Atomic query
An atomic query is an individual information request representing one distinct need extracted from a compound query and answerable independently.
Retrieval Augmented Generation, The Foundational Ideas
A sub-query is an individual query produced by dividing a larger information need into smaller retrieval or reasoning steps.
- How it is used
- Structures multi-part retrieval into individually executable information needs before checking whether their combined evidence answers the user.
- How deep it goes
- Works through decomposition, routing, summarization, and bounded verification, with Python classes; notes that its single-searcher routing differs from the original design.
- Examples
- Uses a UK-versus-EU domestic-PEP compliance comparison and a follow-up query derived from a retrieved guidance citation.
- What you can do after
- Apply it via LevelRAG-style planning to route and summarize separate retrieval tasks, then issue supplemental queries when evidence is incomplete.
Read how Retrieval Augmented Generation, The Foundational Ideas explains atomic query →
Build an Advanced RAG Application (From Scratch)
An atomic sub-query is an individual query representing one information need extracted from a compound query.
- How it is used
- Improves compound-question retrieval by isolating information needs before routing and search.
- How deep it goes
- Defines decomposition, gives prompt rules and outputs, and stops short of detailing synthesis internals.
- Examples
- Uses an Uber–Lyft financial comparison and a simple Uber revenue question to demonstrate splitting and pass-through.
- What you can do after
- Build it from scratch as a Python decomposer that emits focused JSON sub-queries for downstream retrieval.
Read how Build an Advanced RAG Application (From Scratch) explains atomic query →
What to know first
- lexical searchLexical search retrieves or ranks items by matching query terms or other surface-text features against indexed content, often using sparse representations and statistical weighting.
- similarity searchSimilarity search is a retrieval technique that finds or ranks items by their similarity to a query, often by comparing feature or vector representations under a similarity or distance measure.
- retrieval-augmented generationRetrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
- web searchWeb search is the retrieval of information from publicly accessible World Wide Web pages or indexes in response to a query.
Related concepts
- query decompositionproduced by · Query decomposition is the technique of dividing a complex information need into smaller subqueries or subtasks that can be processed separately.
- compound querypart of · A compound query combines multiple conditions, subqueries, or information needs to express complex search or retrieval criteria.
Questions about atomic query
What is atomic query?
An atomic query is an individual information request representing one distinct need extracted from a compound query and answerable independently.
Which Manning books explain atomic query?
Retrieval Augmented Generation, The Foundational Ideas and Build an Advanced RAG Application (From Scratch).
What should I know before learning atomic query?
Manning books that teach atomic query usually introduce lexical search, similarity search, retrieval-augmented generation and web search first.
What is atomic query part of?
Atomic query is part of compound query. A compound query combines multiple conditions, subqueries, or information needs to express complex search or retrieval criteria.
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.

