egg/OCR
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • cf894b076e feat: create PDF layout restoration proposal egg 2025-11-20 19:00:49 +08:00
  • a957f06588 chore: archive dual-track-document-processing change proposal egg 2025-11-20 18:10:50 +08:00
  • 53844d3ab2 docs: complete API documentation and archive dual-track proposal egg 2025-11-20 18:01:58 +08:00
  • e23aaacd84 fix: resolve OCR track converter data structure mismatch egg 2025-11-20 17:51:18 +08:00
  • 2ecd022d6b test: complete Section 8.4 End-to-end tests with GPU memory management egg 2025-11-20 16:58:10 +08:00
  • 9f449e8a19 docs: add GPU memory management section to design.md egg 2025-11-20 16:42:23 +08:00
  • b997f9355a fix: make torch import optional and add PaddlePaddle GPU memory management egg 2025-11-20 16:40:44 +08:00
  • 7064ea30d5 fix: add original_filename field to DocumentMetadata egg 2025-11-20 12:26:41 +08:00
  • ef335cf3af feat: implement Office document direct extraction (Section 2.4) egg 2025-11-20 12:20:50 +08:00
  • 0974fc3a54 fix: resolve E2E test failures and add Office direct extraction design egg 2025-11-20 12:13:18 +08:00
  • c50a5e9d2b test: add unit and integration tests for dual-track processing egg 2025-11-19 12:50:44 +08:00
  • c2288ba935 feat: add frontend support for dual-track processing egg 2025-11-19 12:34:01 +08:00
  • 0fcb2492c9 test: add unit tests for DocumentTypeDetector egg 2025-11-19 12:14:59 +08:00
  • 1d0b63854a feat: add dual-track API endpoints for document processing egg 2025-11-19 09:38:12 +08:00
  • 8b9a364452 feat: add GPU optimization and fix TableData consistency egg 2025-11-19 09:17:27 +08:00
  • ecdce961ca feat: update PDF generator to support UnifiedDocument directly egg 2025-11-19 08:48:25 +08:00
  • ab89a40e8d feat: add unified JSON export with standardized schema egg 2025-11-19 08:36:24 +08:00
  • 5bcf3dfd42 fix: complete layout analysis features for DirectExtractionEngine egg 2025-11-19 08:15:11 +08:00
  • a3a6fbe58b feat: add OCR to UnifiedDocument converter for PP-StructureV3 integration egg 2025-11-19 08:05:20 +08:00
  • 062cb1f423 chore: update tasks - OCR service dual-track integration complete egg 2025-11-19 07:29:47 +08:00
  • 82139c8c64 feat: integrate dual-track processing into OCR service egg 2025-11-19 07:29:06 +08:00
  • 0608017a02 chore: update tasks.md with completed infrastructure work egg 2025-11-18 20:37:30 +08:00
  • 2d50c128f7 feat: implement core dual-track processing infrastructure egg 2025-11-18 20:17:50 +08:00
  • cd3cbea49d chore: project cleanup and prepare for dual-track processing refactor egg 2025-11-18 20:02:31 +08:00
  • 0edc56b03f fix: 修復PDF生成中的頁碼錯誤和文字重疊問題 egg 2025-11-18 18:57:01 +08:00
  • 5cf4010c9b fix: 修復多頁PDF頁碼分配錯誤和logging配置問題 egg 2025-11-18 12:13:25 +08:00
  • d99d37d93e feat: add detailed logging to PDF generation process egg 2025-11-18 08:33:22 +08:00
  • 41ddee5c46 chore: remove test scripts and clean up codebase egg 2025-11-18 08:16:50 +08:00
  • 92e326b3a3 fix: prevent text/table/image overlap by filtering text in all regions egg 2025-11-18 08:16:19 +08:00
  • e839d68160 fix: add image_regions and tables to bbox dimension calculation egg 2025-11-18 07:42:28 +08:00
  • 00e0d1fd76 fix: ensure calculate_page_dimensions checks all bbox sources egg 2025-11-18 07:27:29 +08:00
  • dc31121555 fix: correct OCR coordinate scaling by inferring dimensions from bbox egg 2025-11-17 21:01:38 +08:00
