pengxiao 6395ee3b49 feat: replace pymupdf image extraction with pdf2image + Heron layout detection ...

PDF image extraction now renders pages with pdf2image, detects figure
regions using docling-layout-heron (RT-DETRv2), and crops only the
detected pictures. Removes full-page fallback for text-only pages.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-06-02 22:38:31 +08:00

..

data_backup.py

Initial commit: 国土空间规划课程智能体 v1.0

2026-05-22 09:40:18 +08:00

docker_init.py

Initial commit: 国土空间规划课程智能体 v1.0

2026-05-22 09:40:18 +08:00

import_book_structure.py

Initial commit: 国土空间规划课程智能体 v1.0

2026-05-22 09:40:18 +08:00

service_monitor.py

Initial commit: 国土空间规划课程智能体 v1.0

2026-05-22 09:40:18 +08:00

test_pdf_image_extract.py

feat: replace pymupdf image extraction with pdf2image + Heron layout detection

2026-06-02 22:38:31 +08:00

vectorizer_service.py

Initial commit: 国土空间规划课程智能体 v1.0

2026-05-22 09:40:18 +08:00