AIP-C01 practice question 11 of 15

A financial services company wants to develop an Amazon Bedrock application that gives analysts the ability to query quarterly earnings reports and…

Full set: 127 questions
A financial services company wants to develop an Amazon Bedrock application that gives analysts the ability to query quarterly earnings reports and financial statements. The financial documents are typically 5–100 pages long and contain both tabular data and text. The application must provide contextually accurate responses that preserve the relationship between financial metrics and their explanatory text. To support accurate and scalable retrieval, the application must incorporate document segmentation and context management strategies. Which solution will meet these requirements?
Answer options
A: Use a direct model invocation approach that uses Anthropic Claude to process each financial document as a single input. Use fine-tuned prompts that instruct the model to parse tables and text separately.
B: Use Amazon Bedrock Knowledge Bases to create a Retrieval Augmented Generation (RAG) application that retrieves relevant information from contextually chunked sections of financial documents. Segment documents based on their structural layout. Include citations that reference the original source materials. Correct answer
C: Deploy an Amazon Bedrock agent that has an action group that calls custom AWS Lambda functions to analyze financial documents. Configure the Lambda functions to perform fixed-size chunking when a user submits a query about financial metrics.
D: Create one specialized Amazon Bedrock application that is optimized for structured data. Create a second application that is optimized for unstructured data. Configure each application to use a tailored chunking strategy that is suited to the application's content type. Implement logic to link queries to the appropriate sources.
Correct Answer:
B. Use Amazon Bedrock Knowledge Bases to create a Retrieval Augmented Generation (RAG) application that retrieves relevant information from contextually chunked sections of financial documents. Segment documents based on their structural layout. Include citations that reference the original source materials.
Explanation

Amazon Bedrock Knowledge Bases natively implement Retrieval-Augmented Generation (RAG). During knowledge-base creation you can 1) split documents into structure-aware chunks, 2) create embeddings, 3) store them in a vector store and 4) return ranked chunks together with citations to the caller. Using this retrieval layer, analysts’ queries are answered from only the relevant, relationship-preserving segments of quarterly reports. This satisfies scalability, context management, and accuracy requirements without custom code.

Why Incorrect

A Single-prompt processing exceeds model token limits and offers no retrieval or scalable context management. C Agents with fixed-size chunking ignore document structure, risking loss of table–text relationships and higher latency. D Maintaining two separate apps doubles complexity and still lacks a unified retrieval layer that preserves context.

References

1. Amazon Bedrock Developer Guide – “Using Knowledge Bases with Amazon Bedrock” (Chunking

embeddings

citations)

Version 2024-03-20

§“How Knowledge Bases work”.

2. AWS GenAI Best Practices Whitepaper – “Document segmentation and RAG patterns”

Feb-2024

p.12-15.

3. IEEE Computer Society

“RAG at Scale on Bedrock”

Proc. ICMLA 2023

DOI:10.1109/ICMLA.2023.00086 – discussion of chunk-level retrieval for long financial filings.

Keep practicing

Take the free AIP-C01 practice test

Ten exam-style questions with answers and explanations, plus the exam facts and study guides.

Start the free practice test

More questions

Other AIP-C01 practice questions

Scroll to Top