Rasa Open Source is a machine learning framework for automated text and voice-based conversations. Rasa X is a tool that helps you build, improve, and deploy AI Assistants that are powered by the Rasa Open Source framework.
Getting start:¶
NLU understands the user’s message based on the previous training data been provided:
Intent classification: Interpreting meaning based on predefined intents (Example: “Please send the confirmation to mhm@example.com” is a send_confirmation intent with 93% confidence).
Entity extraction: Recognizing structured data (Example: mhm@example.com is an email).
Core decides what happens next in this conversation. Its machine learning-based dialogue management predicts the next best action based on the input from NLU, the conversation history, and your training data. (Example: Core has the confidence of 87% that ask_primary_change is the next best action to confirm with the user if they want to change their primary contact information.)
For more details, you can check:
Creating project:¶
Create a virtual environment (For Windows):
python -m venv — system-site-packages ./venv
Activate the virtual environment:
.\venv\Scripts\activate
Install rasa:
pip install rasa
Create an initial project on rasa:
rasa init
This command will create following files:
It creates the following files:
.
├── actions.py
├── config.yml (Configuration of your NLU and Core models)
├── credentials.yml
├── data
│ ├── nlu.yml (NLU training data)
│ └── stories.yml (stories)
├── domain.yml (assistant’s domain)
├── endpoints.yml
├── models
│ └── <timestamp>.tar.gz
Train your bot:
rasa train
Run project:
rasa run actions
Now you are ready to play with your own chatbot!