skills.rest
dtsong
dtsongCOMMUNITY
Explore all skills by this author →
GitHub

RAG Architecture

Design RAG pipelines by analyzing documents, chunking, embeddings, and vector databases.

1|1|Updated Feb 21, 2026
Search Tags:#semantic search#llm#rag#vector database#retrieval#chunking#embedding
One-click install
npx skills add https://github.com/dtsong/claude-code-windows-setup --skill rag-architecture
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: RAG Architecture
Source: https://github.com/dtsong/claude-code-windows-setup/tree/main/skills/council/oracle/rag-architecture
Command: npx skills add https://github.com/dtsong/claude-code-windows-setup --skill rag-architecture

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you design and optimize Retrieval-Augmented Generation (RAG) pipelines, ensuring efficient and accurate information retrieval for your AI applications.

Core Features & Use Cases

  • End-to-End Design: Covers document analysis, chunking, embedding, vector database selection, and retrieval optimization.
  • Customizable Strategies: Provides options for various chunking methods, embedding models, and vector stores.
  • Use Case: You need to build a RAG system for your company's internal knowledge base. This Skill will guide you through selecting the best chunking strategy for your documents, choosing an appropriate embedding model, and deciding on a vector database that fits your performance and cost requirements.

Quick Start

Design a RAG pipeline for a corpus of technical documentation, focusing on semantic chunking and the Pinecone vector database.

Frequently Asked Questions about RAG Architecture

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

FAQPage Schema
How do I design a RAG pipeline for technical documentation?▼

Designing a RAG pipeline involves analyzing source documents, defining chunking strategies, selecting embedding models, choosing a vector database, and optimizing retrieval processes like semantic or hybrid search.

What is the best chunking strategy for a retrieval-augmented generation system?▼

The best chunking strategy depends on your specific document types and volume. You can optimize retrieval by analyzing source documents and applying semantic chunking methods tailored to your query patterns.

How do I choose a vector database for my RAG architecture?▼

Choose a vector database by evaluating your requirements for query volume, update frequency, latency, and cost constraints. The selection process directly impacts your semantic search and retrieval performance.

Can I use hybrid search and reranking to improve LLM retrieval?▼

Yes, you can improve LLM retrieval by utilizing hybrid search and reranking strategies. These methods optimize the retrieval process by refining the relevance of chunks fetched from the vector database.

When should I optimize my RAG pipeline for cost versus latency?▼

Optimize your RAG pipeline for cost or latency based on your specific project constraints. You must balance document update frequency and query patterns against quality and performance requirements during the design phase.

Related Skills

Explore More Software Engineering Skills→
lrbjklrbjk

unity-project-scout

Assess Unity projects for version, render pipeline, packages, asmdefs, and folder structure.

Community
Intermediate
rukikotoorukikotoo
6

rag

Query the econometrics RAG knowledge base to retrieve relevant document chunks.

Community
Intermediate
JoeyJoziahJoeyJoziah

AgentDB Vector Search

Builds semantic vector search over document corpora with AgentDB.

Community
Advanced
masermediagroup-stackmasermediagroup-stack
1

embedding-optimization

Configure embedding models, chunking, and caching for RAG pipelines.

Community
Advanced