Question 50: AI-103: Developing AI Apps and Agents on Azure
You have an app named App1 that uses a Microsoft Foundry multimodal model deployment.App1 runs optical character recognition (OCR) on uploaded images and appends the OCR output to the prompt as additional context. Some uploaded images contain embedded text. You need to prevent potentially malicious instructions from b…
Nội dung câu hỏi
You have an app named App1 that uses a Microsoft Foundry multimodal model deployment.App1 runs optical character recognition (OCR) on uploaded images and appends the OCR output to the prompt as additional context. Some uploaded images contain embedded text. You need to prevent potentially malicious instructions from being processed by the model. What should you use?
Các lựa chọn
Đáp án được giữ gọn theo nhãn A, B, C, D trong phần bình chọn tương tác.
- A. image moderation
- B. prompt shields for documents — đáp án hiện tại
- C. protected material text
- D. prompt shields for user prompts
Cộng đồng
0 bình luận công khai. Tên thành viên được ẩn một phần.