  • d33f605bdb fix: add proper coordinate scaling from OCR space to PDF space egg 2025-11-17 20:45:36 +08:00
  • fa1abcd8e6 feat: implement layout-preserving PDF generation with table reconstruction egg 2025-11-17 20:21:56 +08:00
  • 012da1abc4 fix: migrate UI to V2 API and fix admin dashboard egg 2025-11-17 08:55:50 +08:00
  • 62609de57c fix: add result_dir configuration for task result storage egg 2025-11-16 19:52:26 +08:00
  • 67d5c226df feat: implement actual OCR processing in start_task endpoint egg 2025-11-16 19:38:22 +08:00
  • ff566c3af4 fix: migrate ProcessingPage from V1 batch API to V2 task API egg 2025-11-16 19:31:32 +08:00
  • 439458c7fe fix: migrate UploadPage to V2 API and fix logout navigation egg 2025-11-16 19:22:36 +08:00
  • ad5c8be0a3 fix: add V2 file upload endpoint and update frontend to v2 API egg 2025-11-16 19:13:22 +08:00
  • 3f41a33877 docs: update documentation for chart recognition enablement egg 2025-11-16 19:04:30 +08:00
  • 7e12f162b4 feat: enable chart recognition with PaddlePaddle 3.2.1 egg 2025-11-16 18:57:38 +08:00
  • eb77322f8a docs: clarify chart recognition limitation and provide verification tool egg 2025-11-16 18:47:39 +08:00
  • 6bb5b7691f test: fix all failing tests - achieve 100% pass rate (18/18) egg 2025-11-16 18:39:10 +08:00
  • 90fca5002b test: run and fix V2 API tests - 11/18 passing egg 2025-11-16 18:16:47 +08:00
  • 8f94191914 feat: add admin dashboard, audit logs, token expiry check and test suite egg 2025-11-16 18:01:50 +08:00
  • fd98018ddd refactor: complete V1 to V2 migration and remove legacy architecture egg 2025-11-14 21:27:39 +08:00
  • ad2b832fb6 feat: complete external auth V2 migration with advanced features egg 2025-11-14 17:19:43 +08:00
  • 470fa96428 feat: add database table prefix and complete schema definition egg 2025-11-14 15:40:24 +08:00
  • 88f9fef2d4 refactor: enhance auth migration proposal with user task isolation egg 2025-11-14 15:33:18 +08:00
  • 28e419f5fa proposal: migrate to external API authentication egg 2025-11-14 15:14:48 +08:00
  • b048f2d640 fix: disable chart recognition due to PaddlePaddle 3.0.0 API limitation egg 2025-11-14 13:16:17 +08:00
  • 80c091b89a fix: add PaddlePaddle 2.x/3.x API compatibility layer egg 2025-11-14 10:56:29 +08:00
  • 36944117f4 fix: update setup script to install PaddlePaddle GPU version from official source egg 2025-11-14 09:35:12 +08:00
  • d80d60f14b fix: update PaddleOCR 3.x API - replace deprecated gpu_mem parameter with device parameter egg 2025-11-14 09:22:56 +08:00
  • 7536f43513 feat: implement GPU acceleration support for OCR processing egg 2025-11-14 07:42:13 +08:00
  • 6452797abe feat: add GPU acceleration support OpenSpec proposal egg 2025-11-14 07:34:06 +08:00
  • d7e64737b7 feat: migrate to WSL Ubuntu native development environment egg 2025-11-13 21:00:42 +08:00
  • 0f81d5e70b feat: Docker化部署 - 單容器架構轉換 beabigegg 2025-11-13 13:12:59 +08:00
  • 57cf91271c feat: modernize frontend UI with Tailwind v4 and professional design system beabigegg 2025-11-13 08:55:01 +08:00
  • 9cf36d8e21 fix: resolve 7 frontend-backend API inconsistencies and add comprehensive documentation beabigegg 2025-11-13 08:54:37 +08:00
  • fed112656f update FRONTEND documentation beabigegg 2025-11-12 23:55:21 +08:00
  • 21bc2f92f1 feat: modernize frontend architecture with professional UI/UX design beabigegg 2025-11-12 23:54:44 +08:00
  • 69302144f5 2nd beabigegg 2025-11-12 22:54:56 +08:00
  • da700721fa first beabigegg 2025-11-12 22:53:17 +08:00