import ctypes import datetime import json import logging import os import sys import func_timeout from desktop_env.envs.desktop_env import DesktopEnv from mm_agents.gpt_4v_agent import GPT4v_Agent # Logger Configs {{{ # logger = logging.getLogger() logger.setLevel(logging.DEBUG) datetime_str: str = datetime.datetime.now().strftime("%Y%m%d@%H%M%S") file_handler = logging.FileHandler(os.path.join("logs", "normal-{:}.log".format(datetime_str)), encoding="utf-8") debug_handler = logging.FileHandler(os.path.join("logs", "debug-{:}.log".format(datetime_str)), encoding="utf-8") stdout_handler = logging.StreamHandler(sys.stdout) sdebug_handler = logging.FileHandler(os.path.join("logs", "sdebug-{:}.log".format(datetime_str)), encoding="utf-8") file_handler.setLevel(logging.INFO) debug_handler.setLevel(logging.DEBUG) stdout_handler.setLevel(logging.INFO) sdebug_handler.setLevel(logging.DEBUG) formatter = logging.Formatter( fmt="\x1b[1;33m[%(asctime)s \x1b[31m%(levelname)s \x1b[32m%(module)s/%(lineno)d-%(processName)s\x1b[1;33m] \x1b[0m%(message)s") file_handler.setFormatter(formatter) debug_handler.setFormatter(formatter) stdout_handler.setFormatter(formatter) sdebug_handler.setFormatter(formatter) stdout_handler.addFilter(logging.Filter("desktopenv")) sdebug_handler.addFilter(logging.Filter("desktopenv")) logger.addHandler(file_handler) logger.addHandler(debug_handler) logger.addHandler(stdout_handler) logger.addHandler(sdebug_handler) # }}} Logger Configs # logger = logging.getLogger("desktopenv.experiment") PATH_TO_VM = r"C:\Users\tianbaox\Documents\Virtual Machines\Ubuntu\Ubuntu.vmx" def run_one_example(example, agent, max_steps=10, example_trajectory_dir="exp_trajectory", recording=True): trajectory_recording_path = os.path.join(example_trajectory_dir, "trajectory.json") env = DesktopEnv( path_to_vm=PATH_TO_VM, action_space=agent.action_space, task_config=example ) # reset the environment to certain snapshot observation = env.reset() done = False step_num = 0 if recording: # send a request to the server to start recording env.controller.start_recording() while not done and step_num < max_steps: actions = agent.predict(observation) step_num += 1 for action in actions: # Capture the timestamp before executing the action action_timestamp = datetime.datetime.now().strftime("%Y%m%d@%H%M%S") logger.info("Step %d: %s", step_num, action) observation, reward, done, info = env.step(action) logger.info("Reward: %.2f", reward) logger.info("Done: %s", done) logger.info("Info: %s", info) # Save screenshot and trajectory information with open(os.path.join(example_trajectory_dir, f"step_{step_num}_{action_timestamp}.png"), "wb") as _f: with open(observation['screenshot'], "rb") as __f: screenshot = __f.read() _f.write(screenshot) with open(trajectory_recording_path, "a") as f: f.write(json.dumps({ "step_num": step_num, "action_timestamp": action_timestamp, "action": action, "reward": reward, "done": done, "info": info, "screenshot_file": f"step_{step_num}_{action_timestamp}.png" })) f.write("\n") if done: logger.info("The episode is done.") break def stop_recording(): try: env.controller.end_recording(os.path.join(example_trajectory_dir, "recording.mp4")) except Exception as e: print(f"An error occurred while stopping the recording: {e}") try: func_timeout.func_timeout(30, stop_recording) except func_timeout.exceptions.FunctionTimedOut: logger.info("Recording timed out.") result = env.evaluate() logger.info("Result: %.2f", result) with open(trajectory_recording_path, "a") as f: f.write(json.dumps({ "result": result })) f.write("\n") # env.close() logger.info("Environment closed.") def main(example_class, example_id): action_space = "pyautogui" gpt4_model = "gpt-4-0125-preview" gemini_model = "gemini-pro-vision" logger.info("Running example %s/%s", example_class, example_id) logger.info("Using model %s", gpt4_model) # logger.info("Using model %s", gemini_model) with open(f"evaluation_examples/examples/{example_class}/{example_id}.json", "r", encoding="utf-8") as f: example = json.load(f) example["snapshot"] = "exp_v1" api_key = os.environ.get("OPENAI_API_KEY") agent = GPT4v_Agent(api_key=api_key, model=gpt4_model, instruction=example['instruction'], max_tokens=1000, action_space=action_space, exp="a11y_tree") # api_key = os.environ.get("GENAI_API_KEY") # agent = GeminiPro_Agent(api_key=api_key, model=gemini_model, instruction=example['instruction'], action_space=action_space, exp="a11y_tree") root_trajectory_dir = "exp_trajectory" example_trajectory_dir = os.path.join(root_trajectory_dir, "a11y_tree", example_class, gpt4_model, example_id) # example_trajectory_dir = os.path.join(root_trajectory_dir, "a11y_tree", example_class, gemini_model, example_id) os.makedirs(example_trajectory_dir, exist_ok=True) run_one_example(example, agent, 15, example_trajectory_dir) if __name__ == '__main__': vlc_list = [ # "8ba5ae7a-5ae5-4eab-9fcc-5dd4fe3abf89", # "8ba5ae7a-5ae5-4eab-9fcc-5dd4fe3abf89", # "8f080098-ddb1-424c-b438-4e96e5e4786e", # "bba3381f-b5eb-4439-bd9e-80c22218d5a7", # "fba2c100-79e8-42df-ae74-b592418d54f4", # "efcf0d81-0835-4880-b2fd-d866e8bc2294", # "8d9fd4e2-6fdb-46b0-b9b9-02f06495c62f", # "aa4b5023-aef6-4ed9-bdc9-705f59ab9ad6", # "386dbd0e-0241-4a0a-b6a2-6704fba26b1c", # "9195653c-f4aa-453d-aa95-787f6ccfaae9", # "d06f0d4d-2cd5-4ede-8de9-598629438c6e", # "a5bbbcd5-b398-4c91-83d4-55e1e31bbb81", "f3977615-2b45-4ac5-8bba-80c17dbe2a37", "215dfd39-f493-4bc3-a027-8a97d72c61bf" ] chrome_list = [ # "bb5e4c0d-f964-439c-97b6-bdb9747de3f4", "7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3", "06fe7178-4491-4589-810f-2e2bc9502122", "e1e75309-3ddb-4d09-92ec-de869c928143", "35253b65-1c19-4304-8aa4-6884b8218fc0", "2ad9387a-65d8-4e33-ad5b-7580065a27ca", "7a5a7856-f1b6-42a4-ade9-1ca81ca0f263", "44ee5668-ecd5-4366-a6ce-c1c9b8d4e938", "2ae9ba84-3a0d-4d4c-8338-3a1478dc5fe3", "480bcfea-d68f-4aaa-a0a9-2589ef319381", "af630914-714e-4a24-a7bb-f9af687d3b91" ] calc_list = [ "eb03d19a-b88d-4de4-8a64-ca0ac66f426b", "0bf05a7d-b28b-44d2-955a-50b41e24012a", "7a4e4bc8-922c-4c84-865c-25ba34136be1", "2bd59342-0664-4ccb-ba87-79379096cc08", "ecb0df7a-4e8d-4a03-b162-053391d3afaf", "7efeb4b1-3d19-4762-b163-63328d66303b", "4e6fcf72-daf3-439f-a232-c434ce416af6", "6054afcb-5bab-4702-90a0-b259b5d3217c", "abed40dc-063f-4598-8ba5-9fe749c0615d", "01b269ae-2111-4a07-81fd-3fcd711993b0", "8b1ce5f2-59d2-4dcc-b0b0-666a714b9a14", "0cecd4f3-74de-457b-ba94-29ad6b5dafb6", "4188d3a4-077d-46b7-9c86-23e1a036f6c1", "51b11269-2ca8-4b2a-9163-f21758420e78", "7e429b8d-a3f0-4ed0-9b58-08957d00b127", "347ef137-7eeb-4c80-a3bb-0951f26a8aff", "6e99a1ad-07d2-4b66-a1ce-ece6d99c20a5", "3aaa4e37-dc91-482e-99af-132a612d40f3", "37608790-6147-45d0-9f20-1137bb35703d", "f9584479-3d0d-4c79-affa-9ad7afdd8850", "d681960f-7bc3-4286-9913-a8812ba3261a", "21df9241-f8d7-4509-b7f1-37e501a823f7", "1334ca3e-f9e3-4db8-9ca7-b4c653be7d17", "357ef137-7eeb-4c80-a3bb-0951f26a8aff", "aa3a8974-2e85-438b-b29e-a64df44deb4b", "a01fbce3-2793-461f-ab86-43680ccbae25", "4f07fbe9-70de-4927-a4d5-bb28bc12c52c", ] for example_id in calc_list: main("libreoffice_calc", example_id)