RAG Architecture Patterns

Name: RAG Architecture Patterns
Author: claude-dev-suite

Comprehensive patterns for Retrieval-Augmented Generation, including chunking, hybrid search, re-ranking, and evaluation strategies.

triggers:RAGretrieval augmented generationdocument Q&Aknowledge base chatbotsemantic search pipelinechunking strategy

GitHub SKILL.md

What it does

This skill provides the agent with a standardized blueprint for designing and implementing Retrieval-Augmented Generation (RAG) systems. It moves beyond simple retrieval to offer production-grade patterns for data ingestion and query processing.

When to use it

Use this skill when the user needs to build a knowledge-base chatbot, a document Q&A system, or any pipeline involving semantic search and LLM augmentation.

What's included

Instructions: Detailed guidance on chunking strategies (recursive, semantic, document-aware), retrieval techniques (Hybrid Search combining BM25 and vector search), and the use of re-ranking models to improve precision.
Evaluation: Metrics for measuring context relevance and faithfulness using tools like RAGAS.
Anti-Patterns: A checklist of common mistakes to avoid, such as oversized chunks or ignoring source attribution.

Compatible agents

Claude Code, and other MCP-compatible agents supporting file and tool operations.

Not yet audited

This skill has not been reviewed by our automated audit pipeline yet.

Information

Repository: claude-dev-suite
Stars: 20

More from claude-dev-suite

Deployment Strategies

Guidance and recipes for zero-downtime production deployments: blue-green, canary, rolling updates, rollback checks, and DB migration coordination.

Spring Authorization Server Specialist

Expert guidance for building OAuth 2.1 and OpenID Connect (OIDC) providers using the Spring Authorization Server framework.

Lightning Service Provider (LSP) Integration

Guides agents in integrating with Lightning Service Providers to solve inbound liquidity issues using BLIPs and JIT channels.

Related Skills

Prompt Engineering Patterns

A practical collection of prompt engineering techniques and patterns for building reliable, controllable LLM prompts: CoT, few-shot, structured outputs, templat

DSPy — Declarative LM Programming

Use DSPy to build declarative, modular LM pipelines, optimize prompts automatically, and assemble reliable RAG/agent systems with structured signatures and opti

Microsoft Foundry Classic — Expert Guidance

Comprehensive guidance for building, configuring, troubleshooting, and deploying Microsoft Foundry Classic agents and integrations.

OpenViking Memory Plugin

Provides automatic long-term memory capture and recall for OpenClaw agents: auto-capture, auto-recall, and memory management tools for more context-aware conver

Synalinks Framework

Keras-inspired framework for building structured, neuro-symbolic LLM programs with DataModel schemas, modular Programs, and training/optimization tools.

libagent

Agent orchestration library for conversational AI — coordinates LLM completions, memory, tool execution, and multi-turn flows; useful for building chat agents a

py_mnn_kb — Local GraphRAG Knowledge Base

Local GraphRAG knowledge base backed by SQLite + MNN embeddings; provides CLI tools to build, note, query, and check status for an on-device RAG KB.

elizaOS (crypto skills)

TypeScript framework and character system for building autonomous, multi-platform AI agents with onchain (Solana) integrations and RAG memory.

RAG Architecture Patterns

What it does

When to use it

What's included

Compatible agents