code of the interactive mode

[cyan135]

thanks for the great work!
For the interactive mode, the OMG-Seg paper mentions that the design of the prompt encoder follows SAM, but I can't find the corresponding code that adopts SAM's encoder to generate location queries. Could you tell me where the relevant code is? Also, does it only support using bbox as a prompt? since point prompts seem to be required to expand into bboxes.