A Generative AI Engineer has developed a RAG application to answer questions about a series of fantasy novels from the author's web forum. The text from the novels is chunked and embedded into a vector store along with metadata (page number, chapter number, book title). These chunks are retrieved based on the user's query and sent to an LLM to generate a response. The engineer initially selected the chunking strategy and its configurations based on intuition but now wants to choose the optimal values more systematically.

Which TWO strategies should the engineer use to optimize their chunking strategy and parameters? (Select two.)