python nlu_model.py
The biggest change in how Rasa Core model works is that custom action 'action_weather' now needs to run on a separate server. That server has to be configured in a 'endpoints.yml' file. This is how to train and run the dialogue management model:
- Start the custom action server by running:
python -m rasa_core_sdk.endpoint --actions actions
- Open a new terminal and train the Rasa Core model by running:
python dialogue_management_model.py
- Talk to the chatbot once it's loaded.
The process of running the interactive session is very similar to training the Rasa Core model:
- Make sure the custom actions server is running:
python -m rasa_core_sdk.endpoint --actions actions
- Start the interactive training session by running:
python train_interactive.py
- Configure the slack app as shown in the video
- Make sure custom actions server is running
- Start the agent by running run_app.py file (don't forget to provide the slack_token)
- Start the ngrok on the port 5004
- Provide the url: https://your_ngrok_url/webhooks/slack/webhook to 'Event Subscriptions' page of the slack configuration.
- Talk to you bot.