DSH Plugin HubDSH 插件市场
Sqhao-O/dsh-docs 预览 preview

Sqhao-O/dsh-docs

Plugin插件 Native原生 ⭐ 14 MIT Vision & Media视觉与多媒体Models & Routing模型与路由Docs & Writing文档与写作

DeepSeek Harness 全本地文档智能插件，支持 PDF、Office、图片与扫描文档的离线 OCR 解析。

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

dsh-docs is a native plugin built exclusively for DeepSeek Harness (DSH), that adds fully offline local document intelligence capabilities to the DSH agent. It can parse multiple common document formats including PDF, Word, Excel, PowerPoint, Markdown, HTML, and CSV, and also supports OCR for images and scanned documents directly on the user’s local machine. No external services, Docker containers, or remote API keys are required, and all document processing happens locally without documents ever leaving the user’s disk. It can be installed directly via the DSH CLI with a guided one-prompt flow that handles all setup automatically.

The plugin is intended for DSH users who need their AI agent to work with sensitive local documents without sending data to third-party services. After installation, users add the plugin entry to their DSH profile’s cordis.patch.yml configuration file, then restart the DSH web session to enable the parsing tool. Windows x64 users can download a prebuilt offline OCR runtime that includes English and Simplified Chinese language packs for out-of-the-box use, while users on other platforms can use the native Node engine as a lightweight fallback for non-OCR tasks.

The entire project is released under the open source MIT license, and all included dependencies carry compatible open source licenses. The plugin requires Node.js version 22.19 or later, or any version 24 and newer, to function correctly. It enforces strict path access controls to prevent path traversal attacks, and only permits parsing documents in explicitly authorized directories, including the default session workspace and any extra directories the user adds to an allowlist.

这是一个专为DeepSeek Harness（DSH）开发的原生插件，为DSH智能体提供本地离线文档解析能力。它支持解析PDF、DOCX、XLSX、PPTX、Markdown、HTML、CSV等多种常用文档格式，还能对图片和扫描版文档完成本地离线OCR识别。所有处理流程都在用户本地完成，不需要Docker容器、远程API服务，文档数据全程不会离开用户本地磁盘。

该插件面向需要使用DSH AI智能体处理本地文档的用户，典型工作流是用户将插件安装到自己的DSH配置文件中，完成配置后即可调用dshdoc_extract工具解析工作区内的目标文档。Windows x64平台用户可以下载预编译的离线OCR运行时，自带英语和简体中文语言包，开箱即用，其他平台可以使用Node引擎作为非OCR功能的备选方案。

该插件以MIT许可证开源，依赖的Xberg解析库同样采用MIT许可证，可选的Windows运行时包含了CPython和Apache 2.0许可的Tesseract语言数据。它要求用户本地安装Node.js 22.19以上版本，或24及以上版本，同时遵循严格的文件路径访问控制，仅允许访问用户授权的目录，防止路径遍历攻击。

View on GitHub在 GitHub 查看

Recommended强烈推荐 Send to your DSH发给你的 DSH 安装 
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-docs（Sqhao-O/dsh-docs）
仓库：https://github.com/Sqhao-O/dsh-docs
本站详情页：https://www.yhbd.top/plugins/sqhao-o-dsh-docs/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 14 · 最近提交 2026-09-11 · 主语言 TypeScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 note1 项提示
  • 14 stars - an early-stage project星标 14，属于早期项目
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-doc

把 Sqhao-O/dsh-docs 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

11.3 KB · 缓存于 2026-08-23 03:41:13 · 11.3 KB

dsh-docs

dsh-docs — local document intelligence for DeepSeek Harness: PDF, DOCX, XLSX, PPTX, Markdown, HTML, CSV, OCR, and text

中文 | Installation prompt

dsh-docs gives your DeepSeek Harness agent real document intelligence — entirely on your own machine. Hand it a PDF, Word, Excel, or PowerPoint file and get back clean Markdown, plain text, or structured JSON; hand it a scanned page or image and a fully offline OCR pipeline reads it for you. No Docker, no HTTP service, no API keys, and no document ever leaves your disk.

It ships a pinned, self-contained Python + Xberg runtime with offline Tesseract language data (English and Simplified Chinese), delivering complete PDF/Office/OCR coverage on Windows x64 out of the box. The native Xberg Node binding serves as a lightweight non-OCR fallback on any platform, and every file read stays confined to folders you explicitly authorize.

The published package and plugin id use the dsh-doc spelling and the tools use dshdoc_*; they were renamed from the initial dsh-docling / docling_* release.

One-prompt install

No local checkout or build toolchain is needed. Paste the following prompt into a running DSH session (for example dsh web) in your own project folder. The Harness agent installs the published npm package, downloads the pinned offline OCR runtime, and configures the plugin in one go. The only prerequisite is a working dsh CLI on Node ^22.19 or >= 24; every runtime step is plain Node.js, so any shell works: cmd, PowerShell, pwsh, or Git Bash.

Install the dsh-doc plugin into my DSH web profile, end to end. Do every
step yourself in the terminal and verify the result.

1. Install the published plugin package:
   dsh plugin --profile web add dsh-doc
2. Windows x64 only — download the prebuilt offline OCR runtime. The script
   verifies the pinned archive SHA-256, then verifies every extracted file
   against the bundled manifest:
   node <home>/.dsh/profiles/web/node_modules/dsh-doc/scripts/fetch-runtime-win32-x64.mjs <home>/.dsh/runtimes/dshdoc-runtime-win32-x64
   Replace <home> with my absolute home directory in this and every later step.
   On any other platform, skip this step and use engine: node below.
3. Edit <home>/.dsh/profiles/web/cordis.patch.yml. Preserve every existing
   entry and add or update this one:
   - id: dsh-doc
     config:
       engine: python
       runtimeDir: <home>/.dsh/runtimes/dshdoc-runtime-win32-x64
       defaultOcr: true
       maxOutputChars: 32000
   The session workspace is readable automatically; add allowedLocalRoots only
   for extra persistent directories such as a shared document vault.
   If you skipped step 2, use `engine: node` and `defaultOcr: false` instead
   and omit runtimeDir.
4. Verify with `dsh --profile web --dump-config` that the composed dsh-doc
   entry carries exactly this config, then report the result and remind me to
   restart `dsh web` so I can call dshdoc_health.

Hard constraints: never install, start, or configure Docling Serve, Docker,
containers, or any remote document-conversion service; never configure a
downloadable OCR backend or allow a model download.

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 →

渲染基于仓库 Sqhao-O/dsh-docs 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev dsh-ux 下一个 Next dsh-knowledge →