rag-query

Name: rag-query
Availability: InStock
Author: scanbott

Query the RawgrowthOS knowledge graph for grounded answers via HTTP API.

Updated Apr 21, 2026

Search Tags:#api #qa #rag #retrieval #curl #knowledge-graph

Ready to run

npx skills add https://github.com/scanbott/claude-skills --skill rag-query-scanbott

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: rag-query
Source: https://github.com/scanbott/claude-skills/tree/main/rag-query
Command: npx skills add https://github.com/scanbott/claude-skills --skill rag-query-scanbott

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Answers grounded in indexed documents can be hard to retrieve from the RawgrowthOS knowledge graph. This Skill provides a direct way to query the graph and obtain answers tied to relevant documents.

Core Features & Use Cases

Grounded Q&A: query the RawgrowthOS knowledge graph for answers grounded in indexed documents.
Flexible modes: supports hybrid, local, global, and naive modes for varying specificity.
Lightweight integration: uses a simple HTTP curl-based workflow and clear response formats to integrate with existing tools.

Quick Start

Just provide a question to the RAG service endpoint to get a grounded answer.

Frequently Asked Questions about rag-query

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

FAQPage Schema

How do I query a knowledge graph for grounded answers using RAG?▼

To retrieve grounded answers from a knowledge graph, send a JSON payload with your question and querying mode to the HTTP API endpoint. The RAG service returns a structured answer tied to indexed documents.

What is the difference between hybrid, local, global, and naive RAG querying modes?▼

Hybrid mode fits general querying, local mode targets specific entity lookups, global mode uncovers cross-domain patterns, and naive mode performs simple vector similarity retrieval from indexed documents.

Can I integrate RAG knowledge graph querying into existing tools via curl?▼

Yes, you can query the knowledge graph using a simple HTTP curl-based workflow. It accepts a JSON payload and returns clear response formats, enabling lightweight integration with your existing tools.

When do I need to use global mode for cross-domain knowledge graph retrieval?▼

You need global mode when you want to uncover cross-domain patterns within the knowledge graph. It queries indexed documents to return grounded answers spanning multiple domains, unlike specific local lookups.

Does the RAG query API require any external dependencies?▼

No, the RAG query API operates without external dependencies. It uses a lightweight curl-based workflow to query indexed documents and retrieve structured answers directly from the knowledge graph.