import os import gradio as gr import requests from smolagents import OpenAIServerModel, DuckDuckGoSearchTool, CodeAgent, WikipediaSearchTool from pathlib import Path import tempfile import pandas as pd import re # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # --- File Download Helper --- def download_file_if_any(base_api_url: str, task_id: str) -> str | None: url = f"{base_api_url}/files/{task_id}" try: resp = requests.get(url, timeout=30) if resp.status_code == 404: return None resp.raise_for_status() except requests.exceptions.HTTPError as e: raise e cdisp = resp.headers.get("content-disposition", "") filename = task_id if "filename=" in cdisp: m = re.search(r'filename="([^\"]+)"', cdisp) if m: filename = m.group(1) tmp_dir = Path(tempfile.gettempdir()) / "gaia_files" tmp_dir.mkdir(exist_ok=True) file_path = tmp_dir / filename with open(file_path, "wb") as f: f.write(resp.content) return str(file_path) # --- Basic Agent --- class BasicAgent: def __init__(self): self.agent = CodeAgent( model=OpenAIServerModel(model_id="gpt-4o"), tools=[DuckDuckGoSearchTool(), WikipediaSearchTool()], add_base_tools=True, additional_authorized_imports=[] ) print("BasicAgent initialized.") def __call__(self, question: str) -> str: print(f"Agent received question (first 50 chars): {question[:50]}...") fixed_answer = self.agent.run(question) print(f"Agent returning answer: {fixed_answer}") return fixed_answer # --- Evaluation Logic --- def run_and_submit_all(profile: gr.OAuthProfile | None): space_id = "YajieXu/Final_Assignment_Template" if profile: username = f"{profile.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" 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() 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") try: file_path = download_file_if_any(api_url, task_id) except Exception as e: file_path = None print(f"[file fetch error] {task_id}: {e}") q_for_agent = ( f"{question_text}\n\n---\nA file was downloaded for this task and saved locally at:\n{file_path}\n---\n\n" if file_path else question_text ) if not task_id or question_text is None: continue try: submitted_answer = agent(q_for_agent) 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) 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) # --- Gradio UI --- with gr.Blocks() as demo: gr.Markdown("# Basic Agent Evaluation Runner") gr.Markdown(""" **Instructions:** 1. Log in to your Hugging Face account. 2. Click the button to run the agent and submit answers. 3. Your score will be printed below. """) 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__": print("Launching GAIA agent app...") demo.launch(debug=True, share=False)