@andyyuen nice job! It's very useful as a template for a more advanced project. Thank you!

You have to capture a jpeg from the camera buffer and pass it to the llm... An example could be:

      uint8_t* out_jpg = NULL;
      size_t out_jpg_len = 0;
      frame2jpg(CoreS3.Camera.fb, 255, &out_jpg, &out_jpg_len);
      CoreS3.Camera.free();
      module_llm.yolo.inferenceAndWaitResult(
        yolo_work_id, out_jpg, out_jpg_len, [](String& result) {
           /* do something with result */
          .... 
        }, 2000, "ID");
      free(out_jpg);

the result will contain:

{"bbox":["195.86","197.75","319.00","280.27"],"class":"keyboard","confidence":"0.69"}

HTH