Step-back prompting
Step-back prompting is a prompting technique that reframes a specific question as a broader, more abstract question before addressing the original question.
Essential GraphRAG
Step-back prompting is a prompting technique that reformulates a specific question into a more general question or perspective before retrieval or generation.
- How it is used
- Improves vector-retrieval accuracy and recall by aligning detailed user questions with broader document language.
- How deep it goes
- Defines the rationale, contrasts zero-shot and few-shot prompting, and provides a prompt and generation function without detailing retrieval evaluation.
- Examples
- Uses Estella Leopold’s education, Thierry Audel’s career, and prompt examples involving The Police and Jan Sindel.
- What you can do after
- Apply it via an LLM prompt and generation function to produce broader questions for subsequent vector retrieval.
AI Agents and Applications
Step-back question generation is a technique that reformulates a specific question into a broader question to elicit useful contextual information for retrieval or answering.
- How it is used
- Improves RAG retrieval by adding foundational context before final answer synthesis.
- How deep it goes
- Explains the two-retrieval workflow and chain integration, but does not descend into retrieval or embedding internals.
- Examples
- Uses Brighton travel advice, coastal-city abstraction, prompt templates, and an integrated retriever chain.
- What you can do after
- Apply it via ChatOpenAI-style chains and a vector-store retriever to broaden context before answering.
Read how AI Agents and Applications explains step-back prompting →
Related concepts
- query rewritingkind of · Query rewriting is the transformation of a query into an alternative formulation intended to better support its execution or retrieval while preserving its intended meaning or behavior.
- language modeluses · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
- retrieval-augmented generationused by · Retrieval-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.
- promptproduced by · An input, typically containing instructions or context, supplied to an artificial-intelligence model to guide or elicit its output.
- vector databaseuses · A vector database is a data-management system that stores and indexes numerical vector representations and supports retrieval through similarity or distance searches.
- query optimizationkind of · Query optimization is the process of transforming a query or selecting an execution strategy to improve retrieval effectiveness or efficiency while preserving intended results.
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.