
print_error(e)
return None
story_directory, nlu_data_directory = data.get_core_nlu_directories(
training_files, skill_imports)
new_fingerprint = model.model_fingerprint(config, domain,
nlu_data_directory,
story_directory)
dialogue_data_not_present = not os.listdir(story_directory)
nlu_data_not_present = not os.listdir(nlu_data_directory)
if dialogue_data_not_present and nlu_data_not_present:
print_error(
"No training data given. Please provide dialogue and NLU data in "
"order to train a Rasa model.")
return
if dialogue_data_not_present:
print_warning(
"No dialogue data present. Just a Rasa NLU model will be trained.")
return _train_nlu_with_validated_data(
config=config,
nlu_data_directory=nlu_data_directory,
output=output_path,
fixed_model_name=fixed_model_name,
uncompress=uncompress,
)
if nlu_data_not_present:
print_warning(
"No NLU data present. Just a Rasa Core model will be trained.")
return await _train_core_with_validated_data(
domain=domain,
config=config,
story_directory=story_directory,
output=output_path,
fixed_model_name=fixed_model_name,
uncompress=uncompress,
kwargs=kwargs,
)
if not force_training and old_model:
unpacked = model.unpack_model(old_model)
old_core, old_nlu = model.get_model_subdirectories(unpacked)
last_fingerprint = model.fingerprint_from_path(unpacked)
if not model.core_fingerprint_changed(last_fingerprint,
new_fingerprint):
target_path = os.path.join(train_path, "core")
retrain_core = not model.merge_model(old_core, target_path)
if not model.nlu_fingerprint_changed(last_fingerprint,
new_fingerprint):
target_path = os.path.join(train_path, "nlu")
retrain_nlu = not model.merge_model(old_nlu, target_path)
if force_training or retrain_core:
await _train_core_with_validated_data(
domain=domain,
config=config,
story_directory=story_directory,
output=output_path,
train_path=train_path,
fixed_model_name=fixed_model_name,
uncompress=uncompress,
kwargs=kwargs,
)
else:
print("Dialogue data / configuration did not change. "
"No need to retrain dialogue model.")
if force_training or retrain_nlu:
_train_nlu_with_validated_data(
config=config,
nlu_data_directory=nlu_data_directory,
output=output_path,
train_path=train_path,
fixed_model_name=fixed_model_name,
uncompress=uncompress,
)
else:
print(
"NLU data / configuration did not change. No need to retrain NLU model."
)
if retrain_core or retrain_nlu:
output_path = create_output_path(output_path,
fixed_name=fixed_model_name)
model.create_package_rasa(train_path, output_path, new_fingerprint)
if uncompress:
output_path = decompress(output_path)
print_success("Your Rasa model is trained and saved at '{}'.".format(
output_path))
return output_path
else:
print_success(
"Nothing changed. You can use the old model stored at '{}'"
"".format(os.path.abspath(old_model)))
return old_model
async def train_core_async(
domain: Union[Domain, Text],
config: Text,
stories: Text,
output: Text,
train_path: Optional[Text] = None,
kwargs: Optional[Dict] = None,
) -> Optional[Text]:
"""Trains a Core model.
Args:
domain: Path to the domain file.
config: Path to the config file for Core.
stories: Path to the Core training data.
output: Output path.
train_path: If `None` the model will be trained in a temporary
directory, otherwise in the provided directory.
kwargs: Additional training parameters.
Returns:
If `train_path` is given it returns the path to the model archive,
otherwise the path to the directory with the trained model files.
"""
import rasa.core.train
config = get_valid_config(config, CONFIG_MANDATORY_KEYS_CORE)
_train_path = train_path or tempfile.mkdtemp()
if isinstance(Domain, str) or not train_path:
skill_imports = SkillSelector.load(config)
domain = Domain.load(domain, skill_imports)
story_directory = data.get_core_directory(stories, skill_imports)
else:
story_directory = stories
if not os.listdir(story_directory):
print_error(
"No dialogue data given. Please provide dialogue data in order to "
"train a Rasa Core model.")
return
# normal (not compare) training
print_color("Start training dialogue model ...", color=bcolors.OKBLUE)
await rasa.core.train(
domain_file=domain,
stories_file=story_directory,
output_path=os.path.join(_train_path, "core"),
policy_config=config,
kwargs=kwargs,
)
print_color("Done.", color=bcolors.OKBLUE)
if not train_path:
# Only Core was trained.
output_path = create_output_path(output, prefix="core-")
new_fingerprint = model.model_fingerprint(config,
domain,
stories=story_directory)
model.create_package_rasa(_train_path, output_path, new_fingerprint)
print_success(
"Your Rasa Core model is trained and saved at '{}'.".format(
output_path))
return output_path
return _train_path