LICENSE.md
MANIFEST.in
README.md
pyproject.toml
setup.cfg
setup.py
requirements/base.in
requirements/extra-csv.in
requirements/extra-docx.in
requirements/extra-epub.in
requirements/extra-markdown.in
requirements/extra-odt.in
requirements/extra-paddleocr.in
requirements/extra-pandoc.in
requirements/extra-pdf-image.in
requirements/extra-pptx.in
requirements/extra-xlsx.in
requirements/huggingface.in
test_unstructured/__init__.py
test_unstructured/test_utils.py
test_unstructured/unit_utils.py
test_unstructured/chunking/__init__.py
test_unstructured/chunking/test_base.py
test_unstructured/chunking/test_basic.py
test_unstructured/chunking/test_dispatch.py
test_unstructured/chunking/test_html_output.py
test_unstructured/chunking/test_title.py
test_unstructured/cleaners/__init__.py
test_unstructured/cleaners/test_core.py
test_unstructured/cleaners/test_extract.py
test_unstructured/cleaners/test_translate.py
test_unstructured/common/__init__.py
test_unstructured/common/test_html_table.py
test_unstructured/documents/__init__.py
test_unstructured/documents/test_coordinates.py
test_unstructured/documents/test_elements.py
test_unstructured/documents/test_mappings.py
test_unstructured/documents/test_ontology_to_unstructured_parsing.py
test_unstructured/embed/__init__.py
test_unstructured/embed/test_mixedbreadai.py
test_unstructured/embed/test_octoai.py
test_unstructured/embed/test_openai.py
test_unstructured/embed/test_vertexai.py
test_unstructured/embed/test_voyageai.py
test_unstructured/file_utils/__init__.py
test_unstructured/file_utils/test_encoding.py
test_unstructured/file_utils/test_file_conversion.py
test_unstructured/file_utils/test_filetype.py
test_unstructured/file_utils/test_model.py
test_unstructured/metrics/__init__.py
test_unstructured/metrics/test_element_type.py
test_unstructured/metrics/test_evaluate.py
test_unstructured/metrics/test_table_alignment.py
test_unstructured/metrics/test_table_detection_metrics.py
test_unstructured/metrics/test_table_formats.py
test_unstructured/metrics/test_table_structure.py
test_unstructured/metrics/test_text_extraction.py
test_unstructured/metrics/test_utils.py
test_unstructured/nlp/__init__.py
test_unstructured/nlp/mock_nltk.py
test_unstructured/nlp/test_partition.py
test_unstructured/nlp/test_tokenize.py
test_unstructured/partition/__init__.py
test_unstructured/partition/conftest.py
test_unstructured/partition/test_api.py
test_unstructured/partition/test_auto.py
test_unstructured/partition/test_constants.py
test_unstructured/partition/test_csv.py
test_unstructured/partition/test_doc.py
test_unstructured/partition/test_docx.py
test_unstructured/partition/test_email.py
test_unstructured/partition/test_epub.py
test_unstructured/partition/test_json.py
test_unstructured/partition/test_md.py
test_unstructured/partition/test_msg.py
test_unstructured/partition/test_ndjson.py
test_unstructured/partition/test_odt.py
test_unstructured/partition/test_org.py
test_unstructured/partition/test_ppt.py
test_unstructured/partition/test_pptx.py
test_unstructured/partition/test_rst.py
test_unstructured/partition/test_rtf.py
test_unstructured/partition/test_strategies.py
test_unstructured/partition/test_text.py
test_unstructured/partition/test_text_type.py
test_unstructured/partition/test_tsv.py
test_unstructured/partition/test_xlsx.py
test_unstructured/partition/test_xml.py
test_unstructured/partition/common/__init__.py
test_unstructured/partition/common/test_common.py
test_unstructured/partition/common/test_lang.py
test_unstructured/partition/common/test_metadata.py
test_unstructured/partition/html/__init__.py
test_unstructured/partition/html/test_convert.py
test_unstructured/partition/html/test_html_to_ontology_parsing.py
test_unstructured/partition/html/test_html_to_unstructured_and_back_parsing.py
test_unstructured/partition/html/test_html_utils.py
test_unstructured/partition/html/test_parser.py
test_unstructured/partition/html/test_partition.py
test_unstructured/partition/html/test_partition_v2.py
test_unstructured/partition/html/test_unstructured_elements_to_ontology_parsing.py
test_unstructured/partition/pdf_image/__init__.py
test_unstructured/partition/pdf_image/conftest.py
test_unstructured/partition/pdf_image/test_analysis.py
test_unstructured/partition/pdf_image/test_image.py
test_unstructured/partition/pdf_image/test_inference_utils.py
test_unstructured/partition/pdf_image/test_merge_elements.py
test_unstructured/partition/pdf_image/test_ocr.py
test_unstructured/partition/pdf_image/test_pdf.py
test_unstructured/partition/pdf_image/test_pdf_image_utils.py
test_unstructured/partition/pdf_image/test_pdfminer_processing.py
test_unstructured/partition/pdf_image/test_pdfminer_utils.py
test_unstructured/partition/utils/__init__.py
test_unstructured/partition/utils/test_config.py
test_unstructured/partition/utils/test_sorting.py
test_unstructured/partition/utils/test_xycut.py
test_unstructured/staging/__init__.py
test_unstructured/staging/test_base.py
test_unstructured/staging/test_baseplate.py
test_unstructured/staging/test_datasaur.py
test_unstructured/staging/test_huggingface.py
