SearchRequest

As explained in Spring AI in Action

SearchRequest is a Spring AI request object that specifies the query and filtering or ranking parameters for vector-store similarity retrieval.

How Spring AI in Action covers it

How deep it goes

Explains query, metadata filtering, Top-K, and similarity thresholds through Java builder examples, without detailing retrieval internals.

Examples

Uses GameRulesService to retrieve game-specific rule chunks with query, normalized gameTitle filtering, Top-K, and similarity threshold settings.

What it assumes

Assumes a configured VectorStore and document metadata, while demonstrating request construction and filter expression syntax.

What you can do after

Build it from scratch with Spring AI builder methods and tune retrieved context for relevance, coverage, token usage, and cost.

How it connects

Connects vector stores, metadata filtering, Top-K, similarity thresholds, RAG, and QuestionAnswerAdvisor.

liveBookmanning.com

Read Spring AI in Action on liveBook Get the book at manning.com

Related concepts

• thresholdconfigured by · A threshold is a boundary value against which a quantity is compared to determine whether a condition is met or an action or decision is triggered.
• top-k samplingconfigured by · Top-k sampling is a decoding technique that restricts each next-token selection to the k candidates with the highest probabilities, then samples from those candidates.
• QuestionAnswerAdvisorused by · QuestionAnswerAdvisor is a Spring AI advisor that searches a vector store for documents related to a question and adds them as context to a prompt.
• 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.

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