def create(model_metadata: Metadata,
component_builder: Optional[ComponentBuilder] = None,
skip_validation: bool = False) -> 'Interpreter':
"""Load stored model and components defined by the provided metadata."""
context = {}
if component_builder is None:
# If no builder is passed, every interpreter creation will result
# in a new builder. hence, no components are reused.
component_builder = components.ComponentBuilder()
pipeline = []
# Before instantiating the component classes,
# lets check if all required packages are available
if not skip_validation:
components.validate_requirements(model_metadata.component_classes)
for i in range(model_metadata.number_of_components):
component_meta = model_metadata.for_component(i)
component = component_builder.load_component(
component_meta, model_metadata.model_dir, model_metadata,
**context)
try:
updates = component.provide_context()
if updates:
context.update(updates)
pipeline.append(component)
except components.MissingArgumentError as e:
raise Exception("Failed to initialize component '{}'. "
"{}".format(component.name, e))
return Interpreter(pipeline, context, model_metadata)
def __init__(
self,
cfg: RasaNLUModelConfig,
component_builder: Optional[ComponentBuilder] = None,
skip_validation: bool = False,
model_to_finetune: Optional["Interpreter"] = None,
) -> None:
self.config = cfg
self.skip_validation = skip_validation
self.training_data = None # type: Optional[TrainingData]
if component_builder is None:
# If no builder is passed, every interpreter creation will result in
# a new builder. hence, no components are reused.
component_builder = components.ComponentBuilder()
# Before instantiating the component classes, lets check if all
# required packages are available
if not self.skip_validation:
components.validate_requirements(cfg.component_names)
if model_to_finetune:
self.pipeline = model_to_finetune.pipeline
else:
self.pipeline = self._build_pipeline(cfg, component_builder)
def get(self,
repository_version,
repository_authorization,
rasa_version,
use_cache=True):
update_request = backend().request_backend_parse_nlu(
repository_version, repository_authorization)
repository_name = (f"{update_request.get('version_id')}_"
f"{update_request.get('total_training_end')}_"
f"{update_request.get('language')}")
interpreter = self.interpreters.get(repository_name)
if interpreter and use_cache:
return interpreter
persistor = BothubPersistor(repository_version,
repository_authorization, rasa_version)
model_directory = mkdtemp()
persistor.retrieve(str(update_request.get("repository_uuid")),
model_directory)
self.interpreters[repository_name] = Interpreter(
None, {
"language": update_request.get("language")
}).load(model_directory,
components.ComponentBuilder(use_cache=False))
return self.get(repository_version, repository_authorization,
rasa_version)
def load_entity_extractor(data_file, config_file):
training_data = load_data(data_file)
configuration = config.load(config_file)
comp_builder = components.ComponentBuilder()
#component = comp_builder.create_component("ner_crf",configuration)
#ee = EntityExtractor(components.Component(configuration))
crf = CRFEntityExtractor()
crf.train(training_data, configuration)
model_directory = crf.persist('./models/default/')
return model_directory
def create(
model_dir: Text,
model_metadata: Metadata,
component_builder: Optional[ComponentBuilder] = None,
skip_validation: bool = False,
should_finetune: bool = False,
) -> "Interpreter":
"""Create model and components defined by the provided metadata.
Args:
model_dir: The directory containing the model.
model_metadata: The metadata describing each component.
component_builder: The
:class:`rasa.nlu.components.ComponentBuilder` to use.
skip_validation: If set to `True`, does not check that all
required packages for the components are installed
before loading them.
should_finetune: Indicates if the model components will be fine-tuned.
Returns:
An interpreter that uses the created model.
"""
context: Dict[Text, Any] = {"should_finetune": should_finetune}
if component_builder is None:
# If no builder is passed, every interpreter creation will result
# in a new builder. hence, no components are reused.
component_builder = components.ComponentBuilder()
pipeline = []
# Before instantiating the component classes,
# lets check if all required packages are available
if not skip_validation:
components.validate_requirements(model_metadata.component_classes)
for i in range(model_metadata.number_of_components):
component_meta = model_metadata.for_component(i)
component = component_builder.load_component(
component_meta, model_dir, model_metadata, **context
)
try:
updates = component.provide_context()
if updates:
context.update(updates)
pipeline.append(component)
except components.MissingArgumentError as e:
raise Exception(
"Failed to initialize component '{}'. "
"{}".format(component.name, e)
)
return Interpreter(pipeline, context, model_metadata)
def get(self, update, use_cache=True):
interpreter = self.interpreters.get('teste')
if interpreter and use_cache:
return interpreter
persistor = BothubPersistor(update)
model_directory = mkdtemp()
# persistor.retrieve(
# str(update.repository.uuid),
# str(update.id),
# model_directory)
persistor.retrieve(str('teste'), model_directory)
self.interpreters['teste'] = BothubInterpreter.load(
model_directory, components.ComponentBuilder(use_cache=False))
return self.get(update)
def get(self, update, repository_authorization, use_cache=True):
update_request = backend().request_backend_parse_nlu(
update, repository_authorization
)
interpreter = self.interpreters.get(update_request.get("update_id"))
if interpreter and use_cache:
return interpreter
persistor = BothubPersistor(update, repository_authorization)
model_directory = mkdtemp()
persistor.retrieve(str(update_request.get("repository_uuid")), model_directory)
self.interpreters[update_request.get("update_id")] = BothubInterpreter.load(
model_directory, components.ComponentBuilder(use_cache=False)
)
return self.get(update, repository_authorization)
def get_interpreter(self,
repository_version,
repository_authorization,
rasa_version,
use_cache=True) -> BothubInterpreter:
update_request = backend().request_backend_parse_nlu_persistor(
repository_version,
repository_authorization,
rasa_version,
no_bot_data=True)
repository_name = (
f"{update_request.get('version_id')}_{update_request.get('language')}"
)
last_training = f"{update_request.get('total_training_end')}"
# tries to fetch cache
retrieved_cache = self.cached_interpreters.get(repository_name)
if retrieved_cache and use_cache:
# retrieve cache only if it's the same training
if retrieved_cache["last_training"] == last_training:
retrieved_cache["last_request"] = datetime.now()
return retrieved_cache["interpreter_data"]
persistor = BothubPersistor(repository_version,
repository_authorization, rasa_version)
model_directory = mkdtemp()
persistor.retrieve(str(update_request.get("repository_uuid")),
model_directory)
interpreter = BothubInterpreter(
None, {"language": update_request.get("language")})
interpreter = interpreter.load(
model_directory, components.ComponentBuilder(use_cache=False))
if use_cache: # update/creates cache
self.cached_interpreters[repository_name] = {
"last_training": last_training,
"interpreter_data": interpreter,
"last_request": datetime.now()
}
return interpreter
model_path = get_model(model)
if not model_path:
print_error("No model found. Train a model before running the "
"server using `rasa train nlu`.")
exit(1)
_, nlu_model = get_model_subdirectories(model_path)
if not os.path.exists(nlu_model):
print_error("No NLU model found. Train a model before running the "
"server using `rasa train nlu`.")
exit(1)
# input shell
# rasa.nlu.run.run_cmdline(nlu_model)
print("model_path is {},nlu_model is {}".format(model_path, nlu_model))
print("please input your text to parse")
# message = input().strip()
# message = "这款衣服有货吗"
message = "身高170体重140"
interpreter = Interpreter.load(nlu_model, component_builder)
result = interpreter.parse(message)
print(json.dumps(result, indent=2))
if __name__ == "__main__":
component_builder = components.ComponentBuilder()
test_train_nlu_core()
test_parse()
