Warning: This document is for an old version of Rasa X.

Installation and Setup

To install Rasa X on your computer, use pip:

pip install rasa-x --extra-index-url https://pypi.rasa.com/simple

Since Rasa is a dependency of Rasa X, this will also install the rasa package if you don’t have it already.

To start Rasa X, move into your project directory (or create one using rasa init) and run:

rasa x


When you run Rasa X locally, your training data and stories are read from the files in your project (e.g. data/nlu.md), and any changes you make in the UI are saved back to those files. Conversations and other data are stored in an SQLite database saved in a file called rasa.db.

Getting Conversations to Annotate

If you have an existing Rasa assistant running, you can import those user-assistant conversations into your local instance of Rasa X. See Importing Conversations.

If this is a new Rasa project, you can get your first conversations by inviting some test users to try your assistant.