From the course: AI-Powered Development: GitHub Copilot in Visual Studio

Unlock this course with a free trial

Join today to access over 24,900 courses taught by industry experts.

Use images with the chat

Use images with the chat

- [Instructor] Some AI models powering Copilot are multimodal, meaning they can interpret both text and images and sometimes documents. By attaching an image in the chat window, we can provide valuable visual context, and if a multimodal model is available, Copilot will automatically switch to use it. When you add an image like this one over here, the model doesn't just see the pixels. It actively analyzes the image to understand what's going on. It looks for elements like text. It reads any visible words such as labels, error messages, or code snippets. In this example, it would read the words link to XML. It looks at the layout and interprets how elements are arranged, like buttons, fields, menus, or diagrams. For visual cues, it picks up on structure, flow, or design patterns. This visual understanding is then combined with the written prompt to generate more accurate, relevant, and context aware responses. We're…

Contents