Git Product home page Git Product logo

hun-appointment-chatbot's Introduction

Hun-appointment-chatbot

A simple Hungarian chatbot for booking an appointment using the Rasa framework.

Setup

  • Install dependencies
  • Rasa will try to use NLP models linked to 'hu' in Spacy
    • Link Hungarian models to Spacy: python3 -m spacy link hu_core_ud_lg hu
  • rasa train should work now

Usage

Before using the bot, you'll have to specify a list of dates that the bot'll accept or suggest as free dates. You can do this by adding new roes to the test_data.json file. Each row should correspond to an interval, like this:

[
  {"start_date":  "2021-01-18T12:00", "end_date": "2021-01-18T18:00"},
  {"start_date":  "2021-01-20T12:00", "end_date": "2021-01-20T18:00"}
]

The chatbot will ignore all past intervals or the past part of any relevant intervals.

You can test the chatbot on CLI running rasa run actions & rasa shell, where the first command starts the action server in the background, and the second will start the conversation in the terminal. The program might take a few seconds to load, after which you can initiate a conversation with the chatbot.

The following is an example conversation, that shows the chatbot's capabilities.

USER:   szia                                                                                                                                                                                                                     
BOT:    Szia! Miben segíthetek?
USER:   időpontot szertenék foglalni                                                                                                                                                                                             
BOT:    Okés. Mikor lenne jó?
USER:   holnap esetleg?                                                                                                                                                                                                          
BOT:    Ráérek holnap. Mikor lenne jó aznap?
USER:   ráérsz délután?                                                                                                                                                                                                          
BOT:    12 óra és délután 6 óra között ráérek. Mikor legyen pontosan?
USER:   legyen 14:30-kor                                                                                                                                                                                                         
BOT:    Rendben, akkor holnap délután fél 3-kor találkozunk.
USER:   köszi, viszlát!                                                                                                                                                                                                          
BOT:    Viszlát!

License

This project is licensed under Apache-2.0 license. Feel free to use it in your own projects.

Contribute

Any help or feedback in further developing the library is welcome!

hun-appointment-chatbot's People

Contributors

gellertpalfi avatar gman1999 avatar nsomabalint avatar rfarkas avatar viktorherdinai avatar

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.