Hey guys! I have recently started using RASA. I am trying to build a college enquiry chatbot.
The problem I am facing is the bot is giving a different reply than what it is trained for
It is giving a reply (intent) different than the intent with the highest confidence
Please help
check for the “courses” intent
from rasa_nlu.training_data import load_data from rasa_nlu.config import RasaNLUModelConfig from rasa_nlu.model import Trainer from rasa_nlu import config
training_data = load_data(“nlu.md”)
trainer = Trainer(config.load(“config.yml”))
interpreter = trainer.train(training_data)
model_directory = trainer.persist(“./models/nlu”, fixed_model_name=“current”)
from rasa_core.policies import FallbackPolicy, KerasPolicy, MemoizationPolicy from rasa_core.agent import Agent
fallback = FallbackPolicy(fallback_action_name=“utter_unclear”, core_threshold=0.2, nlu_threshold=0.1)
agent = Agent(‘domain.yml’, policies=[MemoizationPolicy(), KerasPolicy(), fallback])
training_data = agent.load_data(‘stories.md’)
agent.train( training_data, validation_split=0.0, epochs=200 )
agent.persist(‘models/dialogue’)
#Starting the Bot
from rasa_core.agent import Agent agent = Agent.load(‘models/dialogue’, interpreter=model_directory)
print(“Your bot is ready to talk! Type your messages here or send ‘stop’”) while True: a = input() if a == ‘stop’: break responses = agent.handle_message(a) for response in responses: print(response[“text”]) print(interpreter.parse(a))
config.yml (499 Bytes) domain.yml (2.3 KB) nlu.md (1.4 KB) stories.md (673 Bytes)
this is the code
@Juste please help
Hi there, do you have stories in which you tell the bot how to reply to the correct intent? It could be that it’s picking up the intent correctly, but doesn’t know how to respond because it hasn’t seen this context in its stories before.
