myhloli 236a6033f1 refactor: improve block processing logic and enhance span handling пре 5 месеци
..
__init__.py bd9279198c refactor: rename init file and update app.py to enable parsing method пре 6 месеци
block_pre_proc.py 236a6033f1 refactor: improve block processing logic and enhance span handling пре 5 месеци
block_sort.py 0f21495a06 refactor: enhance block processing and sorting utilities for improved span management пре 6 месеци
boxbase.py 236a6033f1 refactor: improve block processing logic and enhance span handling пре 5 месеци
cut_image.py 38ace5dc61 refactor: streamline document analysis and enhance image handling in processing pipeline пре 5 месеци
draw_bbox.py 0a899f1af8 feat: add batch processing for OCR detection and implement new client and common utilities пре 6 месеци
enum_class.py 8f1f9abec5 refactor: enhance bounding box utilities and add configuration reader for S3 integration пре 6 месеци
hash_utils.py cbba27b4f5 refactor: reorganize project structure and update import paths пре 6 месеци
language.py 8f1f9abec5 refactor: enhance bounding box utilities and add configuration reader for S3 integration пре 6 месеци
llm_aided.py 7d4ce0c380 refactor: add LLM-aided title optimization and improve config handling пре 5 месеци
model_utils.py 101b12a10a refactor: improve image handling by transitioning from NumPy arrays to PIL images in cropping functions пре 5 месеци
ocr_utils.py cbba27b4f5 refactor: reorganize project structure and update import paths пре 6 месеци
pdf_classify.py ea5cb65a1f refactor: enhance document parsing by supporting multiple PDF files and improving method organization пре 6 месеци
pdf_image_tools.py 38ace5dc61 refactor: streamline document analysis and enhance image handling in processing pipeline пре 5 месеци
pdf_reader.py 8e55a52693 feat: add mineru-vlm backend. пре 6 месеци
pdf_text_tool.py 1ed61cb5d6 refactor: update OCR span extraction logic and improve PDF page processing пре 5 месеци
pipeline_magic_model.py 236a6033f1 refactor: improve block processing logic and enhance span handling пре 5 месеци
run_async.py 8e55a52693 feat: add mineru-vlm backend. пре 6 месеци
span_block_fix.py f211554137 refactor: improve text processing by adding ligature and unicode replacement functions пре 5 месеци
span_pre_proc.py d2de6d801a refactor: update text span extraction to use new version and improve character handling пре 5 месеци
vlm_magic_model.py 6f2c3ad89e refactor: enhance title block processing and improve markdown generation пре 5 месеци