Lee-Hilex/dsh-mineru

基于 MinerU 的 DeepSeek Harness 多模态文档解析插件:PDF/Word/PPT/Excel/HTML/图片 → 结构化 Markdown(免Token的Agent轻量解析 / 精准解析双API模式)

Project Overview项目介绍

dsh-mineru is a native plugin built exclusively for DeepSeek Harness that integrates OpenDataLab’s MinerU high-precision document parsing engine into the DSH agent workflow. To install the plugin, you first need to have an existing DeepSeek Harness installation running version 0.1.0-rc.6 or newer 0.1.x release, with the dsh CLI available on your system. You can install it directly from npm with a simple command like dsh plugin --profile web add dsh-mineru for the web profile, or build it from source by cloning the repository, running npm install, packing the tarball, and installing the local file. It supports converting common document and image formats into structured Markdown that text-only DSH agents can process.

After installation, you can verify the install by running dsh --profile web --dump-config | grep -A 2 "id: mineru" to confirm the plugin is registered, then restart your DSH web profile and navigate to Settings → Plugins → MinerU Parsing to complete optional configuration. You do not need a MinerU token to start using the plugin, though configuring a token unlocks the higher-precision API that supports legacy Office formats and HTML. Common use cases include summarizing research papers, extracting data from contracts or reports, running OCR on scanned images or screenshots, and batch processing dozens of documents in a single agent call. It is designed for researchers, developers, and knowledge workers who need to process unstructured documents with DSH agents.

The plugin includes several security guardrails: it isolates file paths to the session workspace, blocks malicious ZIP paths, stores tokens only in the local DSH credential vault, and never exposes tokens to logs or error messages. The tokenless Agent API has rate limits, file size caps of 10MB, and a 20-page limit per document, and it does not support older .doc, .ppt, or .xls formats or HTML. dsh-mineru is released under the open-source MIT license, with all parsing functionality hosted by MinerU’s official cloud API, and development contributions are welcome on GitHub.

dsh-mineru 是一款原生 DeepSeek Harness 插件,它将 MinerU 的高精度文档解析引擎接入 DSH 生态,可将 PDF、Word、PPT、Excel、HTML 和图片等常见格式转换为保留结构的 Markdown,让纯文本大模型也能读取处理原本无法解析的二进制文档。它支持两种 API 模式:需要配置 MinerU 令牌的精度 API,以及无需令牌、带 IP 速率限制的免费 Agent API。

用户可以将文档直接拖入对话窗口,插件会自动将文件路径填入输入框,发起请求后即可调用 MinerU 云端服务完成解析,解析结果会以工件形式保存在当前工作区,支持在 DSH 网页界面直接预览。它适合需要解析学术论文、商业合同、分析报告、扫描截图等各类文档的开发者、研究者和办公人员,还支持批量解析数十甚至上百个文件。

本插件要求用户已安装版本不低于 0.1.0-rc.6 的 DeepSeek Harness,可以通过 dsh CLI 直接从 npm 安装,也可克隆源码本地打包安装。无需令牌即可快速开始使用,无令牌模式下对旧版 Office 格式和 HTML 不支持,有速率和文件大小限制。插件采用 MIT 许可证开放源代码,令牌仅保存在用户本地凭据库,不会泄露。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 7 stars - very few users, little community feedback星标只有 7,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装(适合开发者)

CLI Install命令行安装

dsh plugin --profile web add dsh-mineru

把 Lee-Hilex/dsh-mineru 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

dsh-mineru

license version dsh MinerU

Repository: https://github.com/Lee-Hilex/dsh-mineru · npm: dsh-mineru · Changelog

English | 简体中文

dsh-mineru is a MinerU-powered multimodal document parsing plugin for DeepSeek Harness (dsh): turn PDF, Word, PPT, Excel, HTML, and images into structured Markdown. Configure a MinerU token to use the 🎯 Precision API, or leave it blank and use the ⚡ Agent API (tokenless, IP rate-limited).

⚠️ Data leaves this machine: every parse uploads your file to MinerU's remote service — there is no fully offline mode. Do not use it for confidential / case material that must stay on-premises. See Security model.

Contents

Overview

What is this?

dsh-mineru plugs MinerU (OpenDataLab's high-precision document parsing engine) into the DeepSeek Harness agent ecosystem, letting text-only models "read" documents: the model receives structured Markdown (tables, formulas, and images preserved) instead of binary files it cannot open.

Typical use cases:

  • Read papers / contracts / reports: parse a PDF, then ask the agent to summarize or extract data;
  • Batch-processing documents: parse dozens of files in one call, each producing Markdown;
  • OCR for images / screenshots: scanned pages and web screenshots become searchable text;
  • Formulas & tables: math formulas in papers and Excel tables survive with full structure.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

← 上一个 Prev dsh-approval-llm 下一个 Next deepseek-harness-angelina-themes →