Sizing Context Data (Stuffing the Prompt) LastMaxTokenSizeContentPurger #2568
jasonparallel
started this conversation in
General
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
What is the plan for sizing context data to meet the token window?
I see LastMaxTokenSizeContentPurger was added in M1 but it does not appear to be used (or mentioned in the docs).
Any plans to shorten documents vs excluding documents? The functionality I wrote before noticing spring-ai utilizes a sentence detector to shorten documents by whole sentences.
Beta Was this translation helpful? Give feedback.
All reactions