Giter VIP home page Giter VIP logo

luistrainer's Introduction

LUIS Trainer

A Simple python framework to train and build LUIS Models

Description

Creating and training LUIS models on the [website] (www.luis.ai) can be slow and frustrating.
Instead you can use this framework which uses the LUIS API to train your models in a much simpler, meta-data driven way.

Usage

  1. Setup Config

    • Add your subscription_key in config.json (subscription key for LUIS. You can find your's [here] (https://www.luis.ai/Home/UserSettings)
    • Add your App Name, App Description and appID. (LUIS app name and appId)
      If it's a new app and you don't have an id, put appId as None
  2. Create Intents

    • To create a intent just create a .txt file in the intents folder with the filename as the name of the intent.
      You can add all the utterances or examples for this intent in this .txt, each on a seperate line.
  3. Create Entities

    • To create a entity add a json object to the array of the entities field in the config.json file with the following schema
      { "name" : name of entity}

    • To add the entity to a training example, put paranthesis around the example and then list
      the entity names after the example seperated by '<=>'
      eg: "Book a (Delta) flight from (NYC) to (Miami) <=> airlines <=> destination <=> destination"

      The order of entity names should be in the order in which they occur in the statement.

    Note: Currently it doesn't work for hierarchial or composite entities.

  4. Create Phraselists

    • To create a phraselist add a json object to the array of the phraselists field in config.json file with the following schema
      {
      "name" : name of phraselist ,
      "mode" : exchangable or non-exchangable,
      "phrases" : [comma seperated strings of phrases]
      }
  5. Train/Build the LUIS Model

    • CD into code folder and run main.py ($ python main.py)

After following the above steps, you can visit the application portal and you will find your application built and trained.

You can keep making changes to your intent files/ entities/ phraselists any number of times you want. Just run main.py and your model will be retrained with the changes.

Contributing

Feel free to report bugs, issues or send in pull requests.

License

MIT License

luistrainer's People

Contributors

avoidwork avatar ganadiniakshay avatar

Watchers

 avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.