MENU
A company is building a generative AI (GenAI) application that uses Amazon Bedrock APIs to process complex customer inquiries. During peak usage periods, the application experiences intermittent API timeouts that cause issues such as broken response chunks and delayed data delivery. The application struggles to ensure that prompts remain within token limits when handling complex customer inquiries of varying lengths. Users have reported truncated inputs and incomplete responses. The company has also observed foundation model (FM) invocation failures.
The company needs a retry strategy that automatically handles transient service errors and prevents overwhelming Amazon Bedrock during peak usage periods. The strategy must also adapt to changing service availability and support response streaming and token-aware request handling.
Which solution will meet these requirements?
Option B best meets all requirements because it combines AWS-recommended resiliency patterns for transient failures with streaming-aware handling and adaptive protection against cascading retries during peak load. When timeouts and throttling occur, nave retries can amplify traffic and worsen outages. Exponential backoff with jitter is the standard AWS best practice because it spreads retry attempts over time, reduces synchronized retry storms, and lowers the probability of repeatedly colliding with service limits.
The requirement also states the strategy must ''adapt to changing service availability'' and ''prevent overwhelming Amazon Bedrock.'' A circuit breaker pattern directly addresses this by temporarily stopping or reducing retries when failure rates exceed a threshold, allowing the system to degrade gracefully instead of continually hammering the service. This is a key mechanism to prevent cascading failures during throttling events.
Because the application uses response streaming and experiences broken chunks, the retry strategy must be streaming-aware. A streaming response handler that detects chunk delivery timeouts and buffers already received chunks prevents the user from losing progress when a connection drops. Resuming from the last successfully received chunk minimizes redundant generation and reduces additional load on the model compared with restarting the entire stream. This supports better user experience and better service efficiency during intermittent failures.
Token-aware request handling is supported in this architecture because the application can apply token budgeting before invoking the model (for example, trimming or summarizing excessive context) while still preserving streaming output behavior. Option B provides the correct backbone for this by focusing on adaptive control and robust streaming recovery.
Option A is too simplistic and risks retry storms. Option C combines conflicting elements (global token limit, cached completions for streaming) and includes impractical ''request only missing chunks'' behavior that is not a reliable property of streamed generative output. Option D includes useful ideas (load shedding) but relies on static caps and does not provide as strong adaptive retry control as circuit breaking.
Therefore, Option B is the most correct and operationally safe strategy for peak-load Bedrock streaming workloads.