Vector Stores at Professional Scale

Choosing and operating the vector layer: Bedrock Knowledge Bases, OpenSearch neural search, Aurora and S3 options, metadata frameworks, sharding and hierarchical indexing, and the sync pipelines that keep indexes honest.

Content current as of 2026-10.

Lessons

1. Choosing the vector layer
2. Metadata frameworks, sharding, hierarchical indexes
3. Keeping indexes in sync with their sources

Sources

• AIP-C01 exam guide — Content Domain 1 (task 1.4)
• Amazon Bedrock user guide — Knowledge Bases
• Amazon OpenSearch Service — neural search on OpenSearch Serverless
• Amazon Bedrock user guide — Confluence data source connector (incremental sync)