Find phrases, objects and events in text or image using GPT model

#include "docwire.h"

#include <sstream>

 

int main(int argc, char* argv[])

{

using namespace docwire

std::stringstream out_stream

 

try

{

std::filesystem::path("scene_1.png") | openai::Find("tree", std::getenv("OPENAI_API_KEY")) | out_stream

}

catch (const std::exception& e)

{

std::cerr << errors::diagnostic_message(e) << std::endl

return 1

}

assert(fuzzy_match::ratio(out_stream.str(), "2\n- A tree is located on the left side of the image near the people.\n- Another tree is in the background near the center of the image.\n") > 80)

 

return 0

}