Prompt Stuffing vs RAG
As context windows on AI tools continue to grow, it becomes easier to add necessary information to the current request rather than go through the hassle of preprocessing your data and embedding it into a vector database. This talk will discuss both situations: when it is useful and appropriate to stuff the prompt, and when it is better to create embeddings and do a similarity search.
Examples will include a variety of data loaders and vector databases, as well as embedding algorithms.
About Kenneth Kousen
Ken Kousen is a Java Champion, several time JavaOne Rock Star, and a Grails Rock Star. He is the author of the Pragmatic Library books “Mockito Made Clear” and “Help Your Boss Help You,” the O'Reilly books “Kotlin Cookbook”, “Modern Java Recipes”, and “Gradle Recipes for Android”, and the Manning book “Making Java Groovy”. He also has recorded over a dozen video courses for the O'Reilly Learning Platform, covering topics related to Android, Spring, Java, Groovy, Grails, and Gradle.
His academic background include BS degrees in Mechanical Engineering and Mathematics from M.I.T., an MA and Ph.D. in Aerospace Engineering from Princeton, and an MS in Computer Science from R.P.I. He is currently President of Kousen IT, Inc., based in Connecticut.
More About Kenneth »