Commit Graph

  • 4d66d46ba7 Merge branch 'main' into mini mini tigerenwork 2025-08-20 11:05:15 +0800
  • f801ddea77 env:MacMini Only LH 2025-08-19 19:48:12 -0700
  • 1b1c720893 Merge pull request 'feat: 用llm生成脱敏地址' (#3) from dev into main main tigeren 2025-08-20 02:44:53 +0000
  • 51a50a3fb6 feat: 用llm生成脱敏地址 #3 dev tigerenwork 2025-08-20 10:43:53 +0800
  • f981bfa40e Merge pull request 'dev' (#2) from dev into main tigeren 2025-08-20 02:20:41 +0000
  • 84f9ef2b18 feat: 将漏掉的身份证号和社会安全号补上 #2 tigermren 2025-08-20 00:11:56 +0800
  • a001c26e8d feat:优化公司名简化性能 tigermren 2025-08-19 23:28:56 +0800
  • eb33dc137e feat: 优化chunking,避免截断 tigerenwork 2025-08-19 17:43:05 +0800
  • ffa31d33de feat: 过滤掉置信度低的entity tigerenwork 2025-08-19 17:26:30 +0800
  • 24f452818a feat: 更新替换算法,解决匹配token中有空格的问题 tigerenwork 2025-08-19 16:08:49 +0800
  • 40dd0de1b3 feat: 改进ner chunking tigermren 2025-08-19 02:15:05 +0800
  • d446ac1854 feat: 使用NER模型进行识别 tigermren 2025-08-19 01:36:08 +0800
  • 2075218955 feat: 正式fully支持docx tigermren 2025-08-18 01:15:40 +0800
  • afddcf4dd7 fix: 解决magic-doc包的问题 tigermren 2025-08-18 01:01:58 +0800
  • 0820d7bba2 feat:新增magicdoc tigermren 2025-08-18 00:40:39 +0800
  • a16b69475e refine: 整理文件 tigermren 2025-08-17 23:33:56 +0800
  • 84499f52ea feat: 增加错误信息显示 tigermren 2025-08-17 23:26:59 +0800
  • 256e263cff feat: 开启docx解析,但是mineru-api未支持 tigermren 2025-08-17 23:12:45 +0800
  • 1138683da1 refine: 调整docker tigermren 2025-08-17 20:16:07 +0800
  • c85e166208 feat:重构ollama,内置重试逻辑和schema验证 tigermren 2025-08-17 20:09:00 +0800
  • 70b6617c5e refine:重构文档 tigermren 2025-08-17 20:02:37 +0800
  • 1dd2f3884c refine: 新身份证、社会安全代码脱敏规则 tigermren 2025-08-17 15:59:12 +0800
  • 2c985bc963 feat: 地址脱敏隐去门牌、街道、小区等 tigermren 2025-08-17 15:30:52 +0800
  • 437e010aee feat: 配置测试test runner tigermren 2025-08-17 14:11:29 +0800
  • b3be522358 feat: 公司名字mask tigermren 2025-08-17 13:56:25 +0800
  • 2c4ecfd6b0 feat: 中文名按照姓+名拼音首字母脱敏 tigermren 2025-08-16 16:37:24 +0800
  • 8399bc37fc Initial commit tigermren 2025-07-20 21:54:24 +0800
  • 56c718d658 Merge pull request 'feature-ner-keyword-detect' (#1) from feature-ner-keyword-detect into main main-legacy tigeren 2025-07-20 13:43:59 +0000
  • edad8e7322 fix: 解决下载文件后缀的问题 #1 feature-ner-keyword-detect oliviamn 2025-07-17 01:07:13 +0800
  • 68765ab45f fix: 解决下载文件扩展名的问题 oliviamn 2025-07-17 00:20:11 +0800
  • 19d8e4a0b1 镜像导入导出流程及脚本 oliviamn 2025-07-15 00:47:44 +0800
  • 4689fade84 增加统一的docker compose oliviamn 2025-07-15 00:36:59 +0800
  • 88b790dd6b 更新pdf_processor,适用mineru oliviamn 2025-07-15 00:29:34 +0800
  • d3e1927bc5 重新启用pdf_processor oliviamn 2025-07-14 23:49:28 +0800
  • e8cb7b1a04 feat: 调整ner的mask规则 oliviamn 2025-07-14 23:48:55 +0800
  • 1ba4f3cc02 feat: 增加构建mapping的日志 oliviamn 2025-07-14 22:24:43 +0800
  • daf316bb92 add mineru docker file tigerenwork 2025-07-13 17:48:18 +0800
  • 94e500c990 add log for ner tigerenwork 2025-07-13 17:48:08 +0800
  • a4d4a7608b feat: 增加一些日志记录 tigerenwork 2025-07-12 17:39:06 +0800
