Giter VIP home page Giter VIP logo

tracy's Introduction

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.

tracy's People

Contributors

jleicherproxiad avatar yuukanoo avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar

tracy's Issues

Problem with Chinese data

Hi! When I try to use this awesome tool to annotate Chinese datasets, I face a problem that the range of entities will cross over with each other if two entities is adjacent as you can see in the image.
issue
The raw text is 把卧室的灯打开 and 卧室 means bedroom, means lamp, 打开 means turn on. The whole sentence means "turn on the lamp in the bedroom".
Also when I try to export the data to a JSON file these entities are totally a mess.
May be the reason for the problem is that there is a space between words in English but not in Chinese.

Import data from a raw dataset

Hi, I have predefined data file in json format. Now I want to add more data in that file using tracy like we do in rasa-nlu-trainer. How we can do that?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.