c1f7b667d1
<!-- .github/pull_request_template.md --> ## Description <!-- Provide a clear description of the changes in this PR --> ## DCO Affirmation I affirm that all code in every commit of this pull request conforms to the terms of the Topoteretes Developer Certificate of Origin <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **Refactor** - Simplified text processing by unifying multiple size-related parameters into a single metric across chunking and extraction functionalities. - Streamlined logic for text segmentation by removing redundant calculations and checks, resulting in a more consistent chunk management process. - **Chores** - Removed the `modal` package as a dependency. - **Documentation** - Updated the README.md to include a new demo video link and clarified default environment variable settings. - Enhanced the CONTRIBUTING.md to improve clarity and engagement for potential contributors. - **Bug Fixes** - Improved handling of sentence-ending punctuation in text processing to include additional characters. - **Version Update** - Updated project version to 0.1.33 in the pyproject.toml file. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| chunk_by_paragraph.py | ||
| chunk_by_sentence.py | ||
| chunk_by_word.py | ||
| remove_disconnected_chunks.py | ||