skills.rest
aleonsa
aleonsaCOMMUNITY
Explore all skills by this author →
GitHub

rag-patterns

Provides design patterns and best practices for building Retrieval-Augmented Generation pipelines.

1|Updated Mar 10, 2026
Search Tags:#llm#rag#vector database#retrieval#embedding#ragas
One-click install
npx skills add https://github.com/aleonsa/claude-config --skill rag-patterns-aleonsa
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-patterns
Source: https://github.com/aleonsa/claude-config/tree/main/claude/skills/rag-patterns
Command: npx skills add https://github.com/aleonsa/claude-config --skill rag-patterns-aleonsa

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides comprehensive guidance and best practices for building and optimizing Retrieval-Augmented Generation (RAG) pipelines, ensuring efficient and accurate information retrieval for LLM applications.

Core Features & Use Cases

  • End-to-End RAG Architecture: Covers document ingestion, chunking strategies, embedding models, vector stores, retrieval methods, and re-ranking.
  • Advanced Techniques: Explores HyDE, multi-query retrieval, and parent-document retrieval.
  • Evaluation Framework: Details how to use RAGAS for robust pipeline evaluation and debugging.
  • Use Case: When designing a RAG system for customer support documentation, use this Skill to select the optimal chunking strategy, choose a suitable embedding model, and implement hybrid retrieval for better query matching.

Quick Start

Use the rag-patterns skill to understand the RAG pipeline overview and its components.

Frequently Asked Questions about rag-patterns

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

FAQPage Schema
How do I build a production-grade RAG pipeline for LLM applications?▼

To build a RAG pipeline, you need to implement document ingestion, chunking strategies, embedding models, vector stores, retrieval methods, and re-ranking. This ensures efficient and accurate information retrieval for LLM applications.

What's the best way to evaluate RAG system accuracy and debug retrieval issues?▼

Evaluating RAG system accuracy is best done using the RAGAS framework. RAGAS provides robust pipeline evaluation and debugging capabilities to measure information retrieval performance and identify inaccuracies in your LLM application.

What are the best chunking strategies and embedding models for RAG document ingestion?▼

Optimal RAG document ingestion requires selecting appropriate chunking strategies and embedding models tailored to your data. These choices directly impact vector store indexing and query matching efficiency for accurate retrieval.

How does hybrid retrieval and re-ranking improve RAG query matching?▼

Hybrid retrieval and re-ranking improve RAG query matching by combining multiple search methods and prioritizing the most relevant documents. This approach significantly enhances information retrieval accuracy over standard vector similarity searches.

When should I use advanced RAG techniques like HyDE and multi-query retrieval?▼

Use advanced RAG techniques like HyDE and multi-query retrieval when standard retrieval methods fail to capture complex query intent. These approaches generate diverse queries to fetch richer context, improving LLM response accuracy.

Can I use RAG patterns for customer support documentation?▼

Yes, you can apply RAG patterns to customer support documentation. They guide you in selecting optimal chunking strategies, suitable embedding models, and hybrid retrieval to ensure better query matching and accurate responses.

Related Skills

Explore More Software Engineering Skills→
SignmanalSignmanal
1

chroma

Store and query vector embeddings with metadata filtering for RAG applications.

Community
Intermediate
OmidZamaniOmidZamani
120

dspy-rag-pipeline

Build and optimize RAG pipelines with ColBERTv2 in DSPy.

Community
Advanced
ExpeditoJExpeditoJ

synapse

Inject contextual rules into AI prompts across eight processing layers.

Community
Advanced
AI-SafeterAI-Safeter
10

rag-implementation

Integrate external document sources into LLM retrieval pipelines with vector stores.

Community
Advanced