Getting Started with Rasa

Don’t feel like reading?

1: What is Rasa?

Rasa Open Source is a conversational AI framework for building contextual assistants.

Rasa Open Source includes

  • NLU: determines what the user wants and captures key contextual information
  • Core: selects the next best response or action based on conversation history
  • Channels and integrations: connect assistant to users and backend systems

Rasa X is a toolset used to improve a contextual assistant built using Rasa Open Source.

2: Build an assistant with Rasa Open Source

To create your first Rasa project, copy the two commands in the cell below and run them in your terminal.

The first command installs Rasa Open Source and Rasa X onto your system.

The second command rasa init then creates a sample Rasa project in your current directory. This includes some sample training data and the required configuration files to get you started. The command also automatically trains your first model using this data and invites you to speak to the trained assistant.

$ pip install rasa-x --extra-index-url
$ rasa init

3: Improve your assistant with Rasa X

Rasa X is a toolset that layers on top of Rasa Open Source, making it easier to review conversations, identify next steps in development, and improve your assistant.

Run the cell below to start a demo. After a few seconds, you will see a button that opens Rasa X with a simple assistant in another tab.

rasa x

Note: This is just a demo and not a hosted version of Rasa X. Once you close the window, any changes you have made will be lost!

4: Join the Community

The Rasa community is a friendly, diverse group of makers and conversational AI enthusiasts. A lot of us hang out in the forum to answer each other’s questions:

You can get involved with the Rasa community in many ways: Show your support by giving Rasa a star: Star