LICENSE
README.md
pyproject.toml
src/structured_data_extraction/__init__.py
src/structured_data_extraction/classify.py
src/structured_data_extraction/config.py
src/structured_data_extraction/convert.py
src/structured_data_extraction/embed.py
src/structured_data_extraction/extract.py
src/structured_data_extraction/features.py
src/structured_data_extraction/filter_records.py
src/structured_data_extraction/main.py
src/structured_data_extraction/matching.py
src/structured_data_extraction/paths.py
src/structured_data_extraction/rater.py
src/structured_data_extraction/records.py
src/structured_data_extraction/search.py
src/structured_data_extraction/tables.py
src/structured_data_extraction/vocab.py
src/structured_data_extraction.egg-info/PKG-INFO
src/structured_data_extraction.egg-info/SOURCES.txt
src/structured_data_extraction.egg-info/dependency_links.txt
src/structured_data_extraction.egg-info/entry_points.txt
src/structured_data_extraction.egg-info/requires.txt
src/structured_data_extraction.egg-info/top_level.txt
src/structured_data_extraction/models/section_classifier/docling_cats.joblib
src/structured_data_extraction/models/section_classifier/rf_classifier.joblib
src/structured_data_extraction/models/section_classifier/tfidf_char_vectorizer.joblib
src/structured_data_extraction/models/section_classifier/tfidf_vectorizer.joblib
src/structured_data_extraction/templates/extraction.j2
src/structured_data_extraction/templates/schema_discovery.j2
tests/test_convert.py
tests/test_embed.py
tests/test_extract.py
tests/test_features.py
tests/test_matching.py
tests/test_rater.py
tests/test_records.py
tests/test_search.py
tests/test_tables.py