/rasa_core

machine learning based dialogue engine for conversational software

Primary LanguagePythonApache License 2.0Apache-2.0

Rasa Core

Join the chat on Gitter Build Status Coverage Status PyPI version

Introduction

Rasa Core is a framework for building conversational software, which includes:

  • chatbots on Messenger
  • Slack bots
  • Alexa Skills
  • Google Home Actions

etc.

Rasa Core's primary purpose is to help you build contextual, layered conversations with lots of back-and-forth. To have a real conversation, you need to have some memory and build on things that were said earlier. Rasa Core lets you do that in a scalable way.

There's a lot more background information in this blog post

Where to get help

There is extensive documentation:

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

Please use gitter for quick answers to questions.

README Contents:

How to contribute

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. You will also be asked to sign a Contributor License Agreement

Development Internals

Running and changing the documentation

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

brew install sphinx
pip install -r dev-requirements.txt

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

make livedocs

Visit the local version of the docs at http://localhost:8000 in your browser. You can now change the docs locally and the web page will automatically reload and apply your changes.

License

Licensed under the Apache License, Version 2.0. Copyright 2018 Rasa Technologies GmbH. Copy of the license.

As a reference, the following contains a listing of the licenses of the different dependencies as of this writing. Licenses of the dependencies:

required package License
apscheduler MIT
fakeredis BSD
graphviz         MIT
typing PSF
future MIT
six MIT
h5py BSD
jsonpickle BSD
keras MIT
numpy BSD
pandoc MIT
redis MIT
tensorflow Apache Licence 2.0
networkx BSD
fbmessenger Apache Licence 2.0
tqdm MIT
ConfigArgParse MIT