AWS Certified Generative AI Developer - Professional
Get started today
Ultimate access to all questions.
Ultimate access to all questions.
No comments yet.
The company needs to improve the knowledge base to preserve semantic context across related paragraphs on the scale of the entire corpus of data.
Which solution will meet these requirements?
A
Configure the knowledge base to use fixed-size chunking. Set a 300-token maximum chunk size and a 10% overlap between chunks. Use an appropriate Amazon Bedrock embedding model.
B
Configure the knowledge base to use hierarchical chunking. Use parent chunks that contain 1,000 tokens and child chunks that contain 200 tokens. Set a 50-token overlap between chunks.
C
Configure the knowledge base to use semantic chunking. Use a buffer size of 1 and a breakpoint percentile threshold of 85% to determine chunk boundaries based on content meaning.
D
Configure the knowledge base not to use chunking. Manually split each document into separate files before ingestion. Apply post-processing reranking during retrieval.