LAION-AI / LAION-AI/Open-Assistant
Message Drafts Additional Feature Tracking
Open
Nobody has claimed this yet.
inference
- Dominant language
- Python
- Stars
- 37.4k
- Forks
- 3.3k
- PR merge metrics
- No merged PRs in 30d
Description
This is an issue for tracking a few additional features which should be added for message drafts
- Disable all messages drafts under high load (requires fixing inaccurate queue first #2822 )
- Add toggle so users can choose to generate drafts when they feel fit instead of only on a message regeneration (should add disable under load first)
-
Make sure message evaluations are removed when a chat is deleted. -
If the user opts-out of data collection, simply don't generate drafts as they are primarily for collecting data.
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
Start by reviewing issue #2822, which is listed as a prerequisite for disabling drafts under high load. Then determine the implementation entry points and tests for message drafts; completion requires resolving the remaining unchecked requirements and confirming the existing checked behaviors remain intact.
Written by the indexing model from the issue text.
Assessment
- Domain
- backend
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100