-
Install rasa core package
pip install rasa_core
-
Create stories.md and domain.yml files that contain the intents, actions and templates. Example of these files can be found at this link
-
Train bot with the script below. This will create a folder called models with a subfolder called 'dialogue'
python -m rasa_core.train -d domain.yml -s stories.md -o models/dialogue
-
Run the bot using the script below. To talk to the bot send a message such as
/greet
and the bot shall respond with the action outlined in the templatepython -m rasa_core.run -d models/dialogue
-
Install rasa_nlu package
pip install rasa_nlu
-
Create nlu.md and nlu_config.yml files as found at this link
-
Train NLU model with the script below and a subfolder under models called 'current/nlu' will be created
python -m rasa_nlu.train -c nlu_config.yml --data nlu.md -o models --fixed_model_name nlu --project current --verbose
-
Run bot for using the script below
python -m rasa_core.run -d models/dialogue -u models/current/nlu
mandelakibiriti / rasa_quickstart Goto Github PK
View Code? Open in Web Editor NEWTutorial to create Rasa Core bot on local command line
Home Page: https://rasa.com/docs/core/quickstart/