AWS · AIF-C01
Choosing and configuring FMs
AIF-C01 · Lesson 9 of 17 · 1:10:01
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 AIF-C01 exam (AWS Certified AI Practitioner). In this lesson: the criteria for choosing a foundation model, inference parameters like temperature, top K, top P, and the maximum length, Retrieval Augmented Generation with Amazon Bedrock Knowledge Bases, chunking and reranking, and the vector databases on AWS, from OpenSearch Service to Aurora and RDS for PostgreSQL with pgvector. Includes three original practice questions.
Preview the topics
- AnyCompany wants claim summaries that are consistent and factual, with as little creative variation as possible. Which change helps most?
- AnyCompany’s assistant must answer from policy documents that change every week, and cite them, without retraining any model. Which approach fits?
- AnyCompany’s data team already runs PostgreSQL on Amazon RDS, and wants to store embeddings right next to its policy tables. Which option fits?