import os import gradio as gr import requests import pandas as pd from agent import SubmissionAgent DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" def run_and_submit_all(profile: gr.OAuthProfile | None): """ Fetch all questions, run the agent on them, submit answers, and display the final score plus a results table. """ space_id = os.getenv("SPACE_ID") if profile: username = profile.username print(f"User logged in: {username}") else: print("User not logged in.") return "Please login to Hugging Face first.", None api_url = DEFAULT_API_URL questions_url = f"{api_url}/questions" submit_url = f"{api_url}/submit" # Instantiate agent try: agent = SubmissionAgent() except Exception as e: print(f"Error initializing agent: {e}") return f"Error initializing agent: {e}", None # Required code URL for benchmark if space_id: agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" else: agent_code = "SPACE_ID_NOT_AVAILABLE" print(f"Agent code URL: {agent_code}") # Fetch questions print(f"Fetching questions from: {questions_url}") try: response = requests.get(questions_url, timeout=20) response.raise_for_status() questions_data = response.json() if not questions_data: print("Fetched questions list is empty.") return "Fetched questions list is empty.", None print("First question keys:", questions_data[0].keys()) print("First question sample:", questions_data[0]) print(f"Fetched {len(questions_data)} questions.") except requests.exceptions.RequestException as e: print(f"Error fetching questions: {e}") return f"Error fetching questions: {e}", None except ValueError as e: print(f"Error decoding questions JSON: {e}") return f"Error decoding questions JSON: {e}", None except Exception as e: print(f"Unexpected error fetching questions: {e}") return f"Unexpected error fetching questions: {e}", None # Run agent results_log = [] answers_payload = [] print(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: print(f"Skipping malformed item: {item}") continue try: submitted_answer = agent( question_text, task_id=task_id, task_item=item, ) print("=" * 100) print(f"TASK ID: {task_id}") print(f"QUESTION: {question_text}") print(f"SUBMITTED ANSWER: {submitted_answer}") print("=" * 100) 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: print(f"Error 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: print("No answers generated.") return "Agent did not generate any answers.", pd.DataFrame(results_log) # Prepare submission submission_data = { "username": username.strip(), "agent_code": agent_code, "answers": answers_payload, } print(f"Submitting {len(answers_payload)} 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.')}" ) print("Submission successful.") return final_status, pd.DataFrame(results_log) 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 ValueError: error_detail += f" Response: {e.response.text[:500]}" status_message = f"Submission Failed: {error_detail}" print(status_message) return status_message, pd.DataFrame(results_log) except requests.exceptions.Timeout: status_message = "Submission Failed: Request timed out." print(status_message) return status_message, pd.DataFrame(results_log) except requests.exceptions.RequestException as e: status_message = f"Submission Failed: Network error - {e}" print(status_message) return status_message, pd.DataFrame(results_log) except Exception as e: status_message = f"Unexpected submission error: {e}" print(status_message) return status_message, pd.DataFrame(results_log) # Gradio Interface with gr.Blocks() as demo: gr.Markdown("# Hugging Face Unit 4 Agent Evaluation Runner") gr.Markdown( """ Log in with your Hugging Face account, run your agent on all benchmark questions, submit the answers, and view the score plus answer log. """ ) login_button = gr.LoginButton() run_button = gr.Button("Run Evaluation & Submit All Answers") status_output = gr.Textbox( label="Run Status / Submission Result", lines=6, 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], ) if __name__ == "__main__": print("\n" + "-" * 30 + " App Starting " + "-" * 30) space_host_startup = os.getenv("SPACE_HOST") space_id_startup = os.getenv("SPACE_ID") if space_host_startup: print(f"SPACE_HOST: {space_host_startup}") print(f"Runtime URL: https://{space_host_startup}") else: print("SPACE_HOST not found. Probably running locally.") if space_id_startup: print(f"SPACE_ID: {space_id_startup}") print(f"Repo URL: https://huggingface.co/spaces/{space_id_startup}") print(f"Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main") else: print("SPACE_ID not found. Probably running locally.") print("-" * 75 + "\n") print("Launching Gradio app...") demo.launch(debug=True)