| import os | |
| import requests | |
| import pandas as pd | |
| import gradio as gr | |
| from agent import BasicAgent | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| class GAIAAgent: | |
| def __init__(self): | |
| self.agent = BasicAgent() | |
| def __call__(self, question: str, task_id: str) -> str: | |
| return self.agent(question, task_id) | |
| def run_and_submit_all(profile: gr.OAuthProfile | None): | |
| space_id = os.getenv("SPACE_ID") | |
| if not profile or not profile.username: | |
| return "Please Login to Hugging Face with the button.", None | |
| username = profile.username.strip() | |
| agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "" | |
| questions_url = f"{DEFAULT_API_URL}/questions" | |
| submit_url = f"{DEFAULT_API_URL}/submit" | |
| try: | |
| response = requests.get(questions_url, timeout=15) | |
| response.raise_for_status() | |
| questions_data = response.json() | |
| except Exception as e: | |
| return f"Error fetching questions: {e}", None | |
| agent = GAIAAgent() | |
| 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, task_id) | |
| except Exception as e: | |
| submitted_answer = f"[ERROR] {e}" | |
| 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}) | |
| submission_data = {"username": username, "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.')}" | |
| ) | |
| return final_status, pd.DataFrame(results_log) | |
| except Exception as e: | |
| return f"Submission Failed: {e}", pd.DataFrame(results_log) | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# Basic Agent Evaluation Runner") | |
| gr.Markdown(""" | |
| **Instructions:** | |
| 1. Please clone this space and modify the agent logic. | |
| 2. Log in to Hugging Face with the button. | |
| 3. Click 'Run Evaluation & Submit All Answers' to run the full GAIA test. | |
| """) | |
| 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") | |
| run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table]) | |
| if __name__ == "__main__": | |
| print("\n===== Application Startup =====") | |
| space_id = os.getenv("SPACE_ID") | |
| if space_id: | |
| print(f"🔗 Space: https://huggingface.co/spaces/{space_id}") | |
| demo.launch(debug=True) |