Users submit a receipt image and a question.
Read text, layout, and amounts together.
Choose two considerations.
Verify multimodal capability and limits, and test OCR, resolution, table reading, and sensitive data with an appropriate evaluation set.
Detailed explanation
The model matches the input modalities.
The model matches the input modalities.
Image-specific quality and safety are measured.
Image-specific quality and safety are measured.
The input modality is unsupported.
The input modality is unsupported.
Additional modalities still need explanation and safety.
Additional modalities still need explanation and safety.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 2.1のマルチモーダル基盤モデルと評価を確認する。Expected result
入力モダリティとモデル能力、画像特有の評価観点を説明できる。Key points
- Multimodal
- OCR
- Image quality
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
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.