๋ณธ๋ฌธ์œผ๋กœ ๊ฑด๋„ˆ๋›ฐ๊ธฐ
ๅฐ้พ™่™พๅฐ้พ™่™พAI
๐Ÿค–

RAG Search

Backend retrieval skill for structured search of occupational health standards and documents, returning relevant text with source and clause details.

ไธ‹่ฝฝ3.8k
ๆ˜Ÿๆ ‡4
็‰ˆๆœฌ0.1.1
ๆœ็ดข็ ”็ฉถ
ๅฎ‰ๅ…จ้€š่ฟ‡
๐Ÿ’ฌPrompt

ๆŠ€่ƒฝ่ฏดๆ˜Ž

rag-search

Minimal RAG search skill for backend retrieval.

โš ๏ธ Important

This skill is intended to be used as a backend retrieval component and should not be invoked directly by end users.

Use occupational_health_qa or occupational_health_report_writer for direct user requests.

Usage

ไฝ ๏ผš่ฐƒ็”จ rag-search๏ผŒๆŸฅ่ฏข"GBZ 2.1-2019 ่‹ฏ ่ŒไธšๆŽฅ่งฆ้™ๅ€ผ"

Returns

Returns structured search results with:

  • content: Original text from the document
  • source: File name / standard number
  • clause: Clause number (if available)
  • regulation_level: Regulation level (ๅ›ฝๅฎถๆณ•ๅพ‹/ๅ›ฝๅฎถๆ ‡ๅ‡†/่กŒไธšๆ ‡ๅ‡†/etc)
  • score: Relevance score (0-1)

Example Response

{
  "results": [
    {
      "content": "่‹ฏ็š„ๆ—ถ้—ดๅŠ ๆƒๅนณๅ‡ๅฎน่ฎธๆต“ๅบฆ๏ผˆPC-TWA๏ผ‰ไธบ6 mg/mยณ...",
      "source": "GBZ 2.1-2019.pdf",
      "clause": "็ฌฌ4.1ๆก",
      "regulation_level": "ๅ›ฝๅฎถๆ ‡ๅ‡†",
      "score": 0.93
    }
  ]
}

ๅฆ‚ไฝ•ไฝฟ็”จใ€ŒRAG Searchใ€๏ผŸ

  1. ๆ‰“ๅผ€ๅฐ้พ™่™พAI๏ผˆWeb ๆˆ– iOS App๏ผ‰
  2. ็‚นๅ‡ปไธŠๆ–นใ€Œ็ซ‹ๅณไฝฟ็”จใ€ๆŒ‰้’ฎ๏ผŒๆˆ–ๅœจๅฏน่ฏๆก†ไธญ่พ“ๅ…ฅไปปๅŠกๆ่ฟฐ
  3. ๅฐ้พ™่™พAI ไผš่‡ชๅŠจๅŒน้…ๅนถ่ฐƒ็”จใ€ŒRAG Searchใ€ๆŠ€่ƒฝๅฎŒๆˆไปปๅŠก
  4. ็ป“ๆžœๅณๆ—ถๅ‘ˆ็Žฐ๏ผŒๆ”ฏๆŒ็ปง็ปญๅฏน่ฏไผ˜ๅŒ–

็›ธๅ…ณๆŠ€่ƒฝ

๐Ÿค–
local-file-rag-basic

High-performance local File RAG suite (Basic Edition).

612 ไธ‹่ฝฝAI ๆ™บ่ƒฝไฝ“๐Ÿ’ฌ Prompt
๐Ÿค–
HK-101 Living RAG

Provides answers by retrieving and synthesizing information from local text or markdown files using a retrieval-augmented generation approach.

2.0k ไธ‹่ฝฝAI ๆ™บ่ƒฝไฝ“๐Ÿ’ฌ Prompt
๐Ÿค–
rag-query

Query the RAG knowledge base (Qdrant kb_main) by semantic search. Returns top-k chunks with text, doc_id, source, text_type, topic_tags.

39 ไธ‹่ฝฝๆœ็ดข็ ”็ฉถ
๐Ÿค–
Local Rag Search

Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of RAG-based web search with DuckDuckGo, Google, and multi-engine deep research capabilities.

4.6k ไธ‹่ฝฝๆœ็ดข็ ”็ฉถ
๐Ÿค–
RAGLite

Local-first RAG cache: distill docs into structured Markdown, then index/query with Chroma + hybrid search (vector + keyword).

1.1k ไธ‹่ฝฝๆ•ˆ็Ž‡ๅŠžๅ…ฌ
๐Ÿค–
semantic-search

ไผไธš็บง่ฏญไน‰ๆฃ€็ดขๆŠ€่ƒฝ๏ผŒๆ”ฏๆŒ่กจๆ ผ/ๅญ—ๆฎต/ๆ–‡ไปถๆœ็ดขๅ’Œ Text-to-SQL ๆ•ฐๆฎ็”Ÿๆˆ

55 ไธ‹่ฝฝๆ•ฐๆฎๅบ“โš™๏ธ ่„šๆœฌ