# Amazon — Selecting a vector store for Amazon Bedrock Knowledge Bases

- Company: Amazon (amazon.com)
- Announced: 2026-09-17T15:53:13+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://aws.amazon.com/blogs/machine-learning/selecting-a-vector-store-for-amazon-bedrock-knowledge-bases/
- Record: https://forck.live/items/11735-selecting-a-vector-store-for-amazon-bedrock-knowledge-bases
- Subject: Bedrock / Nova

Amazon's guide compares three vector store backends for Amazon Bedrock Knowledge Bases: Amazon OpenSearch Service, Amazon Aurora PostgreSQL with pgvector, and Amazon S3 Vectors, across distinct RAG use cases. It explains how vector databases fit into RAG solutions and provides guidance on selecting the best option based on latency, cost, and search requirements.

## Evidence

Verbatim from https://aws.amazon.com/blogs/machine-learning/selecting-a-vector-store-for-amazon-bedrock-knowledge-bases/:

> This post focuses on the customer-managed path, comparing the three supported backends: Amazon OpenSearch Service , Amazon Aurora PostgreSQL with pgvector , and Amazon S3 Vectors , a capability of Amazon Simple Storage Service (Amazon S3), across distinct RAG use cases.

---

Record: https://forck.live/items/11735-selecting-a-vector-store-for-amazon-bedrock-knowledge-bases
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md