liveBook · Manning

Caching

As explained in Context Engineering

The technique of storing information or computation results for reuse to reduce repeated processing or retrieval.

Caching preloads reusable external context in an LLM system to reduce repeated retrieval and latency. Unlike query-time retrieval, it makes context available in advance; unlike direct injection, it focuses on reusable context rather than loading complete documents. section 3.0

How Context Engineering covers it

How deep it goes
Defines caching through cache-augmented generation and defers detailed trade-offs and selection criteria.
What you can do after
Understand how preloading reusable context differs from query-time retrieval and direct injection.
How it connects
Connects caching with retrieval, retrieval-augmented generation, and direct injection of external knowledge.

Also explained in

Compare how 49 books explain caching →

Related concepts

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