Pass a product image and its description to a model.
Relate the image content to the text in the response.
Which characteristic is most appropriate?
A multimodal model can process or generate more than one information modality, such as text and images.
Detailed explanation
That does not describe multimodal processing.
Multimodality is not a database-control feature.
The model can combine different forms such as images and text.
Key management is separate from model modality.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01ガイドDomain 2.1とAmazon Bedrockの対応モデル情報を確認する。
Official references
What to confirm
モダリティと、単一形式の分類・データベース機能を区別できる。
Key points
- Multiple modalities
- Image and text
- Input format
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
Format capability
Supporting text does not imply that a model also accepts images, audio, or video.
Alignment
Different modalities must be related in a way that supports the intended task and evaluation.