| openai_computer_use_tool | R Documentation |
Browser / desktop control. The model issues actions (click, type, scroll, screenshot) which the caller's harness executes against a virtual computer.
openai_computer_use_tool(
display_width = NULL,
display_height = NULL,
environment = c("browser", "mac", "windows", "ubuntu")
)
display_width, display_height |
Integer screen dimensions in pixels. Required by the API on most environments. |
environment |
One of |
A plain list ready to drop into tools = list(...).
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.