Spaces:
Runtime error
Runtime error
| import json | |
| import os | |
| import gradio as gr | |
| import requests | |
| import pandas as pd | |
| from agent import gaia_hf_agent | |
| from langchain_core.messages import HumanMessage | |
| from logging_config import setup_logging, get_logger | |
| # Set up logging | |
| setup_logging(log_level="INFO", log_file="logs/app.log") | |
| logger = get_logger(__name__) | |
| # (Keep Constants as is) | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| FETCH_QUESTIONS_FROM_FILE = True | |
| # --- Basic Agent Definition --- | |
| # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ | |
| def run_and_submit_all( profile: gr.OAuthProfile | None): | |
| """Fetches all questions, runs the BasicAgent on them, submits all answers, and displays the results. | |
| Args: | |
| profile: The profile of the user who is logged in. | |
| """ | |
| logger.info("=== Starting evaluation process ===") | |
| # --- Determine HF Space Runtime URL and Repo URL --- | |
| space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code | |
| logger.debug(f"Space ID retrieved: {space_id}") | |
| # Step 1: User Authentication | |
| logger.info("Step 1: Checking user authentication") | |
| if profile: | |
| username= f"{profile.username}" | |
| logger.info(f"User successfully authenticated: {username}") | |
| else: | |
| logger.warning("User authentication failed - no profile found") | |
| 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" | |
| logger.info(f"API URLs configured - Questions: {questions_url}, Submit: {submit_url}") | |
| # Step 2: Agent Instantiation | |
| logger.info("Step 2: Instantiating agent") | |
| try: | |
| agent = gaia_hf_agent | |
| logger.info("Agent successfully instantiated") | |
| except Exception as e: | |
| logger.error(f"Error instantiating agent: {e}", exc_info=True) | |
| 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/{space_id}/tree/main" | |
| logger.info(f"Agent code URL: {agent_code}") | |
| # Step 3: Question Fetching | |
| logger.info("Step 3: Fetching questions") | |
| if FETCH_QUESTIONS_FROM_FILE: | |
| logger.info("Fetching questions from local file") | |
| try: | |
| with open("gaia_test_files/filtered_question_list.json", "r", encoding='utf-8') as file: | |
| questions_data = json.load(file) | |
| logger.info(f"Successfully loaded {len(questions_data)} questions from file") | |
| except FileNotFoundError as e: | |
| logger.error(f"Question file not found: {e}") | |
| return f"Question file not found: {e}", None | |
| except json.JSONDecodeError as e: | |
| logger.error(f"Error parsing question file JSON: {e}") | |
| return f"Error parsing question file: {e}", None | |
| except Exception as e: | |
| logger.error(f"Unexpected error loading question file: {e}", exc_info=True) | |
| return f"Error loading questions: {e}", None | |
| else: | |
| logger.info(f"Fetching questions from API: {questions_url}") | |
| try: | |
| response = requests.get(questions_url, timeout=15) | |
| response.raise_for_status() | |
| questions_data = response.json() | |
| if not questions_data: | |
| logger.warning("Fetched questions list is empty") | |
| return "Fetched questions list is empty or invalid format.", None | |
| logger.info(f"Successfully fetched {len(questions_data)} questions from API") | |
| except requests.exceptions.RequestException as e: | |
| logger.error(f"Network error fetching questions: {e}") | |
| return f"Error fetching questions: {e}", None | |
| except requests.exceptions.JSONDecodeError as e: | |
| logger.error(f"Error decoding JSON response from questions endpoint: {e}") | |
| logger.debug(f"Response text: {response.text[:500]}") | |
| return f"Error decoding server response for questions: {e}", None | |
| except Exception as e: | |
| logger.error(f"Unexpected error occurred fetching questions: {e}", exc_info=True) | |
| return f"An unexpected error occurred fetching questions: {e}", None | |
| # Step 4: Agent Execution | |
| logger.info(f"Step 4: Running agent on {len(questions_data)} questions") | |
| results_log = [] | |
| answers_payload = [] | |
| successful_answers = 0 | |
| failed_answers = 0 | |
| for i, item in enumerate(questions_data, 1): | |
| task_id = item.get("task_id") | |
| question_text = item.get("question") | |
| file_name = item.get("file_name") | |
| logger.info(f"Processing question {i}/{len(questions_data)} - Task ID: {task_id}") | |
| current_question = { | |
| "question": question_text | |
| } | |
| if file_name: | |
| current_question["question_file_url"] = f"{DEFAULT_API_URL}/files/{task_id}" | |
| logger.debug(f"Question includes file: {file_name}") | |
| agent_input = [HumanMessage(json.dumps(current_question))] | |
| if not task_id or question_text is None: | |
| logger.warning(f"Skipping item with missing task_id or question: {item}") | |
| failed_answers += 1 | |
| continue | |
| try: | |
| logger.debug(f"Invoking agent for task {task_id}") | |
| response = agent.invoke({"messages": agent_input}) | |
| submitted_answer = response['messages'][-1].content | |
| 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}) | |
| successful_answers += 1 | |
| logger.info(f"Successfully processed task {task_id} ({i}/{len(questions_data)})") | |
| logger.debug(f"Answer for task {task_id}: {submitted_answer}") | |
| except Exception as e: | |
| logger.error(f"Error running agent on task {task_id}: {e}", exc_info=True) | |
| error_msg = f"AGENT ERROR: {e}" | |
| results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": error_msg}) | |
| failed_answers += 1 | |
| logger.info(f"Agent execution completed - Success: {successful_answers}, Failed: {failed_answers}") | |
| if not answers_payload: | |
| logger.error("Agent did not produce any answers to submit") | |
| return "Agent did not produce any answers to submit.", pd.DataFrame(results_log) | |
| # Step 5: Submission Preparation | |
| logger.info("Step 5: Preparing 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}'..." | |
| logger.info(status_update) | |
| logger.debug(f"Submission payload prepared with {len(answers_payload)} answers") | |
| # Step 6: Answer Submission | |
| logger.info(f"Step 6: Submitting {len(answers_payload)} answers to: {submit_url}") | |
| try: | |
| logger.debug("Sending POST request to submission endpoint") | |
| 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.')}" | |
| ) | |
| logger.info("=== Submission successful ===") | |
| logger.info(f"Final score: {result_data.get('score', 'N/A')}% " | |
| f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)") | |
| logger.debug(f"Full submission result: {result_data}") | |
| 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}" | |
| logger.error(f"HTTP error during submission: {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." | |
| logger.error("Submission request timed out after 60 seconds") | |
| 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}" | |
| logger.error(f"Network error during submission: {e}", exc_info=True) | |
| 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}" | |
| logger.error(f"Unexpected error during submission: {e}", exc_info=True) | |
| 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. 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__": | |
| logger.info("=" * 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: | |
| logger.info(f"✅ SPACE_HOST found: {space_host_startup}") | |
| logger.info(f" Runtime URL should be: https://{space_host_startup}.hf.space") | |
| else: | |
| logger.info("ℹ️ SPACE_HOST environment variable not found (running locally?).") | |
| if space_id_startup: # Print repo URLs if SPACE_ID is found | |
| logger.info(f"✅ SPACE_ID found: {space_id_startup}") | |
| logger.info(f" Repo URL: https://huggingface.co/spaces/{space_id_startup}") | |
| logger.info(f" Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main") | |
| else: | |
| logger.info("ℹ️ SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.") | |
| logger.info("=" * (60 + len(" App Starting "))) | |
| logger.info("Launching Gradio Interface for Basic Agent Evaluation...") | |
| demo.launch(debug=True, share=False) | |