Skip to main content

A marker that will use tests to run a cpp program and mark it based on the output. It will use the openAI api and LLMs to help process the output.

Project description

What

This is a test of creating an AI marker for first year programming assignments.

The parituclar assignment example is a simple converter that takes in either binary or decimal numbers and converts them to the other.

Why

In later papers using unit testing frameworks and giving out grades based on this can be done sucsessfully as the students are more confident with programming and can handle having to write a program with exact output. However in first year the focus is still on programming itself and so the challenge of the assignment is with the logic of the program and not the exact format of the output (Unless that is part of the logic!).

This would mean that for example the program could output "Converting binary to decimal answer is 10" or "Converting to decimal: 10" and both would be completely acceptable.

How

The goal of the AI marker is to be able to take in a set of test cases and then run the students program against various unit tests however the grading and marking of these unit tests will be done with a LLMs.

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

ai_assignment_marker-0.1.0.tar.gz (2.4 kB view details)

Uploaded Source

Built Distribution

ai_assignment_marker-0.1.0-py3-none-any.whl (3.6 kB view details)

Uploaded Python 3

File details

Details for the file ai_assignment_marker-0.1.0.tar.gz.

File metadata

  • Download URL: ai_assignment_marker-0.1.0.tar.gz
  • Upload date:
  • Size: 2.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.11.4 Windows/10

File hashes

Hashes for ai_assignment_marker-0.1.0.tar.gz
Algorithm Hash digest
SHA256 dd503c62b6f8bbfe389d629b748cc74e848a04b946b6d5c01120e1ad65a26b60
MD5 042f02b5ebcba8edefadc3b8d23480fd
BLAKE2b-256 9de35398a325eb46a50b0fa0a98a8d045b8586ae4bae542b05964c75aa45f4ad

See more details on using hashes here.

File details

Details for the file ai_assignment_marker-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for ai_assignment_marker-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 1c80a28ff470f7a9a23f1155b13b741beefa637727fd626b47a4ccec18372f04
MD5 f7060fa24085f894d5a91a6f9f4f659b
BLAKE2b-256 9c7112dfcb897011838b32962df0e4e69775be77d99a6626f7bbda196a753f19

See more details on using hashes here.

Supported by

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