import os import gradio as gr import requests import pandas as pd import traceback from agents import manager_agent from datetime import datetime from typing import Optional import time # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" class BasicAgent: def __init__(self): print("BasicAgent initialized.") self.agent = manager_agent self.verbose = True def __call__(self, question: str, files: list[str] = None) -> str: print(f"Agent received question: {question[:50]}... with files: {files}") # Handle files being a list - extract the first file if it's a list file_path = None if files: if isinstance(files, list) and len(files) > 0: file_path = files[0] elif isinstance(files, str): file_path = files result = self.answer_question(question, file_path) print(f"Agent returning answer: {result}") return result def answer_question(self, question: str, task_file_path: Optional[str] = None) -> str: """ Process a GAIA benchmark question and return the answer """ try: if self.verbose: print(f"Processing question: {question}") if task_file_path: print(f"With associated file: {task_file_path}") # Create a context with file information if available context = question # If there's a file, read it and include its content in the context if task_file_path: try: context = f""" Question: {question} This question has an associated file. You can download the file from {DEFAULT_API_URL}/files/{task_file_path} using the download_file_from_url tool. Analyze the file content above to answer the question. """ except Exception as file_e: context = f""" Question: {question} This question has an associated file at path: {task_file_path} However, there was an error reading the file: {file_e} You can still try to answer the question based on the information provided. """ # Check for special cases that need specific formatting if question.startswith(".") or ".rewsna eht sa" in question: context = f""" This question appears to be in reversed text. Here's the reversed version: {question[::-1]} Now answer the question above. Remember to format your answer exactly as requested. """ # Add a prompt to ensure precise answers full_prompt = f"""{context} When answering, provide ONLY the precise answer requested. Do not include explanations, steps, reasoning, or additional text. Be direct and specific. GAIA benchmark requires exact matching answers. For example, if asked "What is the capital of France?", respond simply with "Paris". """ # *** FIXED AGENT CALL - Handles all response formats *** try: raw_response = self.agent.run(full_prompt) if self.verbose: print(f"Raw response type: {type(raw_response)}") print(f"Raw response: {raw_response}") # Handle ALL possible response formats if isinstance(raw_response, dict): answer = raw_response.get('choices', [{}])[0].get('message', {}).get('content', str(raw_response)) elif isinstance(raw_response, list): if len(raw_response) > 0: if isinstance(raw_response[0], dict): # Common format: [{"role": "assistant", "content": "..."}] answer = raw_response[0].get('content', str(raw_response[0])) elif isinstance(raw_response[0], list): # Nested list - dig deeper nested = raw_response[0] if isinstance(nested, list) and len(nested) > 0: if isinstance(nested[0], dict): answer = nested[0].get('content', str(nested[0])) else: answer = str(nested[0]) else: answer = str(raw_response[0]) else: answer = str(raw_response[0]) else: answer = "No response" else: answer = str(raw_response) if self.verbose: print(f"Extracted answer type: {type(answer)}") print(f"Extracted answer value: {answer}") except Exception as agent_error: print(f"Agent run error: {agent_error}") traceback.print_exc() return f"Agent error: {agent_error}" # Clean the answer answer = self._clean_answer(answer) if self.verbose: print(f"Generated answer: {answer}") return answer except Exception as e: error_msg = f"Error answering question: {e}" if self.verbose: print(error_msg) traceback.print_exc() return error_msg def _clean_answer(self, answer: any) -> str: """ Ultra-safe answer extraction and cleaning """ # Force to string immediately with extra safety try: if answer is None: return "" if isinstance(answer, list): # If it's a list, try to extract meaningful content if len(answer) == 0: return "" # Try to get content from first element answer = answer[0] if len(answer) > 0 else "" if isinstance(answer, dict): # If it's a dict, try to get 'content' or convert to string answer = answer.get('content', str(answer)) if not isinstance(answer, str): answer = str(answer) except Exception as e: print(f"Error in initial conversion: {e}") return str(answer) if answer else "" # Now answer should definitely be a string try: # Strip whitespace answer = answer.strip() # Remove common prefixes that models often add prefixes_to_remove = [ "The answer is ", "Answer: ", "Final answer: ", "The result is ", "To answer this question: ", "Based on the information provided, ", "According to the information: ", ] for prefix in prefixes_to_remove: if answer.startswith(prefix): answer = answer[len(prefix):].strip() # Remove wrapping quotes if (answer.startswith('"') and answer.endswith('"')) or \ (answer.startswith("'") and answer.endswith("'")): answer = answer[1:-1].strip() return answer except Exception as e: print(f"Error in answer cleaning: {e}, returning raw string") return str(answer) if answer else "" def run_and_submit_all(profile: gr.OAuthProfile | None): """ Fetches all questions, runs the BasicAgent on them, submits all answers, and displays the results. """ 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 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 agent_code = f"https://github.com/ssgrummons/huggingface_final_assignment" 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 # 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") files = item.get("file_name") if not task_id or question_text is None: print(f"Skipping item with missing task_id or question: {item}") continue try: # Handle files - could be None, empty string, list, or string if files is None or files == '' or (isinstance(files, list) and len(files) == 0): print(f"No files for task {task_id}") submitted_answer = agent(question_text) else: print(f"Processing task {task_id} with file: {files} (type: {type(files)})") submitted_answer = agent(question_text, files) 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 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 # --- 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. """ ) 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] ) import sys from pathlib import Path class Tee: def __init__(self, file_path): log_path = Path(file_path) log_path.parent.mkdir(parents=True, exist_ok=True) self.terminal_stdout = sys.__stdout__ self.terminal_stderr = sys.__stderr__ self.log = open(log_path, "a") def write(self, message): self.terminal_stdout.write(message) self.log.write(message) def flush(self): self.terminal_stdout.flush() self.log.flush() def isatty(self): return self.terminal_stdout.isatty() if __name__ == "__main__": # Redirect stdout and stderr log_timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S") log_file = f"./logs/output_{log_timestamp}.log" tee = Tee(log_file) sys.stdout = tee sys.stderr = tee print("\n" + "-"*30 + " App Starting " + "-"*30) space_host_startup = os.getenv("SPACE_HOST") space_id_startup = os.getenv("SPACE_ID") 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(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)