A county-fair desk wants short vendor blurbs from bullet notes and has a couple of hundred past blurbs, not a million-token corpus. The team does not want to own training infrastructure. Which approach fits?
Select an answer to reveal the explanation.
Short Explanation
Think of short vendor blurbs from bullet notes, a couple of hundred past blurbs, and no appetite to own training infrastructure. Call an Amazon Bedrock foundation model. A couple of hundred lines will not train a language model from scratch.
Full Explanation
Amazon Bedrock serves a foundation model through an API when the job is generative text and custom training is not feasible or cost-effective. A couple of hundred blurbs will not support training from scratch. K-Means and Rekognition are not generative text trainers.