
Ultimate access to all questions.
A company is developing a generative AI (GenAI)-powered customer support application that uses Amazon Bedrock foundation models (FMs). The application must maintain conversational context across multiple interactions with the same user. The application must run clarification workflows to handle ambiguous user queries. The company must store encrypted records of each user conversation to use for personalization. The application must be able to handle thousands of concurrent users while responding to each user quickly.
Which solution will meet these requirements?
A
Use Amazon DynamoDB to store conversation history. Use AWS Lambda functions to orchestrate the conversation flow. Use Amazon S3 to store encrypted conversation records. Use Amazon API Gateway to handle user requests.
B
Use Amazon MemoryDB for Redis to store conversation context. Use AWS Step Functions to orchestrate clarification workflows. Use Amazon RDS with encryption enabled to store conversation records. Use Amazon EC2 Auto Scaling groups to handle concurrent users.
C
Use Amazon ElastiCache for Redis to store conversation context. Use AWS Step Functions to orchestrate clarification workflows. Use Amazon DynamoDB with server-side encryption to store conversation records. Use Amazon API Gateway and AWS Lambda to handle concurrent users.
D
Use Amazon Aurora to store conversation history. Use Amazon SQS to manage clarification workflows. Use Amazon S3 with server-side encryption to store conversation records. Use Amazon ECS to handle concurrent users.
E
Use Amazon DocumentDB to store conversation context. Use AWS Lambda functions to manage clarification workflows. Use Amazon Redshift to store encrypted conversation records. Use Amazon API Gateway to handle user requests.
F
Use Amazon Neptune to store conversation graphs. Use Amazon EventBridge to orchestrate clarification workflows. Use Amazon FSx to store encrypted conversation records. Use Amazon EKS to handle concurrent users.
No comments yet.