import os import gradio as gr import requests import pandas as pd from alfred import Alfred # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" MOCK_SUBMISSION = True QUESTIONS_LIMIT = 3 # Use 0 for no limit ! class Application: def __init__(self): self.space_id = os.getenv("SPACE_ID") self.username = None self.questions_url, self.submit_url = self._get_runtime_and_repo_urls() @staticmethod def _get_username(profile: gr.OAuthProfile | None): """Get profile username""" if profile: username= f"{profile.username}" print(f"User logged in: {username}") return username else: print("User not logged in.") return None @staticmethod def _get_runtime_and_repo_urls(): """Determine HF Space Runtime URL and Repo URL""" api_url = DEFAULT_API_URL questions_url = f"{api_url}/questions" submit_url = f"{api_url}/submit" return questions_url, submit_url def _fetch_questions(self): """ Fetches questions from `questions_url`. Sends a GET request to retrieve and parse questions as JSON. Handles network, JSON decoding, and unexpected errors. Returns: tuple: (error_message: str or None, questions: list or None) Logs: - Progress, success, empty data, or errors. """ print(f"Fetching questions from: {self.questions_url}") try: response = requests.get(self.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.JSONDecodeError as e: print(f"Error decoding JSON response from questions endpoint: {e}") print(f"Response text: {response.text[:500]}") return f"Error decoding server response for questions: {e}", None 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 return questions_data @staticmethod async def _run_agent(questions_data, agent): """ Runs the agent on a list of questions and collects results. Args: questions_data (list): List of question dictionaries with "task_id" and "question". agent (callable): Callable that processes a question and returns an answer. Returns: tuple: - results_log (list): Logs with "Task ID", "Question", and "Submitted Answer". - answers_payload (list): Payload with "task_id" and "submitted_answer". """ if QUESTIONS_LIMIT > 0: questions_data = questions_data[:QUESTIONS_LIMIT] 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 item with missing task_id or question: {item}") continue try: submitted_answer = await agent(question_text) print(f"SUBMITED_ANSWER: {submitted_answer}") 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}"}) return results_log, answers_payload def _submit(self, answers_payload, submission_data, results_log): """ Submits answers to the specified URL and processes the response. Args: answers_payload (list): List of answers to submit. submission_data (dict): Payload for the POST request. results_log (list): Log of results to convert into a DataFrame. Returns: tuple: (status_message (str), results_df (pd.DataFrame)). Notes: - Sends a POST request to `self.submit_url` with `submission_data`. - Handles exceptions and provides error messages. """ print(f"Submitting {len(answers_payload)} answers to: {self.submit_url}") try: if MOCK_SUBMISSION: mock_response = type('MockResponse', (), { 'status_code': 200, 'json': lambda *args: { "username": self.username, "score": 100, "correct_count": len(answers_payload), "total_attempted": len(answers_payload), "message": "Mock submission successful." } }) response = mock_response() else: response = requests.post(self.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 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 requests.exceptions.JSONDecodeError: error_detail += f" Response: {e.response.text[:500]}" status_message = f"Submission Failed: {error_detail}" print(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df except requests.exceptions.Timeout: status_message = "Submission Failed: The request timed out." print(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df except requests.exceptions.RequestException as e: status_message = f"Submission Failed: Network error - {e}" print(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df except Exception as e: status_message = f"An unexpected error occurred during submission: {e}" print(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df async def eval_and_submit_all(self, profile: gr.OAuthProfile | None): """ Fetches all questions, runs the agent on them, submits all answers, and displays the results. """ self.username = self._get_username(profile) if self.username is None: return "Please Login to Hugging Face with the button.", None # 1. Instantiate the Main Agent try: agent = Alfred() except Exception as e: print(f"Error instantiating agent: {e}") return f"Error initializing agent: {e}", None # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public) agent_code = f"https://huggingface.co/spaces/{self.space_id}/tree/main" print(agent_code) # 2. Fetch Questions questions_data = self._fetch_questions() # 3. Run your Agent results_log, answers_payload = await self._run_agent(questions_data, agent) 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": self.username.strip(), "agent_code": agent_code, "answers": answers_payload} status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{self.username}'..." print(status_update) # 5. Submit status_message, results_df = self._submit(answers_payload, submission_data, results_log) return status_message, results_df class UI: app = Application() @classmethod def _check_space_host_and_id(cls): """Check for SPACE_HOST and SPACE_ID at startup for information""" space_host_startup = os.getenv("SPACE_HOST") space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup if space_host_startup: print(f"✅ SPACE_HOST found: {space_host_startup}") print(f" Runtime URL should be: https://{space_host_startup}.hf.space") else: print("ℹ️ SPACE_HOST environment variable not found (running locally?).") # Print repo URLs if SPACE_ID is found if space_id_startup: print(f"✅ SPACE_ID found: {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("ℹ️ SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.") @classmethod def _build(cls): gr.Markdown("# Main Agent Evaluation Runner") gr.Markdown( """ **Instructions:** 1. Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ... 2. Log in to your Hugging Face account using the button below. This uses your HF username for submission. 3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score. --- **Disclaimers:** Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions). This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async. """ ) gr.LoginButton() run_button = gr.Button("Run Evaluation & Submit All Answers") status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False) # Removed max_rows=10 from DataFrame constructor results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True) run_button.click( fn=cls.app.eval_and_submit_all, outputs=[status_output, results_table] ) @classmethod def launch(cls): """Build Gradio Interface using Blocks""" with gr.Blocks() as demo: cls._build() if __name__ == "__main__": print("\n" + "-"*30 + " App Starting " + "-"*30) cls._check_space_host_and_id() print("-"*(60 + len(" App Starting ")) + "\n") print("Launching Gradio Interface for Main Agent Evaluation...") demo.launch(debug=True, share=False) UI.launch()