import pickle import os import gradio as gr import requests import inspect import pandas as pd import logging from universal_agent import AnswerFormat # Setup logger logging.basicConfig(level=logging.INFO) logger = logging.getLogger(__name__) # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # --- Basic Agent Definition --- # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ # class BasicAgent: # def __init__(self): # logger.info("BasicAgent initialized.") # def __call__(self, question: str) -> str: # logger.info(f"Agent received question (first 50 chars): {question[:50]}...") # fixed_answer = "This is a default answer." # logger.info(f"Agent returning fixed answer: {fixed_answer}") # return fixed_answer def run_and_submit_all( profile: gr.OAuthProfile | None): """ Fetches all questions, runs the BasicAgent on them, submits all answers, and displays the results. """ # --- Determine HF Space Runtime URL and Repo URL --- space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code if profile: username= f"{profile.username}" logger.info(f"User logged in: {username}") else: logger.info("User not logged in.") return "Please Login to Hugging Face with the button.", None api_url = DEFAULT_API_URL questions_url = f"{api_url}/questions" submit_url = f"{api_url}/submit" # # 1. Instantiate Agent ( modify this part to create your agent) # try: # agent = BasicAgent() # except Exception as e: # logger.info(f"Error instantiating agent: {e}") # return f"Error initializing agent: {e}", None # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public) agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" logger.info(agent_code) # # 2. Fetch Questions # logger.info(f"Fetching questions from: {questions_url}") # try: # response = requests.get(questions_url, timeout=15) # response.raise_for_status() # questions_data = response.json() # if not questions_data: # logger.info("Fetched questions list is empty.") # return "Fetched questions list is empty or invalid format.", None # logger.info(f"Fetched {len(questions_data)} questions.") # except requests.exceptions.RequestException as e: # logger.info(f"Error fetching questions: {e}") # return f"Error fetching questions: {e}", None # except requests.exceptions.JSONDecodeError as e: # logger.info(f"Error decoding JSON response from questions endpoint: {e}") # logger.info(f"Response text: {response.text[:500]}") # return f"Error decoding server response for questions: {e}", None # except Exception as e: # logger.info(f"An unexpected error occurred fetching questions: {e}") # return f"An unexpected error occurred fetching questions: {e}", None # 3. Run your Agent # results_log = [] # answers_payload = [] # logger.info(f"Running agent on {len(questions_data)} questions...") # for item in questions_data: # task_id = item.get("task_id") # question_text = item.get("question") # if not task_id or question_text is None: # logger.info(f"Skipping item with missing task_id or question: {item}") # continue # try: # submitted_answer = agent(question_text) # answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer}) # results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer}) # except Exception as e: # logger.info(f"Error running agent on task {task_id}: {e}") # results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"}) # if not answers_payload: # logger.info("Agent did not produce any answers to submit.") # return "Agent did not produce any answers to submit.", pd.DataFrame(results_log) with open("all_questions.pkl", "rb") as f: all_questions = pickle.load(f) with open("results_gpt_mini.pkl", "rb") as f: results = pickle.load(f) answers = [{"task_id":j['task_id'], "submitted_answer": results[i]["structured_response"].answer if isinstance(results[i], dict) else "No answer"} for i,j in enumerate(all_questions)] # 4. Prepare Submission submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers} # submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload} status_update = f"Agent finished. Submitting {len(answers)} answers for user '{username}'..." logger.info(status_update) results_log = [1,2] # 5. Submit logger.info(f"Submitting {len(answers)} answers to: {submit_url}") try: response = requests.post(submit_url, json=submission_data, timeout=60) response.raise_for_status() result_data = response.json() final_status = ( f"Submission Successful!\n" f"User: {result_data.get('username')}\n" f"Overall Score: {result_data.get('score', 'N/A')}% " f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n" f"Message: {result_data.get('message', 'No message received.')}" ) logger.info("Submission successful.") results_df = pd.DataFrame(results_log) return final_status, results_df except requests.exceptions.HTTPError as e: error_detail = f"Server responded with status {e.response.status_code}." try: error_json = e.response.json() error_detail += f" Detail: {error_json.get('detail', e.response.text)}" except requests.exceptions.JSONDecodeError: error_detail += f" Response: {e.response.text[:500]}" status_message = f"Submission Failed: {error_detail}" logger.info(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df except requests.exceptions.Timeout: status_message = "Submission Failed: The request timed out." logger.info(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df except requests.exceptions.RequestException as e: status_message = f"Submission Failed: Network error - {e}" logger.info(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df except Exception as e: status_message = f"An unexpected error occurred during submission: {e}" logger.info(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df # --- Build Gradio Interface using Blocks --- with gr.Blocks() as demo: gr.Markdown("# Agent Evaluation Runner") gr.LoginButton() run_button = gr.Button("Run Evaluation & Submit All Answers") status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False) # Removed max_rows=10 from DataFrame constructor # results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True) run_button.click( fn=run_and_submit_all, outputs=[status_output] # outputs=[status_output, results_table] ) if __name__ == "__main__": logger.info("\n" + "-"*30 + " App Starting " + "-"*30) # Check for SPACE_HOST and SPACE_ID at startup for information space_host_startup = os.getenv("SPACE_HOST") space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup if space_host_startup: logger.info(f"✅ SPACE_HOST found: {space_host_startup}") logger.info(f" Runtime URL should be: https://{space_host_startup}.hf.space") else: logger.info("ℹ️ SPACE_HOST environment variable not found (running locally?).") if space_id_startup: # logger.info repo URLs if SPACE_ID is found logger.info(f"✅ SPACE_ID found: {space_id_startup}") logger.info(f" Repo URL: https://huggingface.co/spaces/{space_id_startup}") logger.info(f" Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main") else: logger.info("ℹ️ SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.") logger.info("-"*(60 + len(" App Starting ")) + "\n") logger.info("Launching Gradio Interface for Basic Agent Evaluation...") demo.launch(debug=True, share=False)