A widely used practitioner textbook covering how to build real-world applications on top of large language models. The RAG chapter is one of the most accessible technical explanations available: it walks through why retrieval is needed (models can't know everything and can't be retrained constantly), how documents are chunked and embedded into vectors, how a vector database finds semantically similar chunks, and how those chunks are inserted into a prompt so the model can "read before it answers." Huyen also covers practical failure modes — irrelevant retrieval, context window limits, and the difference between RAG and fine-tuning — in plain engineering language, without heavy math.
Because it's written for engineers building products rather than AI researchers, this book is an excellent on-ramp for PSM professionals who need to speak intelligently with vendors and IT teams about RAG-based knowledge assistants, understand the trade-offs of different architectures, and ask informed questions about how a proposed tool will ground its answers in PHA, MOC, and incident data rather than hallucinate.
Note: This is a link to a textbook that you can purchase. The curators of psm.ai do not receive any compensation for this referral.
