import os import sys import json import tempfile import gradio as gr import requests import inspect import pandas as pd from typing import List, Dict, Any, Optional import traceback # vimport dotenv # Load environment variables from .env file # dotenv.load_dotenv() # Import our agent from agent import QAgent from answer_data_manager import AnswerDataManager # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # Simulation of GAIA benchmark questions SAMPLE_QUESTIONS = [ { "task_id": "task_002", "question": "What is the square root of 144?", "expected_answer": "12", "has_file": False, "file_content": None } ] SAMPLE_QUESTIONS_OUT = [ { "task_id": "task_001", "question": "What is the capital of France?", "expected_answer": "Paris", "has_file": False, "file_content": None }, { "task_id": "task_003", "question": "If a train travels at 60 miles per hour, how far will it travel in 2.5 hours?", "expected_answer": "150 miles", "has_file": False, "file_content": None }, { "task_id": "task_004", "question": ".rewsna eht sa 'thgir' drow eht etirw ,tfel fo etisoppo eht si tahW", "expected_answer": "right", "has_file": False, "file_content": None }, { "task_id": "task_005", "question": "Analyze the data in the attached CSV file and tell me the total sales for the month of January.", "expected_answer": "$10,250.75", "has_file": True, "file_content": """Date,Product,Quantity,Price,Total 2023-01-05,Widget A,10,25.99,259.90 2023-01-12,Widget B,5,45.50,227.50 2023-01-15,Widget C,20,50.25,1005.00 2023-01-20,Widget A,15,25.99,389.85 2023-01-25,Widget B,8,45.50,364.00 2023-01-28,Widget D,100,80.04,8004.50""" }, { "task_id": "task_006", "question": "I'm making a grocery list for my mom, but she's a picky eater. She only eats foods that don't contain the letter 'e'. List 5 common fruits and vegetables she can eat.", "expected_answer": "Banana, Kiwi, Corn, Fig, Taro", "has_file": False, "file_content": None }, { "task_id": "task_007", "question": "How many studio albums were published by Mercedes Sosa between 1972 and 1985?", "expected_answer": "12", "has_file": False, "file_content": None }, { "task_id": "task_008", "question": "In the video https://www.youtube.com/watch?v=L1vXC1KMRd0, what color is primarily associated with the main character?", "expected_answer": "Blue", "has_file": False, "file_content": None } ] def init_agent(): """Initialize the QAgent.""" print("Initializing QAgent...") try: agent = QAgent() return agent except Exception as e: print(f"Error instantiating agent for GAIA simulation: {e}") return None def save_test_file(task_id: str, content: str) -> str: """Save a test file to a temporary location.""" temp_dir = tempfile.gettempdir() file_path = os.path.join(temp_dir, f"test_file_{task_id}.csv") with open(file_path, 'w') as f: f.write(content) return file_path def run_GAIA_questions_simu(): """ Used only during development for test that simulate GAIA questions. """ # 1. Instantiate Agent agent = init_agent() results = [] correct_count = 0 total_count = len(SAMPLE_QUESTIONS) for idx, question_data in enumerate(SAMPLE_QUESTIONS): task_id = question_data["task_id"] question = question_data["question"] expected = question_data["expected_answer"] print(f"\n{'='*80}") print(f"Question {idx+1}/{total_count}: {question}") print(f"Expected: {expected}") # Process any attached file # file_path = None # if question_data["has_file"] and question_data["file_content"]: # file_path = save_test_file(task_id, question_data["file_content"]) # print(f"Created test file: {file_path}") # Get answer from agent try: answer = agent.invoke(question) # , file_path) print(f"Agent answer: {answer}") # Check if answer matches expected is_correct = answer.lower() == expected.lower() if is_correct: correct_count += 1 print(f"✅ CORRECT") else: print(f"❌ INCORRECT - Expected: {expected}") results.append({ "task_id": task_id, "question": question, "expected": expected, "answer": answer, "is_correct": is_correct }) except Exception as e: error_details = traceback.format_exc() print(f"Error processing question: {e}\n{error_details}") results.append({ "task_id": task_id, "question": question, "expected": expected, "answer": f"ERROR: {str(e)}", "is_correct": False }) # Print summary accuracy = (correct_count / total_count) * 100 print(f"\n{'='*80}") print(f"Test Results: {correct_count}/{total_count} correct ({accuracy:.1f}%)") return results def run_simuGAIA_all( profile: gr.OAuthProfile | None, submit: Optional[bool] = True): """ Fetches all questions, runs the QAgent on them, and displays the results. """ # --- Determine HF Space Runtime URL and Repo URL for submission --- 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" print("submit_url = " + submit_url + " with username = " + username) # 1. Instantiate and init Agent ( modify this part to create your agent) agent = init_agent() # 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/{space_id}/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 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 Exception as e: print(f"An unexpected error occurred fetching questions: {e}") return f"An unexpected error occurred fetching questions: {e}", None # 2.5 Awaken the AnswerDataManager to get and store already answered questions manager = AnswerDataManager("already_answered.json") data = manager.load_data() print(data.__str__) # 3. Run your Agent 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") submitted_answer = "NO ANSWER YET" if not task_id or question_text is None: print(f"Skipping item with missing task_id or question: {item}") continue try: existing_answer = manager.get_answer_by_task_id(task_id) if not existing_answer: # then we call the agent if question_text.startswith("What si the first name of"): # **NOK**: ("Who are the pitchers"): # **NOK**:("What country had the least number"): # ("Where were the Vietnamese"): # ("On June 6, 2023, an article"): # ("How many at bats did the Yankee"): # ("Who did the actor who"): # ("m making a grocery list", 2): # ("What is the surname of the"): # ("Given this table"): # ("Who nominated the only"): # ("How many studio albums"): # (".rewsna eht sa"): <--- REMOVE THAT FOR ALL QUESTIONS print(f"Precise question detected. INVOKING AGENT! Be careful!") submitted_answer = agent.invoke(question_text) # Save answer, task_id, and question_text to already_answered.json # manager.add_answer(task_id, question_text, submitted_answer) success = manager.add_answer( task_id=task_id, question=question_text, submitted_answer=submitted_answer ) if not success: print("Error saving answer to archive.") answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer}) else: submitted_answer = "NO AGENT INVOKED" else: # then we get answer already found from archive submitted_answer = existing_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}"}) 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}' with url being {agent_code}..." print(status_update) print(f"Answers payload content: {answers_payload}") # for answer in answers_payload: # print("task_id: " + answer["Task ID"]) # print("answer: " + answer["Submitted Answer"]) if not submit: return "Run finished. No submission done, as asked.", pd.DataFrame(results_log) # 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 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