liveBook · Manning

Passive retrieval architecture

As explained in Retrieval Augmented Generation, The Foundational Ideas

Passive retrieval is a retrieval strategy that performs search without dynamically deciding whether retrieval is necessary.

Passive retrieval performs a vector search for every user query, whether external evidence is needed or not. It connects an LLM’s parametric memory with non-parametric memory in an external vector database, making retrieval a fixed baseline rather than a query-dependent decision. section 9.0

Its indiscriminate behavior creates several production tradeoffs:

  • Wastes compute on queries that do not require retrieval. section 9.0
  • Pollutes context windows with irrelevant passages that crowd out useful answers. section 9.0
  • Can leave generation ungrounded despite presenting retrieval as protection against fabricated citations. section 9.0

Production baseline

A passive RAG service receives a user query, runs vector search automatically, and places the returned passages into the generation context. Adaptive systems such as Self-RAG instead retrieve on demand, may retrieve multiple times during generation, or skip retrieval entirely. section 9.0

How Retrieval Augmented Generation, The Foundational Ideas covers it

How deep it goes
Defines fixed query-time search and its failure modes, then contrasts it with adaptive retrieval without detailing implementation internals.
Examples
Uses automatic search for every user query and fabricated citations in commercial legal research tools as concrete examples.
What you can do after
Evaluate retrieval architectures by comparing unconditional search costs, context pollution, and grounding risks with adaptive alternatives.
How it connects
Connects RAG, vector databases, parametric memory, non-parametric memory, adaptive retrieval, and Self-RAG.

This explainer was generated by Manning's knowledge graph from the text of Retrieval Augmented Generation, The Foundational Ideas. The section links point to the parts of the book it draws on.