import os import gradio as gr import requests import pandas as pd # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" API_URL = "https://api-inference.huggingface.co/models/Qwen/Qwen2.5-Coder-32B-Instruct" headers = {"Authorization": f"Bearer {os.getenv('HF_TOKEN', '')}"} # --- Simple Agent Definition --- class BasicAgent: def __init__(self): print("Simple Agent initialized.") def __call__(self, question: str) -> str: print(f"Agent received question: {question[:50]}...") try: # Direct Hugging Face API call without extra libraries payload = { "inputs": f"<|im_start|>user\nAnswer this question shortly and accurately: {question}<|im_end|>\n<|im_start|>assistant\n", "parameters": {"max_new_tokens": 100, "return_full_text": False} } response = requests.post(API_URL, headers=headers, json=payload, timeout=20) if response.status_code == 200: result = response.json() if isinstance(result, list) and len(result) > 0: answer = result[0].get("generated_text", "").strip() else: answer = str(result).strip() else: answer = "Error from API" print(f"Agent generated answer: {answer}") return answer except Exception as e: print(f"Error: {e}") return "Fallback Answer" def run_and_submit_all(profile: gr.OAuthProfile | None): space_id = os.getenv("SPACE_ID") if profile: username = f"{profile.username}" else: return "Please Login to Hugging Face with the button.", None questions_url = f"{DEFAULT_API_URL}/questions" submit_url = f"{DEFAULT_API_URL}/submit" 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" 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.", None except Exception as e: return f"Error fetching questions: {e}", None 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": "ERROR"}) if not answers_payload: return "Agent did not produce any answers.", pd.DataFrame(results_log) 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.')}" ) return final_status, pd.DataFrame(results_log) except Exception as e: return f"Submission Failed: {e}", pd.DataFrame(results_log) # --- Build Gradio Interface --- with gr.Blocks() as demo: gr.Markdown("# Basic 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) 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__": demo.launch(debug=True, share=False)