Improve XML chunking algorithm implementation#5
Merged
martgra merged 1 commit intoNov 20, 2025
Conversation
Major improvements: - Target chunk size of 512 tokens (optimized for RAG) vs 6800 previously - 15% overlap between chunks for better context preservation - Better structure preservation (lists, continuations, leddfortsettelse) - Hierarchical context extraction (walks up XML tree for chapter/section info) - Cross-reference extraction for graph-based retrieval - Direct XML-to-chunks processing (removed intermediate parsing step) Technical changes: - Added new LovdataChunker class with three-tier fallback strategy - Updated ChunkingService to use new chunker with chunk_file() API - Simplified FileProcessingService by removing XMLParsingService dependency - Updated pipeline factory with new chunking parameters - Marked old components as deprecated (xml_chunker, recursive_splitter, xml_parsing_service) - Updated integration tests to use new API The new algorithm provides more granular chunking at the ledd (legal paragraph) level with proper handling of complex structures like lists and nested content.
martgra
deleted the
claude/improve-xml-chunking-01AQutrcEUg2M2qv34a66azt
branch
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Major improvements:
Technical changes:
The new algorithm provides more granular chunking at the ledd (legal paragraph) level with proper handling of complex structures like lists and nested content.