myhloli d3b3ea0fa4 fix: simplify path construction in models_download_utils.py 5 сар өмнө
..
__init__.py bd9279198c refactor: rename init file and update app.py to enable parsing method 6 сар өмнө
block_pre_proc.py 236a6033f1 refactor: improve block processing logic and enhance span handling 6 сар өмнө
block_sort.py 284cec041a refactor: replace get_file_from_repos with auto_download_and_get_model_root_path in multiple files 5 сар өмнө
boxbase.py 236a6033f1 refactor: improve block processing logic and enhance span handling 6 сар өмнө
config_reader.py 7eed5ee9c8 refactor: streamline PDF parsing and enhance formula recognition handling 5 сар өмнө
cut_image.py 38ace5dc61 refactor: streamline document analysis and enhance image handling in processing pipeline 6 сар өмнө
draw_bbox.py 57f44dd8ac refactor: update PDF library import from PyPDF2 to pypdf 5 сар өмнө
enum_class.py 4eaa85fd31 refactor: update make mode constants to improve content list handling 5 сар өмнө
format_utils.py 15dd9a0ff1 refactor: reorganize config_reader imports and enhance format utilities 5 сар өмнө
hash_utils.py cbba27b4f5 refactor: reorganize project structure and update import paths 6 сар өмнө
language.py 8f1f9abec5 refactor: enhance bounding box utilities and add configuration reader for S3 integration 6 сар өмнө
llm_aided.py c18934a339 refactor: improve dictionary formatting in output structure 6 сар өмнө
model_utils.py 101b12a10a refactor: improve image handling by transitioning from NumPy arrays to PIL images in cropping functions 6 сар өмнө
models_download_utils.py d3b3ea0fa4 fix: simplify path construction in models_download_utils.py 5 сар өмнө
ocr_utils.py cbba27b4f5 refactor: reorganize project structure and update import paths 6 сар өмнө
pdf_classify.py c01b780bc5 refactor: enhance PDF classification logic and improve resource management 5 сар өмнө
pdf_image_tools.py 38ace5dc61 refactor: streamline document analysis and enhance image handling in processing pipeline 6 сар өмнө
pdf_reader.py 8e55a52693 feat: add mineru-vlm backend. 6 сар өмнө
pdf_text_tool.py 1ed61cb5d6 refactor: update OCR span extraction logic and improve PDF page processing 6 сар өмнө
run_async.py 8e55a52693 feat: add mineru-vlm backend. 6 сар өмнө
span_block_fix.py f211554137 refactor: improve text processing by adding ligature and unicode replacement functions 6 сар өмнө
span_pre_proc.py a3ae57bf20 refactor: streamline text span extraction and remove unused functions 6 сар өмнө