Breeze136/dsh-kb-rag

Name: Breeze136/dsh-kb-rag
Author: Breeze136

Plugin插件 Native原生 ⭐ 14 MIT Memory & Knowledge记忆与知识库 Data & Analysis数据与分析

本地优先的文献知识库 RAG（DeepSeek Harness 插件）：混合检索正文与图注，将模糊记忆定位至具体段落与图表，DOI 一键直达原文。

Project Overview项目介绍

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

kb-rag is a local literature knowledge base built for DSH that also works as an MCP server for any MCP-capable agent. It indexes PDFs and Zotero libraries, and stores the entire index in a single SQLite file. All indexing, embedding, and reranking run locally on the user’s machine, so there are no API costs and no data is uploaded to external services. Results include the passage’s section, physical PDF page, clickable DOI, and full tracing for every in-text citation back to its referenced work. Users can copy or archive the single SQLite index file at any time for backup or moving between devices.

This tool is purpose-built for academic papers, not general-purpose document management. It uses section-aware chunking that weights abstract and method sections more heavily, and natively supports full migration from Zotero libraries. Unlike general RAG tools that return paraphrased summaries, kb-rag returns the exact original passage with full provenance, making it ideal for researchers and graduate students doing literature review and academic writing. After importing a personal library, users can ask research questions and get direct links to the exact location of relevant evidence in their existing papers. It also explicitly marks whether a cited work is already present in the user’s local library.

kb-rag is released under the open source MIT license, and the BAAI/bge embedding and reranker models are downloaded on first use. First use is slower because the total download size is around 1.2GB, and the first query takes roughly 10 seconds to load the models into memory. After the first run, a resident daemon keeps the models in memory, and subsequent queries return in under one second. Known limitations include no support for scanned PDFs without a text layer, weak cross-language retrieval, and no image content indexing. Scanned documents are automatically skipped during ingestion, and OCR is explicitly out of the project’s scope.

这是一个面向学术文献的本地RAG知识库工具，原生支持DeepSeek Harness（DSH），同时可作为MCP服务器适配任何支持MCP协议的智能体。它支持索引本地PDF文献和Zotero文献库，所有索引、嵌入和重排序步骤都在本地运行，无需上传文献，也不会产生额外API费用。整个知识库存储在单个SQLite文件中，返回结果带具体出处、页码、可点击DOI和完整引用追溯信息。

该工具针对学术文献做了专门优化，采用分块加权（摘要和方法部分权重更高），原生支持Zotero迁移，专注于文献检索而非通用文档管理。用户可以导入自己的文献库，之后向工具提问，工具会返回最相关的原文片段而非改写总结，方便研究人员快速定位问题对应的原始文献证据，辅助开展文献调研和学术写作。

该工具采用MIT许可证开源，不支持没有文本层的扫描PDF，跨语言检索能力较弱，目前只支持文本检索，不处理图片内容。首次使用时会自动下载约1.2GB的BAAI嵌入和重排序模型，首次启动较慢，后续查询速度会提升到亚秒级别，知识库可复制存档。

View on GitHub在 GitHub 查看

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-kb-rag（Breeze136/dsh-kb-rag）
仓库：https://github.com/Breeze136/dsh-kb-rag
本站详情页：https://www.yhbd.top/plugins/breeze136-dsh-kb-rag/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 14 · 最近提交 2026-09-23 · 主语言 Python

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-kb-rag

把 Breeze136/dsh-kb-rag 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

27.4 KB · 缓存于 2026-09-23 22:09:45 · 27.4 KB

kb-rag — Local literature RAG with passage-level provenance

English | Chinese

kb-rag is a local literature knowledge base for DSH (DeepSeek Harness) and any MCP-capable agent. It indexes PDFs and Zotero libraries into a single SQLite file, then answers questions with passages rather than paraphrases: every result carries its section, physical PDF page, and a clickable DOI — and every in-text citation in the retrieved passage can be traced back to the referenced work, including whether that work is already in your library.

The npm package dsh-kb-rag is published from npm-package/ in this repository. It is not affiliated with other repositories that share the name dsh-kb-rag.

Indexing, embedding, and reranking all run locally. There is no API cost and no upload.

Quick Start · Deployment shapes · Tool reference · Documentation · Measured performance

What the output looks like

A single kb_rag call returns evidence in this form. The tool renders its interface in Chinese today, so the block below is that output translated; the in-library marker it prints appears here as [in-library]:

**Knowledge base sources Top-2**
deep · reranked with BAAI/bge-reranker-base · cache hit

1. [Chemical vapour deposition of graphene on copper substrates](https://doi.org/10.5555/12345678) — Author A; Author B · 2024 · Carbon · Results · p.4
> graphene domains nucleate on the copper surface and coalesce into a continuous film ... at a growth rate of ~2 um/min
citations from this evidence ([in-library] = already held, searchable)
  · [Ref 4] Author C, et al. Carbon 48, 1234 (2010)
    [in-library] [Nucleation and growth of graphene on transition metals](https://doi.org/10.5555/12345684) (Author C · 2010 · Carbon) (this evidence's Ref 4) · [open in Zotero](zotero://open-pdf/library/items/EXAMPLEKEY1)
  · 3 further citations collapsed (Ref 6-8); use the numbers to fetch them

**Related work**
- [A Practical Guide to Raman Spectroscopy of Graphene] — Author G et al. · 2020 (same author, related topic)

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 Breeze136/dsh-kb-rag 的 README.md。在 GitHub 查看原文 →