AWS AI Practitioner
A developer is building a RAG-based application. The developer needs to prepare company documents to be stored in a knowledge base for semantic search. Which step should the developer perform?
A
Fine-tune the foundation model on company documents
B
Create embeddings from document chunks
✓ Correcta
C
Store documents as plain text in a relational database
D
Convert all documents to CSV format before storing
Explicación
Creating embeddings from document chunks is a fundamental step in building RAG systems. Documents are split into chunks, and each chunk is converted into vector embeddings using an embedding model. These embeddings enable semantic similarity search when retrieving relevant context for the LLM.