Command Line Interface

Command Line Interface Overview

The command line interface (CLI) provides easy-to-remember commands for common tasks.

Command	Effect
`rasa init`	Creates a new project with example training data, actions, and config files.
`rasa train`	Trains a model using your NLU data and stories, saves trained model in `./models`.
`rasa interactive`	Starts an interactive learning session to create new training data by chatting.
`rasa shell`	Loads your trained model and lets you talk to your assistant on the command line.
`rasa run`	Starts a Rasa server with your trained model. See Configuring the HTTP API for details.
`rasa run actions`	Starts an action server using the Rasa SDK.
`rasa visualize`	Visualizes stories.
`rasa test`	Tests a trained Rasa model using your test NLU data and stories.
`rasa data split nlu`	Performs a split of your NLU data according to specified percentages.
`rasa data convert nlu`	Converts NLU training data between different formats.
`rasa x`	Launch Rasa X locally.
`rasa -h`	Shows all available commands.

Creating a New Project

A single command sets up a complete project for you with some example training data.

rasa init

This creates the following files:

.
├── __init__.py
├── actions.py
├── config.yml
├── credentials.yml
├── data
│   ├── nlu.md
│   └── stories.md
├── domain.yml
├── endpoints.yml
└── models
    └── <timestamp>.tar.gz

Note: The rasa init command will ask if you want to train an initial model using this data. If you answer no, the models directory will be empty.

Training a Model

The main command is:

rasa train

This command trains a Rasa model combining a Rasa NLU and a Rasa Core model. If you want to train an NLU or a Core model alone, use rasa train nlu or rasa train core. Rasa will automatically skip training Core or NLU if the training data and config haven’t changed.

After training, your model will be stored in the directory defined by --out. The name of the model is by default <timestamp>.tar.gz. You can specify a name using --fixed-model-name.

Interactive Learning

To start an interactive learning session with your assistant, run:

rasa interactive

If a trained model is provided using the --model argument, the interactive learning process is started with the provided model. If no model is specified, rasa interactive will train a new Rasa model with the data located in data/.

Starting a Server

To start a server running your Rasa model, run:

rasa run

Action Server

To run your action server:

rasa run actions

Visualizing Your Stories

To open a browser tab with a graph showing your stories:

rasa visualize

Evaluating a Model on Test Data

To evaluate your model on test data, run:

rasa test

Create a Train-Test Split

To create a split of your NLU data:

rasa data split nlu

Convert Data Between Markdown and JSON

To convert NLU data from various formats to JSON or Markdown:

rasa data convert nlu

Starting Rasa X

Rasa X can be started locally by executing:

rasa x

By default, Rasa X runs on port 5002. You can change it using the --rasa-x-port argument.

👋 I can help you get started with Rasa and answer your technical questions.