  • f2e6ab44c0 add .env oliviamn 2025-07-12 16:36:56 +0800
  • fcf88e36d6 WIP:新增mineru部分 feature-seperate-mineru tigerenwork 2025-07-12 15:46:05 +0800
  • 1649a9328b WIP: 重构NER processor oliviamn 2025-07-10 00:14:16 +0800
  • 1cf3c45cee WIP oliviamn 2025-07-06 21:11:23 +0800
  • a949902367 完整所有的匹配规则 oliviamn 2025-07-03 23:58:30 +0800
  • 5b1b8f8e9c feat: Enhance NER processing by adding company name mapping and refactoring prompt functions oliviamn 2025-06-27 00:39:38 +0800
  • 5ddef90e8b feat:单独对名字进行NER oliviamn 2025-06-25 01:31:12 +0800
  • ee95f1daa7 WIP: 暂时屏蔽docx,pdf解析 oliviamn 2025-06-25 01:30:43 +0800
  • 12c1b5f75e feat: 显示完成时间 develop oliviamn 2025-06-01 15:47:58 +0800
  • e2ebd2fb09 feat: port 3000 oliviamn 2025-05-28 02:25:45 +0800
  • 2947743d28 feat: set env oliviamn 2025-05-28 02:23:10 +0800
  • 329610088d feat:删除开发docker文件 oliviamn 2025-05-28 02:05:46 +0800
  • c554bd0c2f feat: 增加dockerfile oliviamn 2025-05-28 01:51:58 +0800
  • 3afe01f5f2 fix: 使用环境变量设置baseurl oliviamn 2025-05-27 23:39:01 +0800
  • c3fc9459b8 fix: 设置baseUrl可配置 oliviamn 2025-05-27 23:29:25 +0800
  • fbdeba5088 feat: 增加删除文件功能 oliviamn 2025-05-26 23:19:43 +0800
  • dea3a6bd6a feat:在docker中集成mineru,并且修正下载文件名不正确的问题 oliviamn 2025-05-26 23:07:10 +0800
  • 345fd05a2b fix: 解决md不允许上传的问题 oliviamn 2025-05-26 00:06:37 +0800
  • b3cf9f98a7 refine oliviamn 2025-05-25 16:45:48 +0800
  • 24c5bbd5d7 refine: 删除文档数据文件夹,用sample_doc取代 oliviamn 2025-05-25 16:43:32 +0800
  • 13ef24a3da feat:增加前端 oliviamn 2025-05-25 00:37:20 +0800
  • 900a614b09 refine: 解决了导入路径的问题 oliviamn 2025-05-25 00:04:19 +0800
  • 3e9c44e8c4 refine: 将原src的内容复制到backend/app/core oliviamn 2025-05-24 23:28:33 +0800
  • e0695e7f0e refine: src rename to core oliviamn 2025-05-24 22:13:20 +0800
  • 76b0351f8f feat: 增加backend oliviamn 2025-05-24 22:06:28 +0800
  • 47e78c35bb Add Markdown document processing support and enhance document handling oliviamn 2025-05-24 21:05:48 +0800
  • caa4d6d2ef Update README.md to clarify installation steps and add LibreOffice dependency oliviamn 2025-05-24 14:55:04 +0800
  • 5abfa4998d 实现docx转md oliviamn 2025-05-21 00:15:01 +0800
  • 0f158c159b Enhance PDF content masking by introducing mapping prompts oliviamn 2025-05-08 00:04:50 +0800
  • 7d0be5aa8a 将题词抽象出来 oliviamn 2025-05-06 00:13:19 +0800
  • 815427a509 文件写入output folder的.work隐藏目录下 oliviamn 2025-05-05 23:34:10 +0800
  • e6fb9b9a83 调整目录结构 oliviamn 2025-05-05 20:33:08 +0800
  • edca9a87a0 Refactor PdfDocumentProcessor to enhance PDF content processing oliviamn 2025-05-05 19:15:03 +0800
  • 6acf3e5423 Update requirements.txt to upgrade requests and add magic-pdf dependency oliviamn 2025-05-05 18:53:22 +0800
  • 592fb66f40 Enhance document processing with Ollama integration and update .gitignore tigermren 2025-04-23 01:09:33 +0800
  • fc68c243bb add gitignore tigermren 2025-04-23 00:06:39 +0800
  • 0904ab5073 Initial commit: Document processing app with Ollama integration tigermren 2025-04-23 00:02:10 +0800