xzc/pdf_title_image @ c189ec226b545607f6a51cf2d5c789824af2dac2

Aucune description

sprivacy c189ec226b First commit		il y a 1 an
extracted_images	76f6e51fc3 version 0.1	il y a 1 an
LLMAgent.py	9365b80daa 08/08/2024 16:12:52	il y a 1 an
README.md	65241d1460 添加评审因素段落定位	il y a 1 an
all_tables.json	a2eeab68b2 添加全量表格解析模块，表格新增表名识别，新增大纲识别	il y a 1 an
document_.py	0152861ab0 08/08/2024 17:19:21	il y a 1 an
extract_financial_report.py	c189ec226b First commit	il y a 1 an
extract_price.py	c189ec226b First commit	il y a 1 an
get_info.py	c189ec226b First commit	il y a 1 an
instance_locate.py	c189ec226b First commit	il y a 1 an
lmu.py	59d20e64a0 添加BMP图形保存，添加摘要生成、关键词检测	il y a 1 an
matcher.py	65241d1460 添加评审因素段落定位	il y a 1 an
ocr_api.py	c189ec226b First commit	il y a 1 an
requirements.txt	7e37b38fec extract content with outlines	il y a 1 an
responser.py	ee3755c347 add j2k picture extract	il y a 1 an
scan_dir.py	c189ec226b First commit	il y a 1 an
text_extractor.py	c189ec226b First commit	il y a 1 an
tools.py	ace5c2b4fb add requirements	il y a 1 an

主要模块描述 1、tools 大纲解析模块 2、get_info PDF信息抽取模块 3、matcher 段落定位模块