def start_training(bot: str, user: str):
""" Prevents training of the bot if the training session is in progress otherwise start training """
exception = None
model_file = None
training_status = None
ModelProcessor.set_training_status(
bot=bot,
user=user,
status=MODEL_TRAINING_STATUS.INPROGRESS.value,
)
try:
model_file = train_model_for_bot(bot)
training_status = MODEL_TRAINING_STATUS.DONE.value
except Exception as e:
logging.exception(e)
training_status = MODEL_TRAINING_STATUS.FAIL.value
exception = str(e)
raise AppException(exception)
finally:
ModelProcessor.set_training_status(
bot=bot,
user=user,
status=training_status,
model_path=model_file,
exception=exception,
)
AgentProcessor.reload(bot)
return model_file
async def train(current_user: User = Depends(auth.get_current_user)):
model_file = await train_model_from_mongo(current_user.get_bot())
AgentProcessor.reload(current_user.get_bot())
return {
"data": {
"file": model_file
},
"message": "Model trained successfully"
}
async def download_file(current_user: User = Depends(auth.get_current_user), ):
"""Download latest trained model file"""
try:
model_path = AgentProcessor.get_latest_model(current_user.get_bot())
return FileResponse(model_path)
except Exception as e:
return AppException(str(e))
def test_get_agent(self, monkeypatch):
def mongo_store(*arge, **kwargs):
return None
monkeypatch.setattr(Utility, "get_local_mongo_store", mongo_store)
agent = AgentProcessor.get_agent("tests")
assert isinstance(agent, Agent)
async def chat(request_data: TextData,
current_user: User = Depends(auth.get_current_user)):
""" This function returns a bot response for a given text/query. It is basically
used to test the chat functionality of the bot """
model = AgentProcessor.get_agent(current_user.get_bot())
response = await model.handle_text(request_data.data,
sender_id=current_user.get_user())
return {"data": {"response": response[0]["text"] if response else None}}
async def predict_intent(request_data: TextData,
current_user: User = Depends(auth.get_current_user)):
model = AgentProcessor.get_agent(current_user.get_bot())
response = await model.parse_message_using_nlu_interpreter(
request_data.data)
intent = response.get("intent").get("name") if response else None
confidence = response.get("intent").get("confidence") if response else None
return {"data": {"intent": intent, "confidence": confidence}}
async def predict_intent(request_data: TextData,
current_user: User = Depends(auth.get_current_user)):
""" This function returns the predicted intent of the entered text by using the trained
rasa model of the chatbot """
model = AgentProcessor.get_agent(current_user.get_bot())
response = await model.parse_message_using_nlu_interpreter(
request_data.data)
intent = response.get("intent").get("name") if response else None
confidence = response.get("intent").get("confidence") if response else None
return {"data": {"intent": intent, "confidence": confidence}}
async def download_model(
background_tasks: BackgroundTasks,
current_user: User = Depends(auth.get_current_user),
):
"""Download latest trained model file"""
try:
model_path = AgentProcessor.get_latest_model(current_user.get_bot())
response = FileResponse(model_path,
filename=os.path.basename(model_path),
background=background_tasks)
response.headers[
"Content-Disposition"] = "attachment; filename=" + os.path.basename(
model_path)
return response
except Exception as e:
raise AppException(str(e))
def test_get_agent_from_cache_does_not_exists(self):
with pytest.raises(AppException):
agent = AgentProcessor.get_agent("test")
assert isinstance(agent, Agent)
def test_get_agent_from_cache(self):
agent = AgentProcessor.get_agent("tests")
assert isinstance(agent, Agent)
async def chat(request_data: TextData,
current_user: User = Depends(auth.get_current_user)):
model = AgentProcessor.get_agent(current_user.get_bot())
response = await model.handle_text(request_data.data)
return {"data": {"response": response[0]["text"] if response else None}}