import os import re import gradio as gr import requests import pandas as pd from smolagents import CodeAgent, DuckDuckGoSearchTool from smolagents.models import OpenAIServerModel SYSTEM_PROMPT = """You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.""" DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" def extract_final_answer(response_text: str) -> str: match = re.search(r"FINAL ANSWER:\s*(.*)", response_text, re.IGNORECASE) return match.group(1).strip() if match else response_text.strip() class MyAgent: def __init__(self): self.model = OpenAIServerModel(model_id="gpt-4") self.agent = CodeAgent( tools=[DuckDuckGoSearchTool()], model=self.model ) def __call__(self, question: str) -> str: messages = [ {"role": "system", "content": SYSTEM_PROMPT}, {"role": "user", "content": question} ] try: response = self.model(messages) # Extract the actual text from response if isinstance(response, dict): choices = response.get('choices') if choices and len(choices) > 0: text = choices[0].get('message', {}).get('content', '') else: text = '' elif isinstance(response, str): text = response else: text = str(response) return extract_final_answer(text) except Exception as e: import traceback traceback.print_exc() return f"AGENT ERROR: {e}" def run_and_submit_all(profile: gr.OAuthProfile | None): 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 with the button.", None api_url = DEFAULT_API_URL questions_url = f"{api_url}/questions" submit_url = f"{api_url}/submit" try: agent = MyAgent() 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 or invalid format.", 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": 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.')}" ) results_df = pd.DataFrame(results_log) return final_status, results_df 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 Exception: error_detail += f" Response: {e.response.text[:500]}" return f"Submission Failed: {error_detail}", pd.DataFrame(results_log) except requests.exceptions.Timeout: return "Submission Failed: The request timed out.", pd.DataFrame(results_log) except Exception as e: return f"An unexpected error occurred during submission: {e}", pd.DataFrame(results_log) with gr.Blocks() as demo: gr.Markdown("# Basic Agent Evaluation Runner") gr.Markdown( """ **Instructions:** 1. Clone this space, modify code to define your agent's logic, tools, and packages. 2. Log in to your Hugging Face account using the button below. 3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see your score. **Note:** Submitting can take some time. """ ) 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("\n" + "-"*30 + " App Starting " + "-"*30) space_host = os.getenv("SPACE_HOST") space_id = os.getenv("SPACE_ID") if space_host: print(f"✅ SPACE_HOST found: {space_host}") print(f" Runtime URL should be: https://{space_host}.hf.space") else: print("ℹ️ SPACE_HOST environment variable not found (running locally?).") if space_id: print(f"✅ SPACE_ID found: {space_id}") print(f" Repo URL: https://huggingface.co/spaces/{space_id}") print(f" Repo Tree URL: https://huggingface.co/spaces/{space_id}/tree/main") else: print("ℹ️ SPACE_ID environment variable not found (running locally?).") print("-"*(60 + len(" App Starting ")) + "\n") print("Launching Gradio Interface for Basic Agent Evaluation...") demo.launch(debug=True, share=False)