skills.rest
infantesromeroadrian
infantesromeroadrianCOMMUNITY
Explore all skills by this author →
Website𝕏@infantes_adrianGitHub

rag-systems

Guide RAG pipeline design with chunking, embeddings, and hybrid search best practices.

Updated Aug 23, 2026
Search Tags:#embeddings#rag#evaluation#retrieval#reranking#vector-store#hybrid-search
One-click install
npx skills add https://github.com/infantesromeroadrian/arca-claude-code --skill rag-systems-infantesromeroadrian
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-systems
Source: https://github.com/infantesromeroadrian/arca-claude-code/tree/main/skills/rag-systems
Command: npx skills add https://github.com/infantesromeroadrian/arca-claude-code --skill rag-systems-infantesromeroadrian

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Retrieval-Augmented Generation pipelines often struggle with retrieving high-quality, contextually relevant passages. This Skill provides a consolidated set of best practices to improve retrieval quality, chunking behavior, embedding choices, and evaluation workflows across RAG systems.

Core Features & Use Cases

  • Chunking strategies and document structuring for reliable retrieval across long texts and codebases
  • Embeddings, vector stores, and indexing tactics for scalable, accurate search
  • Hybrid search, reranking, and MMR patterns to boost precision and recall
  • End-to-end evaluation frameworks (RAGAS and traditional metrics) with monitoring and guardrails
  • Advanced patterns (Self-RAG, Corrective RAG, GraphRAG) for robust knowledge work

Quick Start

Design, implement, and evaluate a complete RAG pipeline using chunking, embeddings, and hybrid search.

Frequently Asked Questions about rag-systems

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

FAQPage Schema
What's the best way to improve retrieval quality in a RAG pipeline?▼

Improve RAG pipeline retrieval quality by applying best practices for chunking strategies, embeddings selection, hybrid search patterns, and reranking to boost context precision and recall.

How do I evaluate retrieval-augmented generation systems?▼

Evaluate retrieval-augmented generation systems using end-to-end frameworks like RAGAS alongside traditional metrics to measure retrieval precision and monitor pipeline performance with guardrails.

When should I use hybrid search and reranking for vector store retrieval?▼

Use hybrid search and reranking for vector store retrieval when standard embeddings fail to distinguish highly similar passages, requiring Maximal Marginal Relevance patterns to boost precision.

Does this RAG guidance support chunking strategies for long documents and codebases?▼

Yes, this RAG guidance supports chunking strategies and document structuring specifically designed for reliable retrieval across long texts and complex codebases.

What are advanced patterns for robust retrieval-augmented generation?▼

Advanced patterns for robust retrieval-augmented generation include Self-RAG, Corrective RAG, and GraphRAG to handle complex knowledge work and multi-model orchestration across agents.

Can I apply these RAG best practices to domain-specific corpora?▼

Yes, you can apply these RAG best practices to domain-specific corpora, utilizing indexing tactics and multi-model orchestration to achieve scalable and accurate search results.

Related Skills

Explore More Data & Analytics Skills→
Himanshu040604Himanshu040604

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications.

Community
Advanced
ouakarouakar

ai-engineer

Design and deploy production AI/ML systems with MLOps pipelines and monitoring.

Community
Advanced
Yangel-hideYangel-hide

qmd

Search local knowledge stores with hybrid BM25, vector, and LLM reranking.

Community
Advanced
nmdranmdra
26

notebrain-assistant

Index and query Obsidian markdown vaults with ChromaDB for semantic retrieval and graph analysis.

Community
Advanced