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-0.4.1.tar.gz (179.1 kB view details)

Uploaded Source

Built Distribution

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

heymans-0.4.1-py3-none-any.whl (203.3 kB view details)

Uploaded Python 3

File details

Details for the file heymans-0.4.1.tar.gz.

File metadata

  • Download URL: heymans-0.4.1.tar.gz
  • Upload date:
  • Size: 179.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.25

File hashes

Hashes for heymans-0.4.1.tar.gz
Algorithm Hash digest
SHA256 323ec244e3259c2432b129ecaf0b225432e163c9a418b113ad2e1f1256c2045e
MD5 b4983dce1d35127f28d97ab8a61bbf26
BLAKE2b-256 00625ae7b1b1f054dd7c44aa99869922c2911a5c88ad2e07de92ea618c7f38d7

See more details on using hashes here.

File details

Details for the file heymans-0.4.1-py3-none-any.whl.

File metadata

  • Download URL: heymans-0.4.1-py3-none-any.whl
  • Upload date:
  • Size: 203.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.25

File hashes

Hashes for heymans-0.4.1-py3-none-any.whl
Algorithm Hash digest
SHA256 ab70f5b0e0dfe386108505d475f79b6e3510e349bef42592f03c68933db0902e
MD5 0ab361c13e147eced79bb3f414d966b7
BLAKE2b-256 e801ad0c2821b8268c058376888198a3ef21eea92f4bb26218cd51fd694b97ca

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