Page MenuHomePhabricator

Commons app GSoC 2025: Improve the app using AI and especially embedded LLMs
Closed, InvalidPublic

Description

Brief summary

The Commons app is an open source Android app that allows anyone to upload pictures to Wikimedia Commons (the image repository used by Wikipedia, Wikinews and other projects).

The goal of this GSoC is to improve the app using AI and especially embedded LLMs:

  1. Implement a helper app to crowdsource AICore testing
  2. Use caption to suggest depictions
  3. Detect wrongly-set caption language
  4. Add illustrations to the warning pop-ups
  5. Brainstorm and find other areas where AI/LLMs can really improve the quality of pictures/metadata the user uploads to Commons, then implement them. If none, implement phases 1 and 2 of Nearby notable things from OpenStreetMap instead.

Skills required

  • Kotlin or Java
  • Android development

Experience with AI/ML/LLMs is NOT required.

Mentors

Microtasks

Please read gsoc.md which guides you on how to choose an issue and perform a microtask.

Size

Project size: 350 hours
Difficulty: Intermediate

Event Timeline

Nicolas_Raoul renamed this task from Commons app GSoC 2025: Improve the app using AI and especially embedded LLM to Commons app GSoC 2025: Improve the app using AI and especially embedded LLMs.Jan 17 2025, 4:48 AM
Nicolas_Raoul renamed this task from Commons app GSoC 2025: Improve the app using AI and especially embedded LLMs to Commons app GSoC 2026: Improve the app using AI and especially embedded LLMs.Mar 6 2025, 12:47 PM

Please make sure the Commons community was consulted about these proposed uses before implementing. Wikimedia communities tend to be extremely skeptical of proposed uses of AI.

Nicolas_Raoul renamed this task from Commons app GSoC 2026: Improve the app using AI and especially embedded LLMs to Commons app GSoC 2025: Improve the app using AI and especially embedded LLMs.Jan 20 2026, 7:59 AM

Closing as this was for 2025.

2026 task is here: https://phabricator.wikimedia.org/T414881