dsh-plugin-rag
文件与数据 活跃维护

dsh-plugin-rag

YYTbit/dsh-plugin-rag

直接为模型注入本地知识库检索能力,自动向量化文档并匹配上下文,回答引用私有数据,全程无需上传云端,插件式安装即刻启用。

1
Stars 标星
0
Forks 分支
1
Watchers 关注
0
Open Issues
TypeScript
主要语言
MIT
开源协议
7 KB
仓库大小
1 个月前
最后推送
一键安装扩展 / 插件指令
dsh plugin --profile web add github:YYTbit/dsh-plugin-rag
git clone https://github.com/YYTbit/dsh-plugin-rag.git
git clone git@github.com:YYTbit/dsh-plugin-rag.git
README.md master

dsh-plugin-rag

Local knowledge base RAG for DeepSeek Harness.

What it does

Indexes project files (markdown, code, configs) and provides keyword search to find relevant context. No external APIs or embedding models needed -- pure local TF-IDF search.

Install

dsh plugin --profile your-profile add dsh-plugin-rag

CLI

# Search for relevant files
rag "authentication" ./src

# Show index stats
rag --index ./src ./docs

What gets indexed

  • Markdown (.md, .txt)
  • Code (.ts, .js, .py, .rs, .go, .java, .c, .cpp)
  • Config (.json, .yaml, .toml, .env)
  • Docs (.html, .xml, .sql, .graphql)

Skips: node_modules, .git, dist, build, pycache

Configuration

- id: rag
  name: dsh-plugin-rag
  config:
    indexPaths: ['.']
    maxResults: 3
    maxBytes: 4096
    enableInjection: true

How it works

  1. Scans directories for text files
  2. Builds a keyword index (TF-IDF scoring)
  3. Injects index stats into system prompt
  4. Agent uses CLI to search when needed

No embedding models, no external APIs, no heavy dependencies.

License

MIT -- YYTbit