Repository navigation
fix: 분할 조각 예산을 최종 EU 텍스트 기준으로 계산 Fixes #33 - #37
Merged
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
문제
행 단위로 분할한 조각의 최종
text가 한도(512)를 넘었다. 측정값[803, 179].Linux/Python 3.12와 Windows/Python 3.14.5에서 같은 수치가 나와 플랫폼 문제가 아니다.
split.py::estimate_chunk_tokens가 캡션 + 표 HTML + 각주만 세고, 모든 조각에 복제되는 섹션 헤더·table_abstract·문맥 단락·평탄화 셀 문장을 예산에서 뺐다. 샘플 EU 기준 최종text2,821자 중 1,255자(45%)가 추정에서 누락됐다.변경
count_eu_tokens()로 최종 텍스트 전체를 세도록 예산 계산 변경llm_summary로 분기검증
환경: Windows 11 / Python 3.14.5, docling 미설치 경량 구성
tests/specification/test_spec_split.py11건 전원 통과. 남은 실패는qa15(GAP-02, #34 ).영향
분할 조각 수가 늘어나므로 Recall@1 수치가 달라진다. 벤치마크 재측정은 추후 수행한다.
Fixes #33