rag-system-builder

name	rag-system-builder
description	Build Retrieval-Augmented Generation (RAG) Q&A systems with Claude or OpenAI. Use for creating AI assistants that answer questions from document collections, technical libraries, or knowledge bases.
type	reference
version	1.2.0
last_updated	"2026-01-02T00:00:00.000Z"
category	data
related_skills	["knowledge-base-builder","semantic-search-setup","document-rag-pipeline"]
capabilities	[]
requires	[]
tags	[]

Rag System Builder

Overview

This skill creates complete RAG (Retrieval-Augmented Generation) systems that combine semantic search with LLM-powered Q&A. Users can ask natural language questions and receive accurate answers grounded in your document collection.

Quick Start

from sentence_transformers import SentenceTransformer
import anthropic

# Setup
model = SentenceTransformer('all-MiniLM-L6-v2')
client = anthropic.Anthropic()

# Retrieve context (simplified)
query = "What are the safety requirements?"
query_embedding = model.encode(query, normalize_embeddings=True)
# ... search for similar chunks ...

# Generate answer
response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": f"Context: {context}\n\nQuestion: {query}"}]
)
print(response.content[0].text)

When to Use

• Building AI assistants for technical documentation
• Creating Q&A systems for standards libraries
• Developing chatbots with domain expertise
• Enabling natural language queries over knowledge bases
• Adding AI-powered search to existing document systems

Prerequisites

• Knowledge base with extracted text (see knowledge-base-builder)
• Vector embeddings for semantic search (see semantic-search-setup)
• API key: ANTHROPIC_API_KEY or OPENAI_API_KEY

Related Skills

• knowledge-base-builder - Build the document database first
• semantic-search-setup - Generate vector embeddings
• pdf/text-extractor - Extract text from PDFs
• document-rag-pipeline - Complete end-to-end pipeline