Short-Term Memory

In the previous lesson, you learned why short-term memory is necessary — without it, every prompt reaches the LLMA model trained on text to predict the next token, and so to generate language. cold, with no knowledge of what came before.

In this lesson, you will learn how short-term memory is modeled as a graph, what propertiesA named value stored on a node or a relationship. each message nodeA vertex in a graph. In a property graph it can carry labels and properties. stores, and what the library does automatically when you add a message.