import os import json from dotenv import load_dotenv import gradio as gr import requests import inspect import pandas as pd from agent import BasicAgent import time from datetime import datetime # Load environment variables from .env file load_dotenv() # --- Constants --- DEFAULT_API_URL = os.getenv('DEFAULT_API_URL', "https://agents-course-unit4-scoring.hf.space") CHECKPOINT_FILE = "agent_checkpoint.json" def run_and_submit_all( profile: gr.OAuthProfile | None): """ Fetches all questions, runs the BasicAgent 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 ( modify this part to create your agent) try: agent = BasicAgent() 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 ( usefull for others so please keep it public) agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" print(agent_code) # Check for existing checkpoint checkpoint_data = None if os.path.exists(CHECKPOINT_FILE): try: with open(CHECKPOINT_FILE, 'r') as f: checkpoint_data = json.load(f) print(f"Found checkpoint with {len(checkpoint_data.get('questions', []))} questions and {len(checkpoint_data.get('answers', []))} answers") except Exception as e: print(f"Error loading checkpoint: {e}") # If checkpoint is corrupt, remove it try: os.remove(CHECKPOINT_FILE) except: pass checkpoint_data = None # Initialize results tracking results_log = [] answers_payload = [] if checkpoint_data: # If we have a checkpoint, use it questions_data = checkpoint_data.get('questions', []) # Load any answers we already have existing_answers = checkpoint_data.get('answers', []) existing_answers_dict = {a.get('task_id'): a.get('submitted_answer') for a in existing_answers} print(f"Loaded {len(existing_answers)} existing answers from checkpoint") # Load existing results log if 'results_log' in checkpoint_data: results_log = checkpoint_data.get('results_log', []) # We'll use the checkpoint data print(f"Resuming from checkpoint with {len(questions_data)} questions") else: # 2. Fetch Questions from server 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.") # Save questions to checkpoint immediately save_checkpoint(questions_data, [], username, []) # No existing answers existing_answers_dict = {} 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 on questions we haven't answered yet print(f"Running agent on questions...") for idx, item in enumerate(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 # Check if the question has an associated file and prepend information file_name = item.get("file_name") if file_name and file_name != "": file_url = f"{api_url}/files/{task_id}" question_with_file_info = f"For this task there is file available, with name {file_name}, it's possible to download it from {file_url}\n\n{question_text}" question_text = question_with_file_info # Skip if we already have an answer for this question if task_id in existing_answers_dict: submitted_answer = existing_answers_dict[task_id] print(f"Using cached answer for task_id {task_id}") answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer}) # Check if we already have this in results_log if not any(r.get("Task ID") == task_id for r in results_log): results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer}) continue try: print(f"Processing question {idx+1}/{len(questions_data)}: {task_id}") 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}) # Save checkpoint after each answer save_checkpoint(questions_data, answers_payload, username, results_log) 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}"}) # Save checkpoint even if there was an error save_checkpoint(questions_data, answers_payload, username, results_log) 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: # Check if we're in production mode is_production = os.getenv('PRODUCTION_RUN', 'FALSE').upper() == 'TRUE' if is_production: print("Running in PRODUCTION mode - making actual submission") response = requests.post(submit_url, json=submission_data, timeout=60) response.raise_for_status() result_data = response.json() else: print("Running in SIMULATION mode - generating mock response") # Simulate a successful response result_data = { "username": username, "score": 85, "correct_count": len(answers_payload) - 2, # Simulate some incorrect answers "total_attempted": len(answers_payload), "message": "Simulation mode: This is a mock response" } final_status = ( f"Submission {'Successful' if is_production else 'Simulated'}!\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(f"Submission {'completed' if is_production else 'simulated'} successfully.") # Delete checkpoint file after successful submission if os.path.exists(CHECKPOINT_FILE): try: os.remove(CHECKPOINT_FILE) print(f"Checkpoint file removed after successful submission") except Exception as e: print(f"Warning: Could not remove checkpoint file: {e}") 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 def save_checkpoint(questions_data, answers_payload, username, results_log): """Save checkpoint data to a local file.""" try: checkpoint_data = { 'questions': questions_data, 'answers': answers_payload, 'username': username, 'timestamp': time.time(), 'results_log': results_log } with open(CHECKPOINT_FILE, 'w') as f: json.dump(checkpoint_data, f) print(f"Checkpoint saved with {len(questions_data)} questions and {len(answers_payload)} answers") except Exception as e: print(f"Error saving checkpoint: {e}") # --- 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_raw = os.getenv("SPACE_ID", "") # Ensure proper SPACE_ID format with username/repo if not space_id_raw: # Default if completely missing space_id_startup = "martinsu/Final_Assignment_Template" elif "/" in space_id_raw and not space_id_raw.startswith("/"): # Already has proper username/repo format space_id_startup = space_id_raw elif space_id_raw.startswith("/"): # Has a leading slash but missing username space_id_startup = f"martinsu{space_id_raw}" else: # Just repo name without username space_id_startup = f"martinsu/{space_id_raw}" 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.") # Check for existing checkpoint if os.path.exists(CHECKPOINT_FILE): try: with open(CHECKPOINT_FILE, 'r') as f: checkpoint_data = json.load(f) print(f"✅ Checkpoint found with {len(checkpoint_data.get('questions', []))} questions and {len(checkpoint_data.get('answers', []))} answers") print(f" Created at: {datetime.fromtimestamp(checkpoint_data.get('timestamp', 0)).strftime('%Y-%m-%d %H:%M:%S')}") except Exception as e: print(f"⚠️ Checkpoint file exists but could not be read: {e}") else: print("ℹ️ No checkpoint file found. Will start fresh.") print("-"*(60 + len(" App Starting ")) + "\n") print("Launching Gradio Interface for Basic Agent Evaluation...") demo.launch(debug=True, share=False)