Bug Fix: Reranker Chunk Overlap and CHUNK_SIZE Exceedance#645
Open
hoperun300339 wants to merge 2 commits intonetease-youdao:qanything-v2from
Open
Bug Fix: Reranker Chunk Overlap and CHUNK_SIZE Exceedance#645hoperun300339 wants to merge 2 commits intonetease-youdao:qanything-v2from
hoperun300339 wants to merge 2 commits intonetease-youdao:qanything-v2from
Conversation
Fixed an issue where the reranker would exceed the predefined CHUNK_SIZE, which also negatively impacted reranking precision. The root cause was the separate_list function, which groups adjacent chunks based on their proximity in the original document. In cases where the document is small or adjacent chunks are close together, the grouping logic caused overlap between chunk groups. This resulted in individual chunk sets interfering with each other and the total length of a group exceeding the intended CHUNK_SIZE.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixed an issue where the reranker would exceed the predefined CHUNK_SIZE, which also negatively impacted reranking precision. The root cause was the separate_list function, which groups adjacent chunks based on their proximity in the original document. In cases where the document is small or adjacent chunks are close together, the grouping logic caused overlap between chunk groups. This resulted in individual chunk sets interfering with each other and the total length of a group exceeding the intended CHUNK_SIZE.