feat: enabling local inference through USB tethering

[patnir411]

This is a work in progress, the current commit stands as a working MVP. I'm looking for absolutely any feedback in polishing this for the repository if it'd be a valuable feature to add. Made with the help of Gemini CLI :)

This commit introduces a new "Toggle Server" feature that runs a local HTTP server on the device. This allows developers and researchers to interact with the on-device AI models using curl, with all communication tunneled exclusively over a USB connection.

The server can handle multipart/form-data requests, allowing users to send a prompt, an image, or both. This provides a powerful new way to test, debug, and integrate the on-device models.

Usage

1. Enable USB Debugging:

   • Follow these steps to enable USB debugging on your device.

2. Connect Device to Computer & Enable Port Forwarding:

   adb -d forward tcp:8080 tcp:8080

3. Start the Server in the App:

   • Navigate to the "Toggle Server" screen.
   • Tap the "Start In-App Server" button.

4. Send Requests with curl:

   • Prompt only:

     curl -X POST -F "prompt=Hello, world!" http://localhost:8080

   • Image and prompt:

     curl -X POST -F "prompt=What is in this image?" -F "image=@/path/to/your/image.jpg" http://localhost:8080

[n1203]

This is really much needed 👍