Json streaming POC (WIP) #346
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is a simple POC of how we could implement streaming output for our chat messages. This is a highly desirable feature and almost all AI inference endpoints support it.
Since we deal exclusively in formatted JSON messages, it's a little tricky to extract the partially completed JSON keys/values before they are done (e.g. printing half of a deep string that's not even terminated).
This POC shows how we can do it using https://www.npmjs.com/package/@streamparser/json-whatwg. Example parse is included.
Not to be merged, this is just a hack for now.