| .. |
|
__init__.py
|
bd9279198c
refactor: rename init file and update app.py to enable parsing method
|
5 months ago |
|
block_pre_proc.py
|
236a6033f1
refactor: improve block processing logic and enhance span handling
|
5 months ago |
|
block_sort.py
|
284cec041a
refactor: replace get_file_from_repos with auto_download_and_get_model_root_path in multiple files
|
5 months ago |
|
boxbase.py
|
236a6033f1
refactor: improve block processing logic and enhance span handling
|
5 months ago |
|
config_reader.py
|
bd5252d946
fix: add conditional import for torch and torch_npu in config_reader.py
|
5 months ago |
|
cut_image.py
|
38ace5dc61
refactor: streamline document analysis and enhance image handling in processing pipeline
|
5 months ago |
|
draw_bbox.py
|
41ecaedc0c
feat: disable logging for invalid overlay PDF generation in draw_bbox.py
|
5 months ago |
|
enum_class.py
|
58b8e8a912
fix: add new enum values and improve MIN_BATCH_INFERENCE_SIZE documentation in pipeline_analyze.py
|
5 months ago |
|
format_utils.py
|
0031981e60
Fix otsl to html conversion
|
5 months ago |
|
hash_utils.py
|
cbba27b4f5
refactor: reorganize project structure and update import paths
|
5 months ago |
|
language.py
|
8f1f9abec5
refactor: enhance bounding box utilities and add configuration reader for S3 integration
|
5 months ago |
|
llm_aided.py
|
35cb414f1c
feat: integrate LLM optimization for title enhancement in PDF processing
|
4 months ago |
|
model_utils.py
|
d58b24b5dd
fix: add conditional imports for torch and torch_npu in model_utils.py
|
5 months ago |
|
models_download_utils.py
|
fa9aaaa7b7
fix: update model path handling in model.py and models_download_utils.py
|
5 months ago |
|
ocr_utils.py
|
962a3453ca
fix: adjust OCR confidence threshold and refine category assignment logic
|
4 months ago |
|
pdf_classify.py
|
84fa04e22d
feat: enhance PDF image coverage analysis with improved parsing and coverage calculation
|
5 months ago |
|
pdf_image_tools.py
|
38ace5dc61
refactor: streamline document analysis and enhance image handling in processing pipeline
|
5 months ago |
|
pdf_reader.py
|
4243b0eaed
refactor: increase YOLO layout base batch size and improve progress tracking in predictions
|
4 months ago |
|
pdf_text_tool.py
|
1ed61cb5d6
refactor: update OCR span extraction logic and improve PDF page processing
|
5 months ago |
|
run_async.py
|
8e55a52693
feat: add mineru-vlm backend.
|
5 months ago |
|
span_block_fix.py
|
f211554137
refactor: improve text processing by adding ligature and unicode replacement functions
|
5 months ago |
|
span_pre_proc.py
|
a3ae57bf20
refactor: streamline text span extraction and remove unused functions
|
5 months ago |
myhloli
35cb414f1c
feat: integrate LLM optimization for title enhancement in PDF processing