import os import gradio as gr import requests import inspect import pandas as pd from smolagents import CodeAgent, HfApiModel, DuckDuckGoSearchTool # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # --- Basic Agent Definition --- class BasicAgent: def __init__(self): print("Initializing Smolagents CodeAgent...") # 1. Define the Model # Qwen 2.5 Coder is excellent for the logic/math required in GAIA # It will automatically use the HF_TOKEN from your Space Secrets model = HfApiModel( model_id="Qwen/Qwen2.5-Coder-32B-Instruct", ) # 2. Define Tools search_tool = DuckDuckGoSearchTool() # 3. Initialize the Agent # We allow imports like requests and bs4 so the agent can scrape if needed self.agent = CodeAgent( tools=[search_tool], model=model, additional_authorized_imports=["requests", "bs4", "datetime", "pandas", "math"], max_steps=20, # Give it enough steps to think verbosity_level=1 ) print("Agent initialized successfully.") def __call__(self, question: str) -> str: print(f"Agent received question: {question}") try: # Run the smolagent # We cast to string in case the agent returns a non-string object answer = self.agent.run(question) print(f"Agent calculated answer: {answer}") return str(answer) except Exception as e: print(f"Agent failed with error: {e}") return "Error processing request" # --- Logic to Run and Submit (Provided by Course Template) --- def run_and_submit_all(profile: gr.OAuthProfile | None): """ Fetches all questions, runs the BasicAgent on them, submits all answers, and displays the results. """ # --- Determine HF Space Runtime URL and Repo URL --- space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code if profile: username = f"{profile.username}" print(f"User logged in: {username}") else: print("User not logged in.") 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" # 1. Instantiate Agent try: agent = BasicAgent() except Exception as e: print(f"Error instantiating agent: {e}") return f"Error initializing agent: {e}", None # Link to your codebase agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "https://huggingface.co/spaces/generic/tree/main" print(agent_code) # 2. Fetch Questions print(f"Fetching questions from: {questions_url}") try: response = requests.get(questions_url, timeout=15) response.raise_for_status() questions_data = response.json() if not questions_data: print("Fetched questions list is empty.") return "Fetched questions list is empty or invalid format.", None 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 Exception as e: print(f"An unexpected error occurred fetching questions: {e}") return f"An unexpected error occurred fetching questions: {e}", None # 3. Run your Agent results_log = [] answers_payload = [] print(f"Running agent on {len(questions_data)} questions...") for i, item in enumerate(questions_data): task_id = item.get("task_id") question_text = item.get("question") print(f"Processing {i+1}/{len(questions_data)}: Task {task_id}") if not task_id or question_text is None: continue try: # THE AGENT CALL 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: print(f"Error running agent 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("Agent did not produce any answers to submit.") return "Agent did not produce any answers to submit.", pd.DataFrame(results_log) # 4. Prepare Submission submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload} status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..." print(status_update) # 5. Submit 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.") results_df = pd.DataFrame(results_log) return final_status, results_df except Exception as e: status_message = f"Submission Failed: {e}" print(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df # --- Build Gradio Interface --- with gr.Blocks() as demo: gr.Markdown("# Final Agent Evaluation Runner (SmolAgents)") gr.Markdown( """ **Instructions:** 1. Ensure `HF_TOKEN` is set in your Space Secrets. 2. Log in via the button below. 3. Click 'Run Evaluation'. *Note: This process takes a few minutes as the agent thinks through 10-20 questions.* """ ) gr.LoginButton() run_button = gr.Button("Run Evaluation & Submit All Answers", variant="primary") status_output = gr.Textbox(label="Status", lines=5, interactive=False) results_table = gr.DataFrame(label="Results", wrap=True) run_button.click( fn=run_and_submit_all, outputs=[status_output, results_table] ) if __name__ == "__main__": demo.launch()