openedx / openedx/openedx-ai-extensions
Run a manual deep test of workflows using a gemini provider
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17
- Forks
- 11
- Avg merge
- 5h 33m
- Merged PRs (30d)
- 4
Description
So far, most of the development has tested openAI and anthropic models. We made sure that this works with open weight models, but hosting those at large scale has proven to be a limitation.
Right now there is interest from instances that are operating and have contracts with google. We would like to test some of the some, or all, of the workflows using Gemini as provider to make sure that there are not incompatibilities that we are not aware of.
In case there are incompatibilities, we must report them here, and this issue doesn't necessarily mean that they need to get fixed by the reporter.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names no files, tests, or workflow entry points. First identify the workflows and Gemini provider setup covered by the project, then run the corresponding manual checks. Done means recording any Gemini incompatibilities in this issue, including cases where no incompatibility is found.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, testing-qa
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100