An Azure service that provides access to OpenAI’s GPT-3 models with enterprise capabilities.
But the web search is text based, correct? Its not image search if I understand it correctly.
This browser is no longer supported.
Upgrade to Microsoft Edge to take advantage of the latest features, security updates, and technical support.
Hi,
I am looking for a solution to ground my Azure OpenAI API with image based web grounding. The default web grounding is only text based, it doesn't do image search. I also read that the Bing Visual API has been deprecated. https://learn.microsoft.com/en-us/previous-versions/azure/cognitive-services/bing-visual-search/overview
Do we have any current solution to do image grounding using Bing when used with any LLMs such as Azure OpenAI gpt 5.1 ?
An Azure service that provides access to OpenAI’s GPT-3 models with enterprise capabilities.
But the web search is text based, correct? Its not image search if I understand it correctly.
Web search works in Agent console worked to do image search with an image inputs.
WebSearch+Response API is already supported scenario (No work code available image inputs, facing not supported error when tested with image directly, feel free to test with base 64 image and share your observation).
But it worked with new foundry Agents.
Attached screenshot and documentation below for reference.
With Agents
Attached screenshot and relevant document from Agent with Websearch
Attached screenshot and relevant document on Agents from Grounding with Bing search.
Note:
Customer are advised to use Grounding with Bing search along Agents, Default Bing search resource are depreciated.
Reference - https://learn.microsoft.com/en-us/lifecycle/announcements/bing-search-api-retirement
Please let us know if it serves as solution for you.
Thank you.