myhloli c660fdc8f0 feat(llm): add LLM-aided formula and text correction ...

- Add LLM-aided formula and text correction functionality
- Update config reader to include LLM-aided settings
- Create new LLM-aided processing module
- Update main processing script to incorporate LLM-aided corrections
- Modify download scripts to check for new config version

2024-12-24 14:33:35 +08:00

..

config

fix: 1. ocr txt mode error 2. lose pdf_parse_type field

2024-12-07 18:03:39 +08:00

data

docs: check links in doc

2024-12-11 16:56:25 +08:00

dict2md

feat(llm): add LLM-aided formula and text correction

2024-12-24 14:33:35 +08:00

filter

refactor(magic_pdf): switch to pdfminer for invalid character detection

2024-12-11 01:41:35 +08:00

integrations

refactor: move some constants or enums defs to config folder

2024-11-19 16:56:53 +08:00

libs

feat(llm): add LLM-aided formula and text correction

2024-12-24 14:33:35 +08:00

model

perf(layout): optimize layout detection for PDF extraction

2024-12-12 12:10:05 +08:00

pipe

docs: add dataset method description

2024-12-03 14:06:58 +08:00

post_proc

feat(llm): add LLM-aided formula and text correction

2024-12-24 14:33:35 +08:00

pre_proc

fix(pre_proc): prevent errors when imageWriter is None

2024-12-02 11:20:49 +08:00

resources

feat(table): integrate RapidTable model for table recognition

2024-11-08 18:26:00 +08:00

rw

refactor(libs): remove unused imports and functions

2024-11-27 14:51:30 +08:00

spark

refactor: move some constants or enums defs to config folder

2024-11-19 16:56:53 +08:00

tools

fix: classif pdf type

2024-12-11 19:50:35 +08:00

utils

feat: support convert ppt/pptx/doc/docx

2024-12-11 16:56:25 +08:00

__init__.py

目录重构

2024-03-01 16:07:51 +08:00

pdf_parse_by_ocr.py

refactor: isolate inference and pipeline

2024-12-03 14:06:58 +08:00

pdf_parse_by_txt.py

refactor: isolate inference and pipeline

2024-12-03 14:06:58 +08:00

pdf_parse_union_core_v2.py

feat(llm): add LLM-aided formula and text correction

2024-12-24 14:33:35 +08:00

user_api.py

fix: 1. ocr txt mode error 2. lose pdf_parse_type field

2024-12-07 18:03:39 +08:00