Where can you store embeddings on AWS?
Why C is the answer
Amazon OpenSearch Service
Amazon OpenSearch Service can store embeddings and search them. Aurora is another option.
In detail
- OpenSearch Service can store and search vectors.
- Aurora is another option.
Use case
An illustrative scenario, not a real incident.
A team that already runs OpenSearch Service stores its embeddings there, beside its search workloads.
See it in different ways
sequenceDiagram participant U as User participant K as Knowledge base participant M as Foundation model U->>K: Question K-->>M: Relevant chunks with the question M-->>U: Grounded answer
sequenceDiagram participant U as User participant K as Knowledge Bases participant S as Vector store participant M as Foundation model U->>K: Question K->>S: Finds similar chunks S-->>K: Passages K->>M: Prompt with passages M-->>U: Answer
mindmap
root(("Vector store"))
n1["Search"]
n2["Amazon OpenSearch Service"]
n3["Database"]
n4["Amazon Aurora"]Key point: OpenSearch Service can store vectors.
Why the other options are wrong
- A. AWS Budgets
- Budgets tracks spending.
- B. Amazon Route 53
- Route 53 is DNS.
- D. AWS Identity and Access Management
- IAM manages access.

