PRODUCTION SCENARIO
An ecommerce company wants an Amazon Bedrock model to write a two-sentence highlight for each of 2 million archived customer reviews. The results are loaded into an analytics table the next morning. No user waits for an individual response.
Which invocation method will meet these requirements?
Answering here is anonymous. Nothing is saved unless you sign in.
Show answer and explanation
Answer: Batch inference with input and output in Amazon S3
Batch inference processes a large number of requests efficiently in a single job: the prompts are read from Amazon S3, the job runs asynchronously, and the responses are written back to an S3 bucket. It is intended for offline datasets like this one, where no user is waiting on any individual response.