liveBook · Manning

External memory

External memory is an addressable store of information maintained outside a model’s learned parameters or immediate context and made available for later retrieval.

How 2 Manning books explain it

Retrieval Augmented Generation, The Foundational Ideas

Information stored outside a model's learned parameters in an external, searchable collection that can be updated independently.

How it is used
Supplies language models with changeable, searchable knowledge without requiring that information to be learned in model parameters.
How deep it goes
Defines external knowledge and compares its benefits and tradeoffs, but does not detail retrieval implementation.
Examples
Uses Wikipedia, company databases, market reports, court rulings, and medical research as examples of external knowledge.
What you can do after
Evaluate the freshness, verifiability, update cost, and retrieval tradeoffs of external knowledge.

Read how Retrieval Augmented Generation, The Foundational Ideas explains external memory →

Context Engineering

Non-parametric memory is information outside a model that can be saved, retrieved, and updated at runtime.

How it is used
Provides continuity across independent agent calls and sessions through externally managed information.
How deep it goes
Explains storage tiers, context selection, load and promotion, and management practices without specifying an implementation.
Examples
Illustrates session and cross-session recall with a user's evening-flight preference.
What you can do after
Evaluate how external memory supports agent continuity and which information enters the context window.

Read how Context Engineering explains external memory →

Also covered in

What to know first

Related concepts

Questions about external memory

What is external memory?

External memory is an addressable store of information maintained outside a model’s learned parameters or immediate context and made available for later retrieval.

Which Manning books explain external memory?

Retrieval Augmented Generation, The Foundational Ideas and Context Engineering.

What should I know before learning external memory?

Manning books that teach external memory usually introduce language model, memory, recurrent neural network and parameter first.

What is the difference between external memory and parametric knowledge?

External memory is an addressable store of information maintained outside a model’s learned parameters or immediate context and made available for later retrieval. Parametric knowledge is information encoded in a model’s learned parameters through training, rather than supplied or retrieved from an external source at inference time.

What is external memory a kind of?

External memory is a kind of memory. Memory is a storage capability or mechanism for retaining information or computational state for later access or use.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.