#!/usr/bin/env python3 """ GAIA Benchmark Agent Interface This script integrates the modular GAIA agent with the provided interface template. It replaces the BasicAgent class with our GAIA agent implementation. """ import os import gradio as gr import requests import inspect import pandas as pd from typing import Dict, List, Any, Optional # Import the GAIA agent modules from gaiaX.config import ( logger, CONFIG, HF_USERNAME, OPENAI_API_KEY, TAVILY_API_KEY, API_BASE_URL, validate_env_vars ) from gaiaX.agent import initialize_agent, get_agent_response from gaiaX.question_handlers import process_question, detect_question_type # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # --- GAIA Agent Implementation --- class GAIAAgent: """ GAIA Benchmark Agent implementation that integrates with the provided interface. """ def __init__(self): """Initialize the GAIA agent.""" logger.info("Initializing GAIA agent...") # Validate environment variables try: validate_env_vars() except ValueError as e: logger.error(f"Environment validation failed: {e}") raise # Initialize the LangChain agent self.agent = initialize_agent(OPENAI_API_KEY, "openai_functions") logger.info("GAIA agent initialized successfully.") def __call__(self, question: str) -> str: """ Process a question and return the answer. Args: question: The question text Returns: The agent's answer as a string """ logger.info(f"Agent received question (first 50 chars): {question[:50]}...") # Create a question dictionary question_dict = { "task_id": "custom_question", "question": question, "has_file": False } # Process the question try: # Detect question type question_type = detect_question_type(question) logger.info(f"Detected question type: {question_type}") # Process the question result = process_question(self.agent, question_dict, API_BASE_URL) # Extract the answer answer = result.get("answer", "") if not answer: logger.warning("Agent returned an empty answer.") answer = "I couldn't generate an answer for this question." logger.info(f"Agent returning answer (first 50 chars): {answer[:50]}...") return answer except Exception as e: logger.error(f"Error processing question: {e}") return f"Error: {str(e)}" # --- Run and Submit All Function --- def run_and_submit_all(profile: gr.OAuthProfile | None): """ Fetches all questions, runs the GAIA Agent on them, submits all answers, and displays the results. """ # --- Determine HF Space Runtime URL and Repo URL --- 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" # 1. Instantiate Agent try: agent = GAIAAgent() 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 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 # 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") if not task_id or question_text is None: print(f"Skipping item with missing task_id or question: {item}") 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: 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("# GAIA Benchmark Agent Evaluation Runner") gr.Markdown( """ **Instructions:** 1. Log in to your Hugging Face account using the button below. This uses your HF username for submission. 2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score. --- **Note:** This interface uses the modular GAIA Benchmark Agent to process questions from the GAIA benchmark. The agent uses LangChain and OpenAI's language models to analyze questions, retrieve relevant context, and generate accurate answers across various domains of AI and machine learning. """ ) 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) # 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 GAIA Benchmark Agent Evaluation...") demo.launch(debug=True, share=False)