Commit Graph

12 Commits

Author SHA1 Message Date
starmen1265 ae8f6080c9 删除就技能
PR Test / lint (pull_request) Successful in 2s
2026-03-16 16:55:21 +08:00
starmen1265 0f0011b4a6 refactor(kb-workflow): remove legacy code - use kb_pipeline only
Root cause: kb_workflow.py contained 312 lines of deprecated legacy
code that was confusing AI agents. The legacy functions have been
completely replaced by the kb_pipeline package.

Changes:
- Removed all legacy functions (is_video_content, check_duplicate, etc.)
- Kept only process_command() and main() entry points
- Updated SKILL.md to remove old command examples
- File reduced from 495 to 143 lines (71% reduction)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 15:27:31 +08:00
starmen1265 6883a701c0 docs(kb-workflow): update SKILL.md for new pipeline architecture
PR Test / lint (pull_request) Successful in 2s
- Simplify to single-command workflow: kb-workflow process <url>
- Document new CLI parameters and options
- Add architecture overview
- Remove deprecated multi-step manual process

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 01:03:18 +08:00
starmen1265 33eeb6bc34 feat(04-05): add CLI 'process' subcommand
- Add process_command function that executes full pipeline
- Add subparser for 'process' command with URL argument
- Add --output-dir and --skip-completed flags
- Add --no-skip flag to re-run all steps
- Maintain backward compatibility with legacy arguments

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-13 23:44:10 +08:00
starmen1265 cf7cbd2ad0 feat: kb-deep-analyzer 支持文章类型分析
PR Test / lint (pull_request) Successful in 2s
- 新增 --type article 参数
- 文章类型生成 300 字摘要 + 完整原文
- 视频类型保持原有时间轴分析逻辑
- 更新相关文档

🤖 Generated by AI
2026-03-13 11:12:34 +08:00
starmen1265 3909bb0321 fix: 修复知乎专栏文章爬取问题
PR Test / lint (pull_request) Successful in 1s
- zhihu_content.py 添加 zhuanlan/article 类型支持
- 内部自动调用 zhihu_article_crawler.py 爬取新数据
- 更新 SKILL.md 文档,明确知乎专栏处理流程
- 解决读取旧数据导致分析错误内容的问题
2026-03-09 23:15:59 +08:00
starmen1265 04c1ba2e80 feat(kb-workflow): 归档目录改为 ~/work/zq/30.资源/AI分析
Deploy to knowledge-base / deploy (push) Failing after 0s
- 添加 KB_ARCHIVE_PATH 环境变量配置归档目录
- 添加 KB_GIT_ROOT 环境变量配置 Git 仓库根目录
- 默认归档到 ~/work/zq/30.资源/AI分析/YYYY-MM-DD/
- Git 提交到 ~/work/zq 仓库
- 更新 SKILL.md 文档说明新的目录结构
2026-03-09 00:07:08 +08:00
starmen1265 202960eb64 fix: 统一知识库技能模型名称为 glm-5,补充 OCR 和 kb-funasr 说明
- kb-deep-analyzer: glm-4.7 → glm-5, gpt-4 → glm-5
- kb-workflow: 步骤5增加 OCR 和 kb-funasr 作为备用方案
- 统一命令使用 --type subtitle-download
2026-02-27 15:36:18 +08:00
starmen1265 9259a3731a feat: 添加知乎视频支持
新增:
- kb-zhihu-content/: 知乎视频下载模块
  - zhihu_content.py: 视频下载工具(使用 yt-dlp)
  - SKILL.md: 技能说明文档

修改:
- kb_workflow.py:
  - CONTENT_AGENTS 添加 zhihu
  - VIDEO_CONTENT_TYPES 添加 zvideo

- SKILL.md:
  - 添加 4.1.2 知乎视频处理流程
  - 更新子技能清单,添加知乎视频条目
  - 更新内容类型判断表格
2026-02-16 22:19:25 +08:00
starmen1265 09618f52c5 feat: 添加专栏文章处理支持
- kb_workflow.py: 添加内容类型判断函数
  - is_video_content(): 判断视频内容
  - is_text_content(): 判断文字内容(专栏/问答)
  - is_image_content(): 判断图片内容
  - get_content_handler(): 获取处理方式

- SKILL.md: 完善条件分支逻辑
  - 添加内容类型判断表格
  - 添加专栏文章处理流程说明
  - 添加专栏文章的步骤4.2处理指南
  - 更新子技能清单,添加专栏文章命令
2026-02-16 21:07:26 +08:00
starmen1265 3dc8d246d0 修复并集成说话者分离功能
修复:
- kb-whisper-diarization/whisper_diarization.py 变量名 bug

集成:
- kb-workflow/SKILL.md 步骤5 添加说话者分离选项
- 自动检测 HF_TOKEN 选择识别模式
- 子技能清单添加 kb-whisper-diarization

文档:
- kb-whisper-diarization/SKILL.md 完善 HF_TOKEN 获取步骤
2026-02-15 23:18:11 +08:00
starmen1265 86daba5771 添加技能模块 2026-02-15 01:17:39 +08:00