Training dialogue manager in python


I am trying to train rasa dialogue manager inside a python file using the following script:

Import the policies and agent

from rasa_core.policies import FallbackPolicy, MemoizationPolicy,KerasPolicy from rasa_core.agent import Agent

Initialize the model with domain.yml

agent = Agent(‘domain.yml’, policies=[MemoizationPolicy(), KerasPolicy()])

loading our training dialogues from

training_data = agent.load_data(‘’)

Training the model

agent.train( training_data, validation_split=0.0, epochs=200 )


However, it seems that “rasa_core” has been deprecated and I get some errors. Is there any alternative to do that with new version of rasa?

Best, Sara

Hi @saramoha, the rasa_core has been deprecated in favor of a single rasa module that unifies Core and NLU. Please make sure you’re using the latest version of our framework.