AWS · MLA-C02 · BETA
Knowledge bases and retrieval pipelines
MLA-C02 · Lesson 14 of 23 · 1:53:40
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Lesson 14 of the free MLA-C02 beta series (AWS Certified Machine Learning Engineer – Associate, domain 3, deployment and orchestration). In this lesson: managed and customer-managed knowledge bases, Retrieve and RetrieveAndGenerate with filters and reranking, incremental sync and direct ingestion, and refresh pipelines and retrieval design. With three quick checks and a recap, and AnyCompany Mobility, a car sharing service, as the running example.
Preview the topics
- Answers about rentals in Lisbon sometimes quote rules from Porto. Each document already has a metadata file with a city attribute. What should the ML engineer do?
- Fee tables are uploaded to Amazon S3 at random times, and the assistant must use a new table within minutes. The team wants the least code to run and maintain. What should the ML engineer build?
- An agent builds its own prompt, with its own instructions and tools, and only needs the most relevant chunks, with their sources. Which operation should it call?