# RAG

> Use this tool when you need to efficiently manage and search large document collections or knowledge bases using semantic search capabilities. It solves problems related to information retrieval, document management, and AI assistant development by providing features like filtering, metadata support, and cosine similarity search. The RAG server takes in text content and metadata as input and outputs relevant search results, making it ideal for building custom AI assistants that require accurate information retrieval from cloud-based repositories.

Canonical page: https://skillsregistry.net/skills/kalicyh-rag  
JSON: https://api.skillsregistry.net/v1/skills/kalicyh-rag

## Description

A cloud-based RAG server that provides document management and semantic search capabilities using OpenAI's embedding and chat APIs. The implementation features an in-memory vector store with cosine similarity search, document ingestion tools for adding and managing text content with metadata, search functionality with filtering support, and utility tools for database statistics and management. Built with persistence support through JSON serialization and designed for cloud-only operation without local vector databases, it's useful for building AI assistants that need to search and retrieve information from custom document collections, knowledge bases, or content repositories.

## Trust

- **Trust score (0–1):** 0.45
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/kalicyh-rag)
- **Repository:** <https://github.com/kalicyh/mcp-rag>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "kalicyh-rag"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kalicyh-rag` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kalicyh-rag/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt