Skip to content
/ tracy Public

A simple and easy to use trainer to generate Rasa/Snips NLU datasets

License

Notifications You must be signed in to change notification settings

YuukanOO/tracy

Folders and files

NameName
Last commit message
Last commit date

Latest commit

09e84ac · Apr 14, 2019

History

57 Commits
Apr 14, 2019
Apr 14, 2019
Jan 15, 2018
Feb 25, 2018
Jan 15, 2018
Mar 6, 2018
Dec 19, 2018
Mar 26, 2018
Apr 14, 2019
Apr 14, 2019
Mar 7, 2018

Repository files navigation

tracy

A simple and easy to use trainer to generate Rasa NLU and Snips NLU needed files.

Inspired by Chatito and Rasa NLU Trainer.

Want to create your own personal assistant? Check my other project pytlas!

Screenshot

How does that work?

An agent represents a project (bot, assistant, whatever).

A skill represents what your agent can do. To define its capabilities, you must create intents within a skill to keep it logically organized (or you can put all your intents in one skill if you wish).

An intent is made of slots and samples. Slots defines what could be extracted from your samples. A slot could be of a particular entity type. This way, you can easily shared common stuff such as locations, enums or so.

Once you have define some skills, you can attached them to your agent and click the Train button to export the resulting dataset.

Data are persisted via LocalStorage as of now.

Development

Run npm install to install packages and npm start to start the webpack dev server.

About

A simple and easy to use trainer to generate Rasa/Snips NLU datasets

Topics

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages