Deduplicate RAG chunks across embedding batches - #4
Merged
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Soundcreates
marked this pull request as ready for review
October 2, 2026 15:09
This branch was successfully deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Change
Deduplicate normalized document content across Chroma ingestion batches while bounding the cross-batch fingerprint set.
Verification
tracemallocpeak was 9.55 MiB of traced auxiliary allocation, excluding the preloaded input corpus.The benchmark uses a fake vector collection and prebuilt input documents; it measures deduplication-path allocations and submissions, not real embedding/network latency or production OOM rates. Beyond the signature cap, deduplication remains batch-local.