TechFlow news: OpenAI has announced the official release of GPT-4 Turbo with Vision via its API.
Developers can now request the model's visual recognition and analysis capabilities using JSON-formatted text and function calls, generating JSON code snippets that can automate actions within connected applications—such as "sending emails, posting content online, or making purchases." However, OpenAI notes on its API page: "We strongly recommend implementing a user confirmation process before taking real-world actions on behalf of users."
An OpenAI spokesperson said these updates help streamline developers' workflows and build more efficient applications, as "previously, developers had to use separate models for text and images, but now, with just one API call, the model can analyze images and apply reasoning."
