Closed haoxin closed 1 week ago
@haoxin Thanks for your feedback! We will investigate and update as appropriate.
Hello @haoxin
You're correct that the GPT model, as deployed following the provided documentation, doesn't incorporate Vision Enhancement or On Your Data (OYD) functionalities with images. This model is specifically designed for generating text based on input prompts and doesn't include native support for image processing or analysis.
If you are looking to perform image analysis or processing using Azure AI services, there are a number of other services and models available that may better suit your needs. For example, you can use the Computer Vision API to perform image analysis tasks such as object detection, image tagging, and optical character recognition (OCR).
Please refer the below link. https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/gpt-with-vision?tabs=rest%2Csystem-assigned%2Cresource#:~:text=GPT%2D4%20Turbo%20provisioned%20managed,and%20image/vision%20inference%20requests.
@haoxin If there are any further questions regarding the documentation, please tag me in your reply and we will be happy to continue the conversation.
@haoxin We are going to close this thread, if there are any further questions regarding the documentation, please tag me in your reply and we will be happy to continue the conversation.
[Enter feedback here] The deployed GPT model does not support Vision Enhancement and On Your Data (OYD) with images.
Document Details
⚠ Do not edit this section. It is required for learn.microsoft.com ➟ GitHub issue linking.