Coder Social home page Coder Social logo

chatbot-kim's Introduction

KI-Campus Chatbot "KIM"

Training of the Model

Choose the folder with the chatbot in English (KI-Campus_en) or in German (KI-Campus_de)

    rasa train

Configuration

Course Recommender Endpoint

NOTE Currently only supported for German chabot (rasa/KI-Campus_de/)

Create (or modify) the configuration file kic_recommender.yml in directory

    rasa/KI-Campus_de/

and add/modify configuration entry for Course Recommender Endpoint with the base URL for the endpoint and the access token:

# This file contains the custom service endpoints your bot can use.

# recommender service (DFKI) configuration
recommender_api:
  url: "<base URL for recommender service endpoint>"
  token: "<recommender access token>"

Usage

Start the Rasa Server

    rasa run --enable-api

Start the Action Server

    rasa run actions

NOTE the actions must not be started from within the actions/ sub-directory, but the rasa project's root directory (e.g. rasa/KI-Campus_de/), otherwise not all actions may be automatically started.

Start for Development

Change configuration to 'for local development' endpoint in endpoints.yml in sub-directories

    rasa/KI-Campus_de/
    rasa/KI-Campus_en/

then (within the respective directory) start the chatbot shell with

    rasa shell

for testing logged-in user, get your access-token from the ki-campus website and start shell with

    rasa shell --conversation-id <access-token>

Docker

In the outer project structure run:

Docker Compose (de)

    docker-compose -f docker-compose_de.yml -p kicampus_de up --build

Docker Compose (en)

    docker-compose -f docker-compose_en.yml -p kicampus_en up --build

chatbot-kim's People

Contributors

russaa avatar tabeaot avatar theresazobel avatar tstaubitz avatar

Stargazers

Youngmuk Kim avatar  avatar Nikolaus Schlemm avatar  avatar

Watchers

MatthiasWiesner avatar  avatar  avatar  avatar  avatar

Forkers

mmig

chatbot-kim's Issues

[13.07.2023]: [Improved Feedback]

We want to enhance the feedback feature at the end of the chatbot conversation to gain more useful insights.

Steps/Questions:

  1. Wurde dein Aliegen gelöst bzw. ausreichend beantwortet? Ja / Nein
    -> Nein: Was hat dir nicht gefallen?
    (a) Antwort passte nicht zum Anliegen
    (b) Antwort war nicht ausreichend oder verständlich
    (c) Etwas anderes

  2. Wie wahrscheinlich ist es, dass du den Chatbot nocheinmal verwendest?
    Bewerte auf einer Skala von 1 (sehr unwahrscheinlich) bis 5 (sehr wahrscheinlich)

  3. Wie freundlich wirkte der Chatbot auf dich ?
    Bewerte auf einer Skala von 1 (sehr unfreundlich) bis 5 (sehr freundlich)

  4. Wie frustrierend fandest du dein Gespräch mit dem Chatbot?
    Bewerte auf einer Skala von 1 (gar nicht frustrierend) bis 5 (sehr frustrierend)

  5. Hast du noch weitere Anregungen / Feedback für uns? Freitext

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.