refactor(memory): replace truncation with parallel chunked extraction#111
Closed
shivamvishwakarm wants to merge 2 commits into
Closed
refactor(memory): replace truncation with parallel chunked extraction#111shivamvishwakarm wants to merge 2 commits into
shivamvishwakarm wants to merge 2 commits into
Conversation
Contributor
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem:
Currently we're using hard truncate for memory. If it's exclude certain number of character count. So, are directly ignoring all the content after that max boundary. So that problem with this approach is may be the relevant part of memory in the last so ignoring that would half memory and stale memory/wrong memory.
Soln:
Replace hard truncation with a sliding-window chunker that processes all content in parallel and merges deduplicated results. Adds sentence-boundary snapping and overlap to avoid losing context at seams.