{"skill":{"slug":"afrexai-rag-production","displayName":"RAG Production Engineering","summary":"Build, optimize, and operate production-ready Retrieval-Augmented Generation systems with best practices in architecture, chunking, embedding, retrieval, eva...","tags":{"ai":"1.0.0","chunking":"1.0.0","embeddings":"1.0.0","evaluation":"1.0.0","latest":"1.0.0","llm":"1.0.0","production":"1.0.0","rag":"1.0.0","retrieval":"1.0.0","vector":"1.0.0"},"stats":{"comments":0,"downloads":130,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1774326653245,"updatedAt":1774327607873},"latestVersion":{"version":"1.0.0","createdAt":1774326653245,"changelog":"Initial release of RAG Production Engineering methodology.\n\n- Provides a comprehensive framework for building, optimizing, and operating Retrieval-Augmented Generation (RAG) systems in production environments.\n- Includes health check scoring, architecture decision guides, detailed document processing and chunking strategies, and chunk metadata standards.\n- Outlines phases: Architecture Decision, Document Processing & Chunking, and Embedding Model Selection.\n- Features best practices for chunking, embedding selection, retrieval evaluation, and monitoring.\n- Designed for teams implementing robust, production-ready RAG solutions.","license":"MIT-0"},"metadata":null,"owner":{"handle":"afrexai-cto","userId":"s176d3cp92hzph7jd2dtka26md83h078","displayName":"afrexai-cto","image":"https://avatars.githubusercontent.com/u/261321054?v=4"},"moderation":null}