AIF-C01 Question 112
Select 4You are developing an AI-powered recommendation system that uses embeddings to store and retrieve item similarity data. You need to choose an AWS service that supports storing and querying embeddings efficiently within a vector database. Which of the following AWS services are suitable for this use case?
- A
Amazon OpenSearch Service
- B
Amazon Aurora
- C
Amazon Neptune
- D
Amazon DocumentDB (with MongoDB compatibility)
- E
Amazon RDS for PostgreSQL
- F
AWS Glue
Show answer and explanation
Correct answers: A, C, D, E
Explanation
Several AWS services can be used to store and query embeddings based on the use case. Amazon OpenSearch Service provides built-in vector search capabilities, making it ideal for storing embeddings for similarity searches. Amazon Neptune supports graph-based use cases involving embeddings. Amazon DocumentDB and Amazon RDS for PostgreSQL are also suitable for storing embeddings, with RDS for PostgreSQL supporting vector operations via extensions like pgvector. AWS Glue, however, is not relevant as it focuses on data integration rather than storage or querying of embeddings.
- A. Correct.
Amazon OpenSearch Service supports vector search capabilities, making it a suitable choice for storing and querying embeddings efficiently.
- B. Incorrect.
Amazon Aurora is a relational database that does not inherently support vector operations or embeddings natively.
- C. Correct.
Amazon Neptune is a graph database that supports storing and querying embeddings for graph-based use cases, making it relevant in this context.
- D. Correct.
Amazon DocumentDB (with MongoDB compatibility) can store embeddings and supports flexible querying, making it a suitable candidate.
- E. Correct.
Amazon RDS for PostgreSQL supports extensions like pgvector, enabling it to store and query embeddings effectively.
- F. Incorrect.
AWS Glue is a data integration service and is not designed for storing or querying embeddings.