import os import time import tempfile import gradio as gr import pandas as pd import traceback from src.agent import CustomAgent, get_config from src.api_client import ApiClient # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" def run_and_submit_all(profile: gr.OAuthProfile | None): """ Fetches all questions, runs the CustomAgent on them, submits all answers, and displays the results. """ # --- Determine HF Space Runtime URL and Repo URL --- space_id = os.getenv("SPACE_ID") 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 # 1. Instantiate Agent ( modify this part to create your agent) agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" print(agent_code) try: agent_config = get_config() print(f"Using agent configuration: {agent_config}") agent = CustomAgent(**agent_config) print("Agent initialized successfully") except Exception as e: error_details = traceback.format_exc() print(f"Error initializing agent: {e}\n{error_details}") return f"Error initializing agent: {e}", None # 2. Fetch Questions api_client = ApiClient(DEFAULT_API_URL) try: questions_data = api_client.get_questions() if not questions_data: return "Fetched questions list is empty or invalid format.", None print(f"Fetched {len(questions_data)} questions.") except Exception as e: error_details = traceback.format_exc() print(f"Error fetching questions: {e}\n{error_details}") return f"Error fetching questions: {e}", None # 3. Run your Agent results_log = [] answers_payload = [] total_questions = len(questions_data) completed = 0 failed = 0 print(f"Running agent on {total_questions} questions...") for item in questions_data: task_id = item.get("task_id") question_text = item.get("question") file_name = item.get("file_name") file_path = None if not task_id or question_text is None: print(f"Skipping item with missing task_id or question: {item}") continue try: # Update progress completed += 1 print( f"Processing question {completed}/{total_questions}: Task ID {task_id}" ) # Check if the question has an associated file if file_name: try: file_path = api_client.get_file(task_id=task_id, file_name=file_name) except Exception as file_e: print(f"Failed to download the file for task {task_id} - {file_e}") # Run the agent to get the answer submitted_answer = agent.forward(question_text, file_path) if submitted_answer: print(f"{submitted_answer[:100]}...") # Add to results 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: # Update error count failed += 1 error_details = traceback.format_exc() print(f"Error running agent on task {task_id}: {e}\n{error_details}") # Add error to results error_msg = f"AGENT ERROR: {e}" answers_payload.append({"task_id": task_id, "submitted_answer": error_msg}) results_log.append( { "Task ID": task_id, "Question": question_text, "Submitted Answer": error_msg, } ) finally: if completed+failed < total_questions: time.sleep(55) # Print summary print(f"\nProcessing complete: {completed} questions processed, {failed} failures") if not answers_payload: return "Agent did not produce any answers to submit.", pd.DataFrame(results_log) # Store results in a log file log_file_path = "src/temp/log.txt" os.makedirs(os.path.dirname(log_file_path), exist_ok=True) timestamp = time.strftime("%Y-%m-%d %H:%M:%S") with open(log_file_path, "a") as log_file: for entry in results_log: log_file.write(f"{timestamp} - {entry}\n") log_file.write( f"{timestamp} - Summary: {completed} questions processed, {failed} failures\n\n" ) # 4. Prepare Submission print(f"Submitting {len(answers_payload)} answers for username '{username}'...") try: result_data = api_client.submit_answers( username.strip(), agent_code, answers_payload, ) # Calculate success rate correct_count = result_data.get("correct_count", 0) total_attempted = result_data.get("total_attempted", len(answers_payload)) success_rate = ( (correct_count / total_attempted) * 100 if total_attempted > 0 else 0 ) final_status = ( f"Submission Successful!\n" f"User: {result_data.get('username')}\n" f"Overall Score: {result_data.get('score', 'N/A')}% " f"({correct_count}/{total_attempted} correct, {success_rate:.1f}% success rate)\n" f"Message: {result_data.get('message', 'No message received.')}" ) print("Submission successful.") return final_status, pd.DataFrame(results_log) except Exception as e: error_details = traceback.format_exc() status_message = f"Submission Failed: {e}\n{error_details}" print(status_message) return status_message, pd.DataFrame(results_log) # --- Build Gradio Interface using Blocks --- with gr.Blocks() as demo: gr.Markdown("# Basic 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=run_and_submit_all, outputs=[status_output, results_table]) if __name__ == "__main__": print("\n" + "-" * 30 + " App Starting " + "-" * 30) # 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?).") if space_id_startup: # Print repo URLs if SPACE_ID is found 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." ) print("-" * (60 + len(" App Starting ")) + "\n") print("Launching Gradio Interface for Basic Agent Evaluation...") demo.launch(debug=True, share=False)