AI-102 Question 468
Single answerYou are developing a customer support chatbot for a retail company using Azure OpenAI Service. The chatbot needs to understand and respond to user queries that include both text and image inputs (e.g., identifying a product from an uploaded image and answering related questions). Which Azure OpenAI model should you use to meet this requirement?
- A
GPT-4
- B
Codex
- C
DALL·E
- D
GPT-4 Vision
Show answer and explanation
Correct answer: D
Explanation
To meet the requirement of processing both text and image inputs for the chatbot, the GPT-4 Vision model is the correct choice. It is specifically designed as a multimodal model in Azure OpenAI, enabling it to understand and generate responses based on both text and image inputs. Other options either lack multimodal capabilities or are specialized for other use cases.
- A. Incorrect.
GPT-4 is a powerful text-based model but does not natively support multimodal inputs such as images.
- B. Incorrect.
Codex is specifically designed for code-related tasks and does not support multimodal capabilities like processing images.
- C. Incorrect.
DALL·E is a model designed for generating images from textual descriptions, but it is not suitable for processing both text and image inputs for chatbot functionality.
- D. Correct.
GPT-4 Vision is a multimodal model that can process both text and image inputs, making it the appropriate choice for this scenario.