AI World 2 · Grounded Answers · Stage 2

Cut and Embed

Chunks that keep their context, an embedding model that reads the language, and vectors no bigger than the budget.

Chunking strategies
Embedding models
Vector dimensions

Domain: AI and machine learning
World: AI World 2: Grounded Answers (Associate)
Game type: Solution board: Drop services into each row's slots, then run records through them.
Time: About 25 minutes on a first attempt (estimated)
Exam guides: DEA-C01Skill 2.4.6: Describe vectorization concepts (for example, Amazon Bedrock knowledge base)
AIF-C01Task 2.1: Explain the basic concepts of generative AI (GenAI); Task 3.1: Describe design considerations for applications that use foundation models (FMs)
MLA-C02Skill 1.2.5: Configure and use embedding models to transform text and image data into numerical representations; Skill 1.2.7: Prepare documents for Retrieval Augmented Generation (RAG) applications (for example, chunking strategies, metadata extraction); Skill 2.2.9: Optimize retrieval components and embedding models.
AIP-C01Skill 1.5.1: Develop effective document segmentation approaches to optimize retrieval performance for FM context augmentation (for example, by using Amazon Bedrock chunking capabilities, Lambda functions to implement fixed-size chunking, custom processing for hierarchical chunking based on content structure); Skill 1.5.2: Select and configure optimal embedding solutions to create efficient vector representations for semantic search (for example, by using Amazon Titan embeddings based on dimensionality and domain fit, by evaluating performance characteristics of Amazon Bedrock embedding models, by using Lambda functions to batch generate embeddings); Skill 5.2.1: Resolve content handling issues to ensure that necessary information is processed completely in FM interactions (for example, by using context window overflow diagnostics, dynamic chunking strategies, prompt design optimization, truncation-related error analysis)