You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, is this function available?
When converting pdf to markdown, we hope to extract both images and tables. For image extraction, we hope to be able to use LLM to view the image, give a description of the image through the context, and have it appear in the markdown content.