LICENSE
MANIFEST.in
README.md
pyproject.toml
configs/config.yaml
configs/default.yaml
configs/stopwords.txt
src/vecclean/__init__.py
src/vecclean/version.py
src/vecclean.egg-info/PKG-INFO
src/vecclean.egg-info/SOURCES.txt
src/vecclean.egg-info/dependency_links.txt
src/vecclean.egg-info/entry_points.txt
src/vecclean.egg-info/requires.txt
src/vecclean.egg-info/top_level.txt
src/vecclean/api/deps.py
src/vecclean/api/main.py
src/vecclean/api/schemas.py
src/vecclean/chunk/splitter.py
src/vecclean/clean/normalize.py
src/vecclean/cli/__main__.py
src/vecclean/core/config.py
src/vecclean/core/embedding.py
src/vecclean/core/pipeline.py
src/vecclean/core/types.py
src/vecclean/cpp/include/cleaner.hpp
src/vecclean/cpp/src/bindings.cpp
src/vecclean/cpp/src/cleaner.cpp
src/vecclean/dedup/chunk_dedup.py
src/vecclean/dedup/sentence_dedup.py
src/vecclean/ingest/detect.py
src/vecclean/utils/hashing.py
src/vecclean/utils/io.py
src/vecclean/utils/logging.py
src/vecclean/utils/timing.py
tests/test1.py