Designs and optimizes high-performance Retrieval-Augmented Generation (RAG) systems with advanced chunking, embedding, and retrieval strategies.
The RAG Engineer skill transforms Claude into a specialized systems architect for building robust AI knowledge bases. It provides expert guidance on the entire RAG pipeline, from intelligent document chunking and embedding model selection to hybrid search implementation and context window optimization. By prioritizing retrieval quality as the foundation for generation, it helps developers eliminate hallucinations, manage token costs, and build production-ready systems that bridge the gap between raw data and LLM understanding.
주요 기능
01Evaluation metrics for retrieval quality (MRR, NDCG)
02Advanced semantic chunking and document preprocessing
03Vector database architecture and scaling strategy