Fix SemanticDoubleMergingSplitter stopword cleanup#22168
Open
fengjikui wants to merge 1 commit into
Open
Conversation
dosubot
Bot
added
the
size:XS
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
_clean_text_advancedlowercases and removes punctuationSemanticDoubleMergingSplitterNodeParsercleaned textRoot cause
_clean_text_advancedstripped punctuation before calling the Punkt sentence tokenizer. With no sentence-boundary punctuation left, Punkt returned the whole text as one token, so individual stopwords were never compared or removed.Fixes #22166.
Validation
uv run --project llama-index-core python - <<'PY' ...reproduced the issue before the fix: output still contained stopwords and the assertion faileduv run --project llama-index-core python - <<'PY' ...after the fix: outputtest text containing stopwords likeuv run --project llama-index-core pytest llama-index-core/tests/node_parser/test_semantic_double_merging_splitter.py -q->4 passed, 6 skippeduv run --project llama-index-core ruff check llama-index-core/llama_index/core/node_parser/text/semantic_double_merging_splitter.py llama-index-core/tests/node_parser/test_semantic_double_merging_splitter.pyuv run --project llama-index-core ruff format --check llama-index-core/llama_index/core/node_parser/text/semantic_double_merging_splitter.py llama-index-core/tests/node_parser/test_semantic_double_merging_splitter.pyAI assistance was used to identify and draft this small fix; I reviewed the code path and verified it locally.