Câu 21: AWS Certified Generative AI Developer - Professional AIP-C01

A retail company is developing a customer service application that must process 10,000 daily queries about products, orders, and warranties. The application must be able to respond to queries about 50,000 product documents that are updated every day. The application must integrate with an order management API to check the status of orders and to help process returns. The application must maintain context throughout multi-turn interactions with customers. The company must collect complete audit trails for application responses. Which solution will meet these requirements with the LEAST operational overhead?

1. A. Deploy a fine-tuned Amazon Bedrock Anthropic Claude model for each product category. Create AWS Lambda functions to connect each model to the order management API. Store conversation history in Amazon DynamoDB.
2. B. Create a custom model that uses continued pre-training on Amazon Bedrock to handle all product documentation. Set up an Amazon API Gateway REST API that uses AWS Lambda functions to connect the model to the order management API.
3. C. Use Amazon SageMaker AI with containers to deploy models. Use Amazon Kendra to search product documents. Use AWS Step Functions to orchestrate calls to the order management API.
4. D. Use an Amazon Bedrock agent with action groups to integrate with the order management API. Associate an Amazon Bedrock knowledge base with the agent to search product documentation by using Retrieval Augmentation Generation (RAG). Enable trace events to capture audit trails. — đáp án hiện tại