ETExamTower
Q12Applications of Foundation Models

A company regularly refreshes its product database by manually uploading digital product guides. The guides include text and images. The company wants to automate this work with generative AI. Select and arrange the steps needed to automate the database-update task by using generative AI. Choose every step once. <Dropdown blanks={[{"id":"step1","options":["Insert data into the product database.","Upload the digital text and image files to an Amazon S3 bucket.","Use Amazon Nova multimodal models to process the digital text and image files."],"answer":"Upload the digital text and image files to an Amazon S3 bucket.","label":"Step 1:"},{"id":"step2","options":["Insert data into the product database.","Upload the digital text and image files to an Amazon S3 bucket.","Use Amazon Nova multimodal models to process the digital text and image files."],"answer":"Use Amazon Nova multimodal models to process the digital text and image files.","label":"Step 2:"},{"id":"step3","options":["Insert data into the product database.","Upload the digital text and image files to an Amazon S3 bucket.","Use Amazon Nova multimodal models to process the digital text and image files."],"answer":"Insert data into the product database.","label":"Step 3:"}]} explanation={"Amazon S3 provides the object storage location for the digital guides. Amazon Nova multimodal models can analyze both text and image inputs, allowing the product data to be extracted or structured after the files are available. That processed output can then be used to insert records into the product database.\n\n**Learn more:** [Amazon Nova User Guide — Amazon Nova models](https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html) · [Amazon S3 User Guide — Uploading objects](https://docs.aws.amazon.com/AmazonS3/latest/userguide/upload-objects.html)"} />

Question exhibit
← → navigate · a answer
Discussion · 1
2
This is always the first step—get the raw data into AWS so it can be processed. After the files are in S3, the Nova multimodal model can extract structured information. Once the model has processed and structured the content, the final step is writing it to the database. 1. Upload product guide files (text + images) to S3 2. Feed them into a Nova multimodal model 3. Extract usable structured data 4. Insert into the product database