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

Support infinitely recursive summarization #2

Open
jrodal98 opened this issue May 27, 2023 · 0 comments
Open

Support infinitely recursive summarization #2

jrodal98 opened this issue May 27, 2023 · 0 comments
Assignees
@jrodal98
Labels
enhancement New feature or request

Comments

@jrodal98
Copy link
Owner

Currently, the text chunk sizes and maximum tokens in a response are hardcoded, meaning...

  • Requests aren't optimized to use the maximum allowed tokens per model
  • Only a maximum of 120,000 characters can be used as input

I can explore using tiktoken to calculate tokens prior to submitting requests, which would allow for more intelligent batching and recursive summarization
@jrodal98 jrodal98 added the enhancement New feature or request label May 27, 2023
@jrodal98 jrodal98 self-assigned this May 27, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@jrodal98 jrodal98

Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@jrodal98