Skip to main content

AI tutor for education

Project description

Heymans AI tutor

Copyright 2024-2026 Sebastiaan Mathôt (@smathot), Wouter Kruijne (@wkruijne), University of Groningen

Heymans AI tutor is a Python library and web app for LLM-based teaching tools. The initial focus will be on automated grading of open exams and interactive quizzes.

This software is in early stages of development and not ready for production.

Dependencies

For Python dependencies, see pyproject.toml. Python 3.10 or later is required. In addition to these, a local redis server needs to run for persistent data between sessions. pandoc needs to be installed for generating invidual feedback reports.

Using as Python library

See example/heymans-brightspace-example.py for an example of how to grade an open-ended exam. This example assumes that you're using the Brightspace learning environment. The example folder also contains example output that is generated during grading.

Running as web server (development)

Download the source code, and in the folder of the source code execute the following:

pip install .               # install dependencies
python app.py               # start the app

Next, access the app (by default) through:

http://127.0.0.1:5000/app/quiz

License

Heymans is distributed under the terms of the GNU General Public License 3. The full license should be included in the file COPYING, or can be obtained from:

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

heymans-0.5.0.tar.gz (181.1 kB view details)

Uploaded Source

Built Distribution

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

heymans-0.5.0-py3-none-any.whl (205.5 kB view details)

Uploaded Python 3

File details

Details for the file heymans-0.5.0.tar.gz.

File metadata

  • Download URL: heymans-0.5.0.tar.gz
  • Upload date:
  • Size: 181.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.25

File hashes

Hashes for heymans-0.5.0.tar.gz
Algorithm Hash digest
SHA256 689aab8fb58a53caca234d9e2e2338de53d4aa2e244b0c11239c81af7874b236
MD5 273bf2fa7db05f2566eec3f79f59bcc3
BLAKE2b-256 35d30f4b6828c9f4948eda80cb9056a8b57b733697f611a884b9673d8e888ec2

See more details on using hashes here.

File details

Details for the file heymans-0.5.0-py3-none-any.whl.

File metadata

  • Download URL: heymans-0.5.0-py3-none-any.whl
  • Upload date:
  • Size: 205.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.25

File hashes

Hashes for heymans-0.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2e16845ac554fbd994f717b9616e7ce88b7ccc7ce55bc3066f026a2cdf2d8c66
MD5 29ef84e4493d8d39e6597d8cddd08576
BLAKE2b-256 8ea9f5aa016d4c8841de941a4b42d439004605340488e28ab8d2a1bdf1aba600

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