Images in prompts · Question 2 of 12
Which task can a multimodal model perform with a photo of a receipt?
1 answer is correct. Easy Created with AI
Show answer
Answer
- D Answering questions about the content, e.g. the total
Explanation
Multimodal models understand image content including text and can answer questions about it or extract information. For reliable, structured extraction at scale, Content Understanding is also suitable.