Rasa Stack

This is AI chatbot based on Rasa Stack.

Setup and installation

If you haven’t installed Rasa NLU and Rasa Core yet, you can do it by navigating to the project directory and running:

pip install -r requirements.txt

You also need to install a spaCy English language model. You can install it by running:

python -m spacy download en

Files for training the Rasa NLU model

• data/nlu_data.json file contains training examples of six intents:

  • greet
  • goodbye
  • thanks
  • deny
  • joke
  • name (examples of this intent contain an entity called 'name')

• nlu_cofing.yml file contains the configuration of the Rasa NLU pipeline:

language: "en"

pipeline: spacy_sklearn

Files for training the Rasa Core model

• data/stories.md file contains some training stories which represent the conversations between a user and the assistant.
• domain.yml file describes the domain of the assistant which includes intents, entities, slots, templates and actions the assistant should be aware of.
• actions.py file contains the code of a custom action which retrieves a Chuck Norris joke by making an external API call.
• endpoints.yml file contains the webhook configuration for custom action.

How to use this project?

1. You can train the Rasa NLU model by running:

python -m rasa_nlu.train -c nlu_config.yml --data data/nlu_data.md -o models --fixed_model_name nlu --project current --verbose

This will train the Rasa NLU model and store it inside the /models/current/nlu folder of your project directory.

2. Train the Rasa Core model by running:

python -m rasa_core.train -d domain.yml -s data/stories.md -o models/current/dialogue -c policies.yml

This will train the Rasa Core model and store it inside the /models/current/dialogue folder of your project directory.

3. Start the server for the custom action by running:

python -m rasa_core_sdk.endpoint --actions actions

This will start the server for emulating the custom action.

4. Test the assistant by running:

python -m rasa_core.run -d models/current/dialogue -u models/current/nlu --endpoints endpoints.yml --credentials credentials.yml

python -m rasa_core.run -d models/current/dialogue -u models/current/nlu --credentials credentials.yml

ngrok http 5005

This will load the assistant in your terminal for you to chat.

Conversation Examples

Example 1 of conversation

User: Hi bot
Bot: Hey There! Tell me your name!
User: My name is Tatiana
Bot: Nice to meet you Tatiana. How can I help?
User: I want to buy a laptop
Bot: Which brand of laptop fo you want to buy?
User: I have identified MacBook
Bot: Order was placed for MacBook laptop
User: Thank you so much
Bot: My pleasure
User: Bye bot
Bot: Have a nice day Tatiana!