GH-2123: Add chunkOverlap support to TokenTextSplitter #4054
Conversation
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
Fixes spring-projectsGH-2123 (spring-projects#2123) - Add chunkOverlap field and configuration to TokenTextSplitter class - Implement overlap functionality in doSplit method with boundary optimization - Add optimizeChunkBoundary method for sentence-aware chunk splitting - Add validation to ensure chunkOverlap < chunkSize - Update Builder pattern with withChunkOverlap method - Add comprehensive test coverage for overlap functionality - Improve existing tests to handle dynamic chunk counts Signed-off-by: Seunghwan Jung <[email protected]> Signed-off-by: Seunghwan Jung <[email protected]>
ralla0405
force-pushed
the
GH-2123-add-overlap-field-to-splitter
branch
from
e584def to
f073fff
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Summary
This PR adds chunk overlap functionality to the
TokenTextSplitterclass toimprove text chunking for better context preservation in document processing.
Closes #2123
Changes
TokenTextSplitter class enhancements:
chunkOverlapfield with default value of 50 tokenschunkOverlap < chunkSizedoSplitmethod to implement overlap logicoptimizeChunkBoundarymethod for sentence-aware splittingTest improvements:
testChunkOverlapFunctionalityto verify overlap behaviortestChunkOverlapValidationfor input validationtestBoundaryOptimizationWithOverlapfor sentence boundary testingtestKeepSeparatorVariationsfor separator handlingKey Features
chunks
possible
Test Coverage
All new functionality is covered by comprehensive unit tests that verify: