liveBook · Manning

External input

As explained in Building Specialized AI Systems

External knowledge is information outside a model’s embedded training knowledge, including proprietary, recent, specialized, or real-time information.

External input is knowledge beyond a model’s embedded training data, such as recent events, proprietary company information, specialized domain material, or real-time updates. section 1.5.1

Use external-input requirements to choose an optimization path:

  • Require retrieval-augmented approaches when the task depends on information outside the model’s pretrained knowledge. section 1.5.1
  • Avoid retrieval when general language tasks, creative writing, or basic reasoning can rely on pretrained knowledge. section 1.5.1
  • Add personalization or fine-tuning when the application requires consistent style, tone, format, or deeper domain reasoning. section 1.5.1

How Building Specialized AI Systems covers it

How deep it goes
Defines external knowledge needs and places them in a four-quadrant decision framework, without detailing retrieval implementation.
Examples
Uses recent events, proprietary company data, specialized domain information, real-time updates, creative writing, and basic reasoning.
What it assumes
Assumes awareness of model training data and application accuracy and consistency requirements.
What you can do after
Evaluate whether an application needs retrieval, pretrained knowledge alone, personalization, or fine-tuning.
How it connects
Connects external knowledge with retrieval-augmented generation, fine-tuning, personalization, pretrained knowledge, and domain reasoning.

Also explained in

Compare how 3 books explain external input →

Related concepts

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