import os import gradio as gr import requests import pandas as pd import re # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # --- Basic Agent Definition --- class BasicAgent: def __init__(self): print("✅ BasicAgent initialized.") def __call__(self, question: str) -> str: """ Process a question and return an answer. Handles basic arithmetic, string extraction, and fallback for other tasks. """ print(f"Agent received question (first 50 chars): {question[:50]}...") try: numbers = [float(n) for n in re.findall(r"\d+\.?\d*", question)] q_lower = question.lower() # Basic addition if ("sum" in q_lower or "add" in q_lower) and numbers: answer = str(sum(numbers)) # Basic multiplication elif "multiply" in q_lower and numbers: product = 1 for n in numbers: product *= n answer = str(product) # Extract first letter (example task type) elif "first letter" in q_lower: words = question.strip().split() answer = words[0][0] if words else "N/A" # Default: return first 5 words else: answer = " ".join(question.strip().split()[:5]) except Exception as e: answer = f"ERROR: {e}" print(f"Agent returning answer: {answer}") return answer # --- Run & Submit Function --- def run_and_submit_all(profile: gr.OAuthProfile | None): """ Fetch all questions, run the BasicAgent on them, submit all answers, and display the results. """ space_id = os.getenv("SPACE_ID") if profile: username = profile.username print(f"User logged in: {username}") else: 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" # Instantiate agent try: agent = BasicAgent() except Exception as e: return f"Error initializing agent: {e}", None agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" # Fetch questions try: response = requests.get(questions_url, timeout=15) response.raise_for_status() questions_data = response.json() if not questions_data: return "Fetched questions list is empty or invalid format.", None print(f"Fetched {len(questions_data)} questions.") except Exception as e: return f"Error fetching questions: {e}", None # Run agent on each question results_log = [] answers_payload = [] 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: 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: results_log.append({ "Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}" }) if not answers_payload: return "Agent did not produce any answers to submit.", pd.DataFrame(results_log) # Submit submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload} 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.')}" ) results_df = pd.DataFrame(results_log) return final_status, results_df except Exception as e: results_df = pd.DataFrame(results_log) return f"Submission Failed: {e}", results_df # --- Gradio Interface --- with gr.Blocks() as demo: gr.Markdown("# Basic Agent Evaluation Runner") gr.Markdown( """ **Instructions:** 1. Log in to your Hugging Face account using the button below. 2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see your score. """ ) gr.LoginButton() run_button = gr.Button("Run Evaluation & Submit All Answers") status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False) results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True) run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table]) # --- Launch App --- if __name__ == "__main__": print("\n" + "-"*30 + " App Starting " + "-"*30) demo.launch(debug=True, share=False)