 myhloli
|
e76f29639f
fix: improve text block detection logic by simplifying overlap checks
|
3 месяцев назад |
|
myhloli
|
0b8a9d51e1
feat: add content field to interline equation block in model_json_to_middle_json.py
|
4 месяцев назад |
|
myhloli
|
f2666385b6
refactor: remove unused title merging logic in model_json_to_middle_json.py
|
4 месяцев назад |
|
myhloli
|
f41fc406c3
fix: enhance memory cleaning condition to check model list length
|
4 месяцев назад |
|
myhloli
|
db4edf289f
fix: enhance memory cleaning condition to check model list length
|
4 месяцев назад |
|
myhloli
|
12b64a0e46
fix: conditionally clean memory based on environment variable
|
4 месяцев назад |
|
myhloli
|
4e2a562231
fix: simplify formula enable handling by removing redundant function call
|
5 месяцев назад |
|
myhloli
|
1383787bad
fix: refactor formula and table enable handling to use environment variables
|
5 месяцев назад |
|
myhloli
|
be99753f58
feat: add progress bar to page processing in result_to_middle_json function
|
5 месяцев назад |
|
myhloli
|
59d8f105e5
feat: introduce OcrConfidence class and update confidence threshold checks in OCR processing
|
5 месяцев назад |
|
myhloli
|
7eed5ee9c8
refactor: streamline PDF parsing and enhance formula recognition handling
|
5 месяцев назад |
|
myhloli
|
29d262618a
refactor: add method option for PDF parsing and improve resource management
|
5 месяцев назад |
|
myhloli
|
15dd9a0ff1
refactor: reorganize config_reader imports and enhance format utilities
|
5 месяцев назад |
|
myhloli
|
b0fd756625
refactor: update OCR handling and improve function parameters for clarity
|
5 месяцев назад |
|
myhloli
|
9bb257769c
refactor: reorganize imports to align with backend structure and improve clarity
|
5 месяцев назад |
|
myhloli
|
a3ae57bf20
refactor: streamline text span extraction and remove unused functions
|
5 месяцев назад |
|
myhloli
|
546be00aac
refactor: update OCR score handling to filter low-confidence results
|
5 месяцев назад |
|
myhloli
|
3334157f15
refactor: clean up unused OCR area calculation and update demo PDF path
|
5 месяцев назад |
|
myhloli
|
236a6033f1
refactor: improve block processing logic and enhance span handling
|
5 месяцев назад |
|
myhloli
|
7d4ce0c380
refactor: add LLM-aided title optimization and improve config handling
|
5 месяцев назад |
|
myhloli
|
d2de6d801a
refactor: update text span extraction to use new version and improve character handling
|
5 месяцев назад |
|
myhloli
|
1ed61cb5d6
refactor: update OCR span extraction logic and improve PDF page processing
|
5 месяцев назад |
|
myhloli
|
51393aa814
refactor: update union_make import and adjust middle JSON structure for consistency
|
5 месяцев назад |
|
myhloli
|
a9abb4e201
refactor: enhance OCR processing and paragraph splitting in document analysis pipeline
|
5 месяцев назад |
|
myhloli
|
0f21495a06
refactor: enhance block processing and sorting utilities for improved span management
|
5 месяцев назад |
|
myhloli
|
ae7b0a6eba
refactor: implement block preprocessing utilities for improved bounding box management
|
5 месяцев назад |
|
myhloli
|
8f1f9abec5
refactor: enhance bounding box utilities and add configuration reader for S3 integration
|
5 месяцев назад |
|
myhloli
|
ea5cb65a1f
refactor: enhance document parsing by supporting multiple PDF files and improving method organization
|
5 месяцев назад |
