I have successfully trained a Rasa NLU Interpreter with my training data and have confirmed that the intent and entities output are correct.
Then, I created Domain, Stories and Custom Actions in for my agent in Rasa Core. I have 2 Custom Actions where I implemented in action.py.
My story is just to execute the custom action
## story_1 * get_description("product": "a") - action_get_description
After training the dialogue model, I ran a Python script to try the bot on console.
interpreter = RasaNLUInterpreter("models/nlu/default/chat") action_endpoint =EndpointConfig(url="http://localhost:5055/webhook") agent =Agent.load("models/dialogue", interpreter=interpreter, action_endpoint=action_endpoint) run.serve_application(agent, channel='cmdline')
But when I tried entering any sentence, it returns an empty array and it’s not uttering the lines I set in dispatcher.utter_message() in the custom actions. I’m not sure how to fix this. Thank you in advance for any suggestions.