AI Assistant: Stream response to avoid the user waiting too much for some reply
Open
Nobody has claimed this yet.
- Dominant language
- Elixir
- Stars
- 296
- Forks
- 86
- Avg merge
- 1d 13h
- Merged PRs (30d)
- 50
Description
User story
As a continuation of the matter raised on #3009 we should stream the LLM response to show sooner to the user that the full reply is in progress, just like the LLMs do when used directly.
Details
TBD
Implementation notes
Release notes
User acceptance criteria
Contributor guide
No contributing guide indexed for this repository
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 reading the related discussion in issue #3009 and locating the AI Assistant response entry point in the Elixir application. Define the streaming behavior and acceptance criteria with maintainers; the work is done when users see the LLM reply incrementally rather than waiting for the complete response.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- elixir
- Domain
- ai, backend
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100