AWS Certified Generative AI – Professional (AIP-C01) — Question 36

An enterprise application uses an Amazon Bedrock foundation model (FM) to process and analyze 50 to 200 pages of technical documents. Users are experiencing inconsistent responses and receiving truncated outputs when processing documents that exceed the FM's context window limits.
Which solution will resolve this problem?

Answer options

• A. Configure fixed-size chunking at 4,000 tokens for each chunk with 20% overlap. Use application-level logic to link multiple chunks sequentially until the FM's maximum context window of 200,000 tokens is reached before making inference calls.
• B. Use hierarchical chunking with parent chunks of 8,000 tokens and child chunks of 2,000 tokens. Use Amazon Bedrock Knowledge Bases built-in retrieval to automatically select relevant parent chunks based on query context. Configure overlap tokens to maintain semantic continuity.
• C. Use semantic chunking with a breakpoint percentile threshold of 95% and a buffer size of 3 sentences. Use the Amazon Bedrock RetrieveAndGenerate API call to dynamically select the most relevant chunks based on embedding similarity scores.
• D. Create a pre-processing AWS Lambda function that analyzes document token count by using the FM's tokenizer. Configure the lambda function to split documents into equal segments that fit within 80% of the context window. Configure the Lambda function to process each segment independently before aggregating the results.

Correct answer: C

Explanation

The correct answer, C, is effective because it uses semantic chunking to select the most relevant chunks based on embedding similarity, ensuring better responses from the FM. Options A and B focus on fixed and hierarchical chunking methods that may not adapt well to varying document needs, while option D relies on an independent processing method that does not optimize for relevance in the context of user queries.