Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

ResponseTooLong Error #2

Open
iankabujiya opened this issue Jan 9, 2024 · 1 comment
Open

ResponseTooLong Error #2

iankabujiya opened this issue Jan 9, 2024 · 1 comment
Assignees
@iankabujiya

Comments

@iankabujiya
Copy link
Collaborator

Occasionally, the library will return a longer response on the /search endpoint, which causes OpenAI to throw a ResponseTooLong error. Likely need to need to post-process JSON according to length restrictions of GPT function calling before returning to the calling model.
@iankabujiya iankabujiya self-assigned this Jan 10, 2024
@iankabujiya
Copy link
Collaborator Author

Update: this is big challenging to get right w/o regression (since the API isn't always accurate on paging + shortening context degrades answer quality). Still looking at solutions.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@iankabujiya iankabujiya

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@iankabujiya