ModelRefs / Multi-Query Retrieval — AI Glossary
Multi-Query Retrieval — AI Glossary
Generating multiple query variants from one user query, retrieving independently for each, and merging deduplicated results.
Overview
Multi-query retrieval (LangChain MultiQueryRetriever) prompts the LLM to generate N perspectives on the query, runs each as a separate retrieval, and unions results after deduplication. Improves recall by covering different facets of the query. Increases retrieval latency proportionally; usually run in parallel.
Reference details
| Topic | rag |
|---|---|
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Multi-Query Retrieval — AI Glossary.
Frequently asked questions
What is Multi-Query Retrieval?
Generating multiple query variants from one user query, retrieving independently for each, and merging deduplicated results.
What concepts are related to Multi-Query Retrieval?
Closely related concepts include query expansion, fusion retrieval, dense retrieval.