agentleFS
Red-empty-potatoRed-empty-potato/ai-agent-skills/skills/rag-pipeline/SKILL.md

rag-pipeline

Skill0 starsChanged 3 months agoMITView on GitHub

Build a minimal Retrieval-Augmented Generation pipeline for grounded, cited answers. 搭建最小可用的 RAG 问答流程。

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

RAG Pipeline | RAG 问答流程

Build a minimal RAG (retrieval-augmented generation) pipeline that answers questions from your own documents with citations.

让模型基于你自己的文档作答并给出出处。

When to use | 适用场景

  • 用户想「让 AI 读我的文档然后问答」
  • 需要比纯 prompt 更可靠的、可溯源的答案

Workflow | 工作流程

  1. 收集源文档,按 ~500–1000 字切块(chunk)。
  2. 选 embedding 模型,把每块转成向量。
  3. 用内存向量库(如 chromadb / faiss,无需密钥)建索引。
  4. 检索:把问题转向量,取 top-k 相关块。
  5. 生成:把检索块 + 问题拼进 prompt,要求带出处引用。

Tips | 提示

  • chunk 大小和 overlap 直接影响效果,先调这两个参数。
  • 检索不到相关内容时让模型明确说「文档里没有」,不要硬答。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.