liveBook · Manning

State

As explained in Grokking AI Applications

The stored sequence of prior user inputs and model outputs that represents an ongoing conversation.

State is the stored sequence of prior user messages and model outputs. Forwarding that sequence with later requests gives an LLM application the context needed to continue an ongoing conversation. section 1.4

Continuing a conversation

After a user message produces a model response, the application stores both. When the user sends another message, it forwards the earlier exchange so the model can respond with conversational context rather than treating the request as isolated. section 1.4

How Grokking AI Applications covers it

How deep it goes
Defines the storage-and-forward operation but defers its implementation details.
Examples
Uses an ongoing chat where subsequent requests receive earlier user messages and model outputs.
What you can do after
Operate applications that preserve conversational context across requests.
How it connects
Connects conversation state with context, prompts, LLMs, and Retrieval-Augmented Generation.

Also explained in

Compare how 39 books explain state →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Grokking AI Applications. The section links point to the parts of the book it draws on.