---
title: "RAG / Direct Vector Search · agent retrieval pattern · Agent Fieldbook"
url: https://agentfieldbook.org/memory/retrieval/rag-semantic/
description: "Embed the query, run vector similarity search over the memory store, inject the top-k matches."
section: "Memory · Retrieval"
source: Agent Fieldbook — generated from the published page
---

# RAG / Direct Vector Search

Embed the query, run vector similarity search over the memory store, inject the top-k matches.

Verified against [arxiv.org](https://arxiv.org/abs/2005.11401)

- [arxiv.org](https://arxiv.org/abs/2005.11401)

## How it works

## At a glance

| Field | Value |
| --- | --- |
| Stage | Retrieval |
| Phase | Read |
| Used by | Mem0· Zep· LangChain retrievers· most vector-DB memory |

## Trade-off

Recall depends on embedding quality; irrelevant top-k or missed facts poison context.

## Basis

## Verified against

- [https://arxiv.org/abs/2005.11401](https://arxiv.org/abs/2005.11401)

The corpus does not rewrite vendor documentation. Where copy is quoted verbatim it is marked as such and attributed to its source.