AWS · AIP-C01
Vector store architectures
AIP-C01 · Lesson 5 of 23 · 31:03
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Prepare for the AIP-C01 exam (AWS Certified Generative AI Developer - Professional). In this lesson: Bedrock managed and customer-managed knowledge bases, OpenSearch Service with ML connectors, Aurora with pgvector, DynamoDB for metadata, metadata files and query filters, performance at scale with shards and HNSW, data source connectors, incremental sync, and direct ingestion. Includes three original practice questions.
Preview the topics
- AnyCompany wants retrieval augmented generation with native connectors, managed embeddings, and a built-in reranker, without operating any vector database. What fits best?
- AnyCompany’s OpenSearch index serves product search, return policies, and supplier manuals together, and latency keeps rising as the index grows. Which change helps most?
- When a supplier discontinues a product, its page must disappear from the assistant’s answers within minutes, not at the next nightly sync. What should AnyCompany use?