---
title: "Discussion on \"One query is never enough: why top RAG systems search three times\" | Hashnode"
description: "Discussion on \"One query is never enough: why top RAG systems search three times\". LangChain has MultiQueryRetriever. LlamaIndex has SubQuestionQueryEngine. Every serious RAG framework decomposes user questions into multiple search queries before hitting the vector database.\nWhy? Because a single embedding compresses your entire qu..."
url: "https://hashnode.com/posts/one-query-is-never-enough-why-top-rag-systems-search-three-times/69ceaf2320ffea80ace78308"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [One query is never enough: why top RAG systems search three times](https://velesdb.hashnode.dev/one-query-is-never-enough-why-top-rag-systems-search-three-times?utm_source=hashnode&utm_medium=feed)

LangChain has MultiQueryRetriever. LlamaIndex has SubQuestionQueryEngine. Every serious RAG framework decomposes user questions into multiple search queries before hitting the vector database. Why? Because a single embedding compresses your entire qu...

Apr 2 · 10 min read · velesdb.hashnode.dev  
Updated Apr 5  
Read the article

## Written by

[Julien L](https://hashnode.com/@wiscale)

@wiscale · Paris, France

  
[View profile](https://hashnode.com/@wiscale)

Building VelesDB & developer tools | Blogging about databases, dev products, and tech.

Developer and maker building VelesDB — a modern database solution for developers. I write about databases, developer tools, product building, and everything in between. Follow my journey as I ship products and share what I learn along the way.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
