本次同步 09-12 至 09-28 的代码变更,主要内容: 新增功能 - 修改密码:后端新增 ChangePasswordRequest DTO 与UserController/UserService 对应接口,前端新增 ChangePasswordDialog 并在 Header 接入入口 - 文件预览组件重构:file-preview 目录拆分出 VideoPreview(支持 blobUrl 直传)、 ImagePreview、AudioPreview,index.tsx 统一调度各类型预览器 - 新增 my_ops 算子模块:markitdown_parser、mineru_pdf_parser、text_quality_evaluator - 新增 tools/minio-file-server MinIO 文件服务 功能增强 - 数据清洗:cleaning_task_service/scheduler/routes 重构, data_juicer_executor 与 wrapper 增强,OperatorTable/LogsTable/TaskDetail 同步调整 - 数据标注:annotation sync.py、project.py 接口与schema 更新 - 数据采集、算子市场、首页与菜单路由相关页面调整 - DataJuicer 算子接入(useOperatorOperations、dj_ops_schema) 结构调整 - deepflow/ 更名为 deep-flow/(419 个文件重命名) - 新增 helm 部署编排、GitHub Actions 之外的自建镜像构建脚本 未纳入本次提交 - scripts-backup/、runtime/python-executor-backup/、components_backup/(备份目录) - *.backup*、__pycache__ 产物 - zh_core_web_sm-3.8.0-py3-none-any.whl(46MB 构建产物) - DataX/(内嵌独立仓库,远程亦未收录其源码)
93 lines
3.0 KiB
YAML
93 lines
3.0 KiB
YAML
name: "MarkItDown Parser"
|
|
description: "基于 MarkItDown 库将多种文档格式统一转换为 Markdown 文本。支持图片上传、远程图片下载与 Base64 转换。"
|
|
language: "python"
|
|
raw_id: "MarkItDownParser"
|
|
version: "1.1.0"
|
|
vendor: "DeepData"
|
|
modal: "text"
|
|
inputs: "text"
|
|
outputs: "text"
|
|
types:
|
|
- 'collect'
|
|
|
|
release:
|
|
- "首次发布:支持多格式文档转 Markdown"
|
|
- "新增图片外部上传图床功能"
|
|
- "优化图片处理优先级与容错机制"
|
|
|
|
settings:
|
|
doc_formats:
|
|
name: "处理的文档格式"
|
|
description: "选择需要处理的文件格式。"
|
|
type: "multiSelect"
|
|
defaultVal: ["docx", "xlsx", "pptx", "csv", "txt", "xml", "doc", "xls", "ppt"]
|
|
required: true
|
|
options:
|
|
- label: "Word (.docx)"
|
|
value: "docx"
|
|
- label: "Word (.doc)"
|
|
value: "doc"
|
|
- label: "Excel (.xlsx)"
|
|
value: "xlsx"
|
|
- label: "Excel (.xls)"
|
|
value: "xls"
|
|
- label: "PowerPoint (.pptx)"
|
|
value: "pptx"
|
|
- label: "PowerPoint (.ppt)"
|
|
value: "ppt"
|
|
- label: "纯文本 (.txt)"
|
|
value: "txt"
|
|
- label: "CSV (.csv)"
|
|
value: "csv"
|
|
- label: "XML (.xml)"
|
|
value: "xml"
|
|
- label: "HTML (.html)"
|
|
value: "html"
|
|
- label: "HTML (.htm)"
|
|
value: "htm"
|
|
|
|
# ================= 原有图片处理配置 =================
|
|
download_remote_images:
|
|
name: "下载远程图片"
|
|
description: "是否自动下载 HTML 中的远程图片。开启后,图片将被本地化或上传。"
|
|
type: "switch"
|
|
defaultVal: "true"
|
|
checkedLabel: "是"
|
|
unCheckedLabel: "否"
|
|
embed_images_base64:
|
|
name: "嵌入 Base64 图片"
|
|
description: "将图片转为 Base64 内联到 Markdown 中。若关闭且未开启上传,图片将保存为本地文件。"
|
|
type: "switch"
|
|
defaultVal: "true"
|
|
checkedLabel: "是"
|
|
unCheckedLabel: "否"
|
|
max_image_width:
|
|
name: "图片最大宽度 (像素)"
|
|
description: "超过此宽度的图片将被等比缩放,减少体积。"
|
|
type: "slider"
|
|
defaultVal: 1200
|
|
min: 400
|
|
max: 4096
|
|
step: 100
|
|
|
|
# ================= 新增:外部图床上传配置 =================
|
|
upload_images:
|
|
name: "上传图片到外部服务"
|
|
description: "开启后,将自动把文档中的图片上传至下方指定的 API,并替换为可访问的网络链接"
|
|
type: "switch"
|
|
defaultVal: "true"
|
|
checkedLabel: "开启上传"
|
|
unCheckedLabel: "使用 Base64/本地"
|
|
upload_api_url:
|
|
name: "图片上传 API 地址"
|
|
description: "接收图片的 POST 接口 (支持 multipart/form-data),例如: http://example.com/upload/form"
|
|
type: "input"
|
|
defaultVal: "http://mfs.ailab.ccoop.cc:18585/upload/form"
|
|
required: false
|
|
preview_base_url:
|
|
name: "图片预览基础地址"
|
|
description: "用于拼接上传返回的相对路径,生成最终 URL。例如: http://example.com/file"
|
|
type: "input"
|
|
defaultVal: "http://mfs.ailab.ccoop.cc:18585"
|
|
required: false
|