AIF-C01 Fundamentals of generative AI HARD
PRODUCTION SCENARIO
A publisher is building an Amazon Bedrock knowledge base that will hold 400 million text chunks. Vector storage is the largest cost line in the project. The team can accept slightly less precise retrieval in exchange for lower storage cost.

Which embedding choice will meet these requirements?

Answering here is anonymous. Nothing is saved unless you sign in.

Show answer and explanation

Answer: Binary embeddings, in a vector store that supports binary vectors

Binary vectors use 1 bit per dimension where float32 vectors use 32 bits per dimension, so they cut vector storage substantially at some cost in how precisely they represent the text. They require an embedding model and a vector store that support binary vectors, which Amazon OpenSearch Serverless and OpenSearch managed clusters do. Adding dimensions or scaling up the store raises cost instead.
Free

Keep practicing AIF-C01

undefined original AIF-C01 practice questions, each with an explanation and a source link. No account needed.

Start free practice set → Timed, explained, free