This is a dedicated watch page for a single video.
A Generative AI Engineer has developed a RAG application designed to answer questions about a series of fantasy novels discussed on the author’s web forum. The novels have been chunked and embedded into a vector store containing metadata like page numbers, chapter titles, and book names. User queries retrieve relevant chunks, which are then processed by an LLM for generating responses. Initially, the engineer used intuition to select chunking strategies and configurations but now wants a systematic approach to optimize these settings. Which TWO approaches should the engineer adopt to refine the chunking strategy and parameters? (Choose two.)