What is the primary focus of the RAG Engineer skill?

It focuses on architecting retrieval-augmented generation systems, ensuring high-quality document processing and efficient data retrieval for LLM applications.

Is this skill compatible with any vector database?

Yes, the principles and patterns provided are database-agnostic and designed to optimize the data pipeline regardless of your specific storage or embedding provider.

Does this skill help with document chunking strategies?

Yes, it provides specific patterns for semantic chunking to maintain document context and structure, avoiding the pitfalls of fixed-size token limits.

Can I use it to improve search accuracy?

Absolutely. It guides users through implementing hybrid search—combining keyword and semantic matching—and adding reranking steps for maximum precision.

RAG Systems Architect

Name: RAG Systems Architect
Author: claudiodearaujo

byclaudiodearaujo

•

Ciencia de Datos y ML

Architects high-performance Retrieval-Augmented Generation systems using advanced chunking strategies and optimized vector search algorithms.

Acerca de

The RAG Systems Architect skill bridges the gap between raw document repositories and LLM understanding by optimizing the entire retrieval pipeline. It provides expert guidance on complex tasks such as semantic chunking, embedding model selection, and hierarchical retrieval to ensure AI applications receive high-context, relevant data. By focusing on the 'garbage in, garbage out' principle, this skill helps developers eliminate hallucinations and improve generation quality through hybrid search patterns, reranking strategies, and metadata pre-filtering.

Características Principales

Context window optimization to maximize LLM relevance
1 GitHub stars
Hybrid search implementation combining BM25 and vector similarity
Hierarchical retrieval for multi-level precision (paragraph to document)
Retrieval pipeline evaluation and reranking logic
Semantic chunking to preserve document structure and context

Casos de Uso

Building a semantic search engine for complex technical documentation
Optimizing vector database indexing for large-scale document processing
Reducing AI hallucinations by implementing multi-stage retrieval pipelines

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add claudiodearaujo/sistema-de-narra-o-de-livro rag-engineer

For use in Claude.ai and ChatGPT

Download Skill

GitHub