This is a dedicated watch page for a single video.
A Generative AI Engineer has developed a Retrieval-Augmented Generation (RAG) application to find answers for questions about a series of fantasy novels posted on the author’s online forum. The text from the novels is divided into chunks, embedded into a vector store with metadata (e.g., page number, chapter number, and book title), retrieved in response to user queries, and passed to a language model for generating answers. Initially, the engineer relied on intuition to select the chunking strategy and related configurations, but now wants to optimize these choices using a more systematic approach. Which TWO strategies should the Generative AI Engineer adopt to refine their chunking strategy and parameters? (Choose two.)