{"skill":{"slug":"afrexai-rag-engineering","displayName":"RAG Engineering","summary":"Expert guidance to build, optimize, and debug production-ready Retrieval-Augmented Generation (RAG) systems using a complete methodology from architecture to...","tags":{"ai":"1.0.0","embedding":"1.0.0","latest":"1.0.0","llm":"1.0.0","rag":"1.0.0","retrieval":"1.0.0","vector":"1.0.0"},"stats":{"comments":0,"downloads":538,"installsAllTime":1,"installsCurrent":1,"stars":1,"versions":1},"createdAt":1771593891103,"updatedAt":1777525279886},"latestVersion":{"version":"1.0.0","createdAt":1771593891103,"changelog":"Initial release of the RAG Engineering skill — a comprehensive guide for building, optimizing, and debugging production-grade Retrieval-Augmented Generation (RAG) systems.\n\n- Introduces a structured methodology covering RAG architecture assessment, data ingestion, preprocessing, and chunking.\n- Provides health check metrics and decision trees for system design choices.\n- Includes step-by-step data processing pipelines and extraction strategies by document type.\n- Offers detailed chunking methods, decision guides, and quality benchmarks.\n- Supplies practical checklists for cleaning and metadata enrichment.\n- Designed to support both prototyping and scalable production use-cases.","license":null},"metadata":null,"owner":{"handle":"1kalin","userId":"s17e1q0nx23qnh4n429zzqc05x83hvsw","displayName":"1kalin","image":"https://avatars.githubusercontent.com/u/15705344?v=4"},"moderation":null}