local-rag

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/xianleewu-local-rag

About

Use cases: documents, testing, data, ml

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools

No tools found

Secrets

None asked for

Install scripts

None found

Runs as

Python package

What's inside

Skill name

local-rag

Description

Build a local RAG index by splitting a document and embedding its chunks using the on-device engine (private/offline). Use when the user wants to chunk and embed a document for retrieval, prepare files for local RAG, or test the engine's doc-split + embedding pipeline. Triggers on "RAG", "embed document", "chunk and embed", "index this doc", "文档切分", "本地知识库", "向量化文档".

License

MIT

Instructions

19 lines in SKILL.md · view on GitHub

# local-rag

用设备上的引擎把文档切块并求向量(本地 RAG 入库的前两步,数据不出设备)。

## 前提
- `pip install -e <helper-repo>/sdk` 且 `ZETTOS_AI_BASE_URL` 指向引擎。
- 设备上已加载 `rag_text_embedding` 实例(用 `local-engine-admin` 查/加载)。
- 文档在**设备本机**路径上。

## 用法

```bash
python run.py <RAG_INSTANCE_ID> </path/on/device/doc.txt>
```

输出每个 chunk 的长度与向量维度。把 (chunk, vector) 存进你自己的向量库即可;
检索时再配合 `rerank` 与 `local-llm-chat` 完成问答。

Signals

Stars

3

Forks

0

Open issues

0

Last commit (this folder)

Jun 11, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License

MIT

Repository

github.com/Xianleewu/zettos-ai-engine-helper

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

GitHubgithub-graphql