Skip to main content

Toolkit for building conversational information access systems.

Project description

DialogueKit

Code style: black PyPi version Coverage Badge Tests Python version

DialogueKit is a library for conversational information access (CIA). It contains based classes for fundamental concepts, such as dialogue participants, dialogue management, natural language understanding, natural language generation, etc. In addition to the fundamental concepts DialogueKit contains an evaluation module, for evaluating the performance of and CIA systems. Consult the documentation for details.

Install as a package

DialogueKit is published to PyPI, install it by running:

pip install dialoguekit

If you want to install a DialogueKit from a specific commit or straight from github this is still possible.

The command will install the latest version from the main branch.

  • On Windows you may need to run this command before pip installing
ssh -t git github.com    
  • pip install
pip install git+ssh://git@github.com/iai-group/dialoguekit.git

If you want to specify a specific commit as the source of the package append the commit hash to the end of the command separated with a "@".

  • Specific commit as the source of the package.
pip install git+ssh://git@github.com/iai-group/dialoguekit.git@faa5c1fca37aaa275105cc1ca7698783719551c2

Usage example

  1. Define agent and user

    from dialoguekit.core.utterance import Utterance
    from dialoguekit.participant.user import User, UserType
    from sample_agents.parrot_agent import ParrotAgent
    
    # Participants
    agent = ParrotAgent("A01")
    user = User("U01")
    
  2. Create and connect platform and dialogue manager

    from dialoguekit.platforms.platform import Platform
    from dialoguekit.manager.dialogue_manager import DialogueManager
    
    platform = Platform()
    dm = DialogueManager(agent, user, platform)
    
    user.connect_dialogue_manager(dm)
    agent.connect_dialogue_manager(dm)
    
  3. Start conversation

      dm.start()
      dm.close()
    

Planned future features

Conventions

We follow the IAI Python Style Guide.

Contributors

(Alphabetically ordered by last name) Jafar Afzali, Krisztian Balog, Aleksander Drzewiecki and Shuo Zhang

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

dialoguekit-0.0.7.tar.gz (709.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

dialoguekit-0.0.7-py3-none-any.whl (736.5 kB view details)

Uploaded Python 3

File details

Details for the file dialoguekit-0.0.7.tar.gz.

File metadata

  • Download URL: dialoguekit-0.0.7.tar.gz
  • Upload date:
  • Size: 709.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.15

File hashes

Hashes for dialoguekit-0.0.7.tar.gz
Algorithm Hash digest
SHA256 807e255d7f3a6d79c99c6ba5b3a94bf9491907603fa890d50e32a7dc9c71f140
MD5 63b061ee53cfc19aeb3a32f6bb7de143
BLAKE2b-256 370999662025aa81ea6a3f5f9841239920473608221f8ab93e263aee0c86b4d3

See more details on using hashes here.

File details

Details for the file dialoguekit-0.0.7-py3-none-any.whl.

File metadata

  • Download URL: dialoguekit-0.0.7-py3-none-any.whl
  • Upload date:
  • Size: 736.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.15

File hashes

Hashes for dialoguekit-0.0.7-py3-none-any.whl
Algorithm Hash digest
SHA256 3e68534a03592f734be8e6b9622e180eb1c364e27d670d6da30f6380d519c842
MD5 8870cc18f22c438f3d024d9e823aa3d2
BLAKE2b-256 213c74083422586d36ae3f41ecfbb9416abb0c4df66f6af60573a0b44a4de2f9

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page