Please use gitter for quick answers to questions. Please also fill out the survey. This feedback will help us make the framework much better.

The idea behind Rasa Core is that conversational software is not like normal software. Rather than writing a bunch of if-else statements, you provide training conversations which are used to create a probabilistic model of what should happen next. Why would you want to do this?

• debugging is easier
• greater flexibility
• can improve automatically over time

Rasa is designed to be composable and hackable, with loosely coupled pieces interacting through simple APIs. This means that you can use it if you don't know anything about machine learning, but if you do it's easy to experiment.

• master  (if you install from github) or
• stable   (if you install from pypi)

If you are new to Rasa and want to create a bot, you should start with the installation and head to the basic tutorial.

• Setup
• How to contribute
• Development Internals
• License

There isn't a released pypi package yet. Hence, you need to clone and install the package from the github repository. For a more detailed description, please visit the Installation page of the docs.

To install, run:

git clone https://github.com/RasaHQ/rasa_dm.git
cd rasa_dm
pip install -r requirements.txt
pip install -e .

This will install the application and necessary requirements. We use rasa NLU for intent classification & entity extraction, but you are free to use other NLU services like wit.ai, api.ai, or LUIS.ai.

We are very happy to receive and merge your contributions. There is some more information about the style of the code and docs in the documentation.

In general the process is rather simple:

1. create an issue describing the feature you want to work on (or have a look at issues with the label help wanted)
2. write your code, tests, and documentation
3. create a pull request describing your changes

You pull request will be reviewed by a maintainer, who might get back to you about any necessary changes or questions.

To build & edit the docs, first install all necessary dependencies:

brew install sphinx
pip install sphinx_rtd_theme
pip install sphinx-autobuild

After the installation has finished, you can run and view the documentation locally using

cd docs
sphinx-apidoc -o . ../rasa_core
make livehtml

Visit the local version of the docs at http://localhost:8000 in your browser.

Licensed under the Apache License, Version 2.0. Copyright 2017 Rasa Technologies GmbH. Copy of the license.