test_unstructured/staging/test_label_box.py
test_unstructured/staging/test_label_studio.py
test_unstructured/staging/test_prodigy.py
test_unstructured/staging/test_weaviate.py
unstructured/__init__.py
unstructured/__version__.py
unstructured/errors.py
unstructured/logger.py
unstructured/py.typed
unstructured/utils.py
unstructured.egg-info/PKG-INFO
unstructured.egg-info/SOURCES.txt
unstructured.egg-info/dependency_links.txt
unstructured.egg-info/requires.txt
unstructured.egg-info/top_level.txt
unstructured/chunking/__init__.py
unstructured/chunking/base.py
unstructured/chunking/basic.py
unstructured/chunking/dispatch.py
unstructured/chunking/title.py
unstructured/cleaners/__init__.py
unstructured/cleaners/core.py
unstructured/cleaners/extract.py
unstructured/cleaners/translate.py
unstructured/common/__init__.py
unstructured/common/html_table.py
unstructured/documents/__init__.py
unstructured/documents/coordinates.py
unstructured/documents/elements.py
unstructured/documents/mappings.py
unstructured/documents/ontology.py
unstructured/embed/__init__.py
unstructured/embed/bedrock.py
unstructured/embed/huggingface.py
unstructured/embed/interfaces.py
unstructured/embed/mixedbreadai.py
unstructured/embed/octoai.py
unstructured/embed/openai.py
unstructured/embed/vertexai.py
unstructured/embed/voyageai.py
unstructured/file_utils/__init__.py
unstructured/file_utils/encoding.py
unstructured/file_utils/file_conversion.py
unstructured/file_utils/filetype.py
unstructured/file_utils/google_filetype.py
unstructured/file_utils/model.py
unstructured/file_utils/ndjson.py
unstructured/metrics/__init__.py
unstructured/metrics/element_type.py
unstructured/metrics/evaluate.py
unstructured/metrics/object_detection.py
unstructured/metrics/table_structure.py
unstructured/metrics/text_extraction.py
unstructured/metrics/utils.py
unstructured/metrics/table/__init__.py
unstructured/metrics/table/table_alignment.py
unstructured/metrics/table/table_eval.py
unstructured/metrics/table/table_extraction.py
unstructured/metrics/table/table_formats.py
unstructured/models/__init__.py
unstructured/nlp/__init__.py
unstructured/nlp/english-words.txt
unstructured/nlp/english_words.py
unstructured/nlp/partition.py
unstructured/nlp/patterns.py
unstructured/nlp/tokenize.py
unstructured/partition/__init__.py
unstructured/partition/api.py
unstructured/partition/auto.py
unstructured/partition/csv.py
unstructured/partition/doc.py
unstructured/partition/docx.py
unstructured/partition/email.py
unstructured/partition/epub.py
unstructured/partition/image.py
unstructured/partition/json.py
unstructured/partition/md.py
unstructured/partition/model_init.py
unstructured/partition/msg.py
unstructured/partition/ndjson.py
unstructured/partition/odt.py
unstructured/partition/org.py
unstructured/partition/pdf.py
unstructured/partition/ppt.py
unstructured/partition/pptx.py
unstructured/partition/rst.py
unstructured/partition/rtf.py
unstructured/partition/strategies.py
unstructured/partition/text.py
unstructured/partition/text_type.py
unstructured/partition/tsv.py
unstructured/partition/xlsx.py
unstructured/partition/xml.py
unstructured/partition/common/__init__.py
unstructured/partition/common/common.py
unstructured/partition/common/lang.py
unstructured/partition/common/metadata.py
unstructured/partition/html/__init__.py
unstructured/partition/html/convert.py
unstructured/partition/html/html_utils.py
unstructured/partition/html/parser.py
unstructured/partition/html/partition.py
unstructured/partition/html/transformations.py
unstructured/partition/pdf_image/__init__.py
unstructured/partition/pdf_image/form_extraction.py
unstructured/partition/pdf_image/inference_utils.py
unstructured/partition/pdf_image/ocr.py
unstructured/partition/pdf_image/pdf_image_utils.py
unstructured/partition/pdf_image/pdfminer_processing.py
unstructured/partition/pdf_image/pdfminer_utils.py
unstructured/partition/pdf_image/pypdf_utils.py
unstructured/partition/pdf_image/analysis/__init__.py
unstructured/partition/pdf_image/analysis/bbox_visualisation.py
unstructured/partition/pdf_image/analysis/layout_dump.py
unstructured/partition/pdf_image/analysis/processor.py
unstructured/partition/pdf_image/analysis/tools.py
unstructured/partition/utils/__init__.py
unstructured/partition/utils/config.py
unstructured/partition/utils/constants.py
unstructured/partition/utils/sorting.py
unstructured/partition/utils/xycut.py
unstructured/partition/utils/ocr_models/__init__.py
unstructured/partition/utils/ocr_models/google_vision_ocr.py
unstructured/partition/utils/ocr_models/ocr_interface.py
unstructured/partition/utils/ocr_models/paddle_ocr.py
unstructured/partition/utils/ocr_models/tesseract_ocr.py
unstructured/patches/__init__.py
unstructured/patches/pdfminer.py
unstructured/staging/__init__.py
unstructured/staging/argilla.py
unstructured/staging/base.py
unstructured/staging/baseplate.py
unstructured/staging/datasaur.py
unstructured/staging/huggingface.py
unstructured/staging/label_box.py
unstructured/staging/label_studio.py
unstructured/staging/prodigy.py
unstructured/staging/weaviate.py