DEV Community

Cover image for RASA - Rasa X
Petr Janik
Petr Janik

Posted on

4 2

RASA - Rasa X

Rasa X is a tool for Conversation-Driven Development (CDD), the process of listening to your users and using those insights to improve your AI assistant.

Installation

Make sure you have your python virtual environment activated (source venv/bin/activate).
To install Rasa X locally, run the following in your project root:

pip install rasa-x --extra-index-url https://pypi.rasa.com/simple
Enter fullscreen mode Exit fullscreen mode

Update the requirements.txt after the installation.

pip freeze > requirements.txt
Enter fullscreen mode Exit fullscreen mode

You can learn more about installing Rasa X in the documentation.

Starting the server

Start the server by running rasa x.
This will open a browser tab on http://localhost:5002 with Rasa X GUI.

Rasa X

Capabilities of Rasa X

  • You can talk to your chatbot. While you are talking, a story and test story is being generated for you. You can also observe what intents have been recognized, with what accuracy, what is the current active_loop, which slot is being filled in etc. You can save the generated story. This is much more convenient than writing the story yourself.
  • You can see and review past conversations.
  • You can tag and filter past conversations.
  • You can correct chatbot's decisions.
  • You can edit all the files we have been working with so far.
  • There's so much more Rasa X is capable of! I encourage you to launch the server and start discovering by yourself.

You can learn more about Rasa X in the documentation.

You can read more about Conversation-Driven Development on Rasa blog or in The CDD Playbook

In the next chapter, we will look at categorical slots.

Repository for this tutorial:

You can checkout the state of the repository at the end of this tutorial by running:

git clone --branch 08-rasa-x git@github.com:petr7555/rasa-dev-tutorial.git
Enter fullscreen mode Exit fullscreen mode

API Trace View

Struggling with slow API calls? 👀

Dan Mindru walks through how he used Sentry's new Trace View feature to shave off 22.3 seconds from an API call.

Get a practical walkthrough of how to identify bottlenecks, split tasks into multiple parallel tasks, identify slow AI model calls, and more.

Read more →

Top comments (0)

A Workflow Copilot. Tailored to You.

Pieces.app image

Our desktop app, with its intelligent copilot, streamlines coding by generating snippets, extracting code from screenshots, and accelerating problem-solving.

Read the docs

👋 Kindness is contagious

Please leave a ❤️ or a friendly comment on this post if you found it helpful!

Okay