skills.rest
winsorllc
winsorllcCOMMUNITY
Explore all skills by this author →
GitHub

rag-search

Index documents with embeddings and search them by semantic similarity.

1|Updated Feb 25, 2026
Search Tags:#embeddings#rag#search#knowledge base#vector search#document retrieval
One-click install
npx skills add https://github.com/winsorllc/upgraded-carnival --skill rag-search-winsorllc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-search
Source: https://github.com/winsorllc/upgraded-carnival/tree/main/.pi/skills/rag-search
Command: npx skills add https://github.com/winsorllc/upgraded-carnival --skill rag-search-winsorllc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill enables efficient and accurate retrieval of information from a collection of documents by understanding the meaning and context of your queries, rather than just matching keywords.

Core Features & Use Cases

  • Semantic Indexing: Creates an index of your documents using embeddings for deep understanding.
  • Similarity Search: Finds the most relevant document chunks based on semantic similarity to your query.
  • Use Case: Quickly find specific configuration details or troubleshooting steps within a large codebase or documentation library.

Quick Start

Use the rag-search skill to index all markdown files in the ./docs directory.

Frequently Asked Questions about rag-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I perform semantic search across my markdown and code documentation?▼

Semantic search across markdown and code files is performed by indexing documents using embeddings and vector storage, enabling retrieval based on context and meaning rather than exact keyword matching.

Can I use local TF-IDF embeddings instead of OpenAI for document retrieval?▼

Yes, document retrieval supports local TF-IDF embeddings alongside OpenAI and Cohere providers, allowing flexible deployment without external API dependencies for your vector search index.

What file formats can I index for vector search and similarity matching?▼

Vector search indexing supports plain text, markdown, JSON, code files, and HTML documents, allowing you to build a comprehensive knowledge base for similarity matching.

How does semantic document retrieval work for finding troubleshooting steps?▼

Semantic document retrieval works by creating an index of document chunks using embeddings, then finding and returning the most relevant chunks based on semantic similarity to your query.

What is the best way to find specific configuration details within a large codebase?▼

The best way to find configuration details in a large codebase is using semantic similarity search, which indexes your files and retrieves relevant information by understanding the context of your query.

Are there limitations when using a local knowledge base for RAG search?▼

RAG search with local TF-IDF embeddings may have less contextual depth compared to OpenAI or Cohere providers, but it enables fully offline document retrieval without external API calls.

Related Skills

Explore More Software Engineering Skills→
mikkelkrogsholmmikkelkrogsholm

bookstrap-ingest

Ingest PDFs, Markdown, HTML, and plain text into Bookstrap knowledge bases with semantic chunking and embeddings.

Community
Advanced
mattwoodcomattwoodco
3

ai-rag-chat

Stream RAG chat answers with source citations from vector search.

Community
Advanced
patricio0312revpatricio0312rev
5

embedding-pipeline-builder

Automate document embedding pipelines for semantic search.

Community
Advanced
BEKO2210BEKO2210
15

search

Search knowledge bases semantically with vector embeddings and keyword fallback.

Community
Advanced