---
format: "aidr-story-markdown/v1"
id: "a6a39cb7eefe8f13c950c0ca8e5c1879d142c140860f7578f59bc21d3ab395e7"
canonical_url: "https://aidr.today/a6a39cb7?lang=en"
title: "Selecting a vector store for Amazon Bedrock Knowledge Bases"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-17T15:53:13.000Z"
category: "Infra"
topics: ["amazon-bedrock","rag","opensearch","aurora","s3-vectors"]
source_urls: ["https://aws.amazon.com/blogs/machine-learning/selecting-a-vector-store-for-amazon-bedrock-knowledge-bases/"]
summary: "Choosing the right vector store for your Amazon Bedrock Knowledge Bases RAG application affects performance and cost. This post compares Amazon OpenSearch Service, Amazon Aurora PostgreSQL with pgvector, and Amazon S3 Vectors across three RAG use cases, with benchmarks and a practical selection framework."
---

# Selecting a vector store for Amazon Bedrock Knowledge Bases

> [Open the canonical story](<https://aidr.today/a6a39cb7?lang=en>)

**Published:** 2026-09-17T15:53:13.000Z
**Category:** Infra
**Topics:** amazon\-bedrock, rag, opensearch, aurora, s3\-vectors

## Summary

Choosing the right vector store for your Amazon Bedrock Knowledge Bases RAG application affects performance and cost\. This post compares Amazon OpenSearch Service, Amazon Aurora PostgreSQL with pgvector, and Amazon S3 Vectors across three RAG use cases, with benchmarks and a practical selection framework\.

## Sources

- [Story source](<https://aws.amazon.com/blogs/machine-learning/selecting-a-vector-store-for-amazon-bedrock-knowledge-bases/>)