import os import gradio as gr import requests import pandas as pd import datasets from mini_agents import MasterAgentWrapper from utils import get_full_file_path from smolagents.memory import ActionStep, PlanningStep, TaskStep, SystemPromptStep, FinalAnswerStep from typing import Optional import numpy as np # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # --- Basic Agent Definition --- # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ columns = [ 'task_id', 'step_class', # Common attributes (from MemoryStep base class) 'model_input_messages', 'tool_calls', 'start_time', 'end_time', 'step_number', 'error', 'duration', 'model_output_message', 'model_output', 'observations', 'observations_images', 'action_output', # PlanningStep attributes 'plan', # TaskStep attributes 'task', 'task_images', # SystemPromptStep attributes 'system_prompt', # FinalAnswerStep attributes 'final_answer' ] class BasicAgent: def __init__(self): self.agent = MasterAgentWrapper() # This is now the MasterAgentWrapper instance print("Master Agent initialized.") def __call__(self, question: str, task_id: str, df_agent_steps: pd.DataFrame) -> tuple[str, pd.DataFrame]: print(f"Agent received question (first 50 chars): {question[:50]}...") try: # Use the wrapper's run method which handles browser tools safely fixed_answer = self.agent.run(question) # Log steps all_steps = self.agent.master_agent.memory.steps new_rows = [] # List to store new rows def serialize_value(value): """Convert complex objects to serializable format""" if hasattr(value, 'dict'): return value.dict() elif hasattr(value, '__dict__'): return str(value.__dict__) elif isinstance(value, (list, tuple)): return [serialize_value(item) for item in value] elif isinstance(value, dict): return {k: serialize_value(v) for k, v in value.items()} return value for step in all_steps: if isinstance(step, ActionStep): step_class = "ActionStep" elif isinstance(step, PlanningStep): step_class = "PlanningStep" elif isinstance(step, TaskStep): step_class = "TaskStep" elif isinstance(step, SystemPromptStep): step_class = "SystemPromptStep" elif isinstance(step, FinalAnswerStep): step_class = "FinalAnswerStep" else: step_class = "UnknownStep" step_dict = step.dict() # Create a new row with default None values new_row = {col: "None" for col in df_agent_steps.columns} # Update with actual values new_row['task_id'] = task_id new_row['step_class'] = step_class # Serialize complex objects before adding to DataFrame for key, value in step_dict.items(): if key in df_agent_steps.columns: try: new_row[key] = serialize_value(value) except Exception as e: print(f"Warning: Could not serialize {key}, using string representation: {e}") new_row[key] = str(value) new_rows.append(new_row) # Append all new rows at once final_row = { 'task_id': task_id, 'step_class': 'FinalAnswerStep', 'model_input_messages': [question], 'model_output_message': fixed_answer, 'model_output': fixed_answer, } new_rows.append(final_row) if new_rows: df_agent_steps = pd.concat([df_agent_steps, pd.DataFrame(new_rows)], ignore_index=True) print(f"Agent returning fixed answer: {fixed_answer}") return fixed_answer, df_agent_steps except Exception as e: print(f"Error in agent execution: {e}") raise def check_required_env_vars() -> tuple[bool, Optional[str]]: """Check if required environment variables are set""" missing_vars = [] # Check HF_TOKEN if not os.getenv("HUGGINGFACE_API_KEY"): missing_vars.append("HUGGINGFACE_API_KEY") # Check SPACE_ID (only warn, not required) if not os.getenv("SPACE_ID"): print("⚠️ SPACE_ID not set - this is normal when running locally") if missing_vars: return False, f"Missing required environment variables: {', '.join(missing_vars)}" return True, None def save_dataset_to_hub(df: pd.DataFrame, dataset_name: str) -> tuple[bool, str]: """Save DataFrame to Hugging Face dataset with proper error handling""" # Check environment variables env_ok, env_error = check_required_env_vars() if not env_ok: return False, f"Cannot save dataset: {env_error}" try: if len(df) == 0: return False, "Cannot save empty dataset" print(f"Saving {len(df)} steps to {dataset_name}...") # Create a copy of the DataFrame to avoid modifying the original df_to_save = df.copy() def is_none_or_nan(x): """Safely check if a value is None or NaN""" if x is None: return True if isinstance(x, (float, np.floating)) and np.isnan(x): return True if x == "None" or x == "nan" or x == "NaN": return True return False def ensure_consistent_type(x, column_name): """Ensure consistent type within a column""" try: if is_none_or_nan(x): return None # Special handling for model_input_messages and similar columns if column_name in ['model_input_messages', 'model_output_message', 'tool_calls']: if isinstance(x, (list, tuple, np.ndarray)): # Convert each item in the array/list to string return str([str(item) if not is_none_or_nan(item) else None for item in x]) if isinstance(x, dict): return str(x) if hasattr(x, 'dict'): return str(x.dict()) if hasattr(x, '__dict__'): return str(x.__dict__) return str(x) # For other columns, convert to string if isinstance(x, (list, tuple, np.ndarray)): return str(x.tolist() if hasattr(x, 'tolist') else list(x)) if isinstance(x, dict): return str(x) if hasattr(x, 'dict'): return str(x.dict()) if hasattr(x, '__dict__'): return str(x.__dict__) return str(x) except Exception as e: print(f"Warning: Error converting value in column {column_name}: {str(e)}") return str(x) if not is_none_or_nan(x) else None # Convert all columns to consistent types for col in df_to_save.columns: print(f"Converting column: {col}") try: # Handle numpy arrays and pandas series if isinstance(df_to_save[col], (np.ndarray, pd.Series)): # Convert None/NaN to None, everything else to string df_to_save[col] = df_to_save[col].apply(lambda x: None if is_none_or_nan(x) else str(x)) else: df_to_save[col] = df_to_save[col].apply(lambda x: ensure_consistent_type(x, col)) # Verify column type consistency sample_values = df_to_save[col].dropna().head() if not sample_values.empty: print(f"Sample values for {col}: {sample_values.iloc[0]}") except Exception as e: print(f"Warning: Error processing column {col}: {str(e)}") # If there's an error, try to convert the entire column to string df_to_save[col] = df_to_save[col].apply(lambda x: None if is_none_or_nan(x) else str(x)) # Convert to dataset dataset = datasets.Dataset.from_pandas(df_to_save) # Add metadata with explicit string types for all columns dataset.info.description = "Agent steps data from evaluation run" # Save to hub with token dataset.push_to_hub( dataset_name, private=True, token=os.getenv("HUGGINGFACE_WRITE_API_KEY") ) return True, f"Successfully saved {len(df_to_save)} steps to {dataset_name}" except Exception as e: error_msg = f"Error saving dataset: {str(e)}" print(error_msg) # Print more detailed error information if hasattr(e, '__cause__') and e.__cause__: print(f"Caused by: {str(e.__cause__)}") return False, error_msg def run_and_submit_all( profile: gr.OAuthProfile | None, mock_submission: bool = False): """ 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) # 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 = [] df_agent_steps = pd.DataFrame(columns=columns) 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") file_path = get_full_file_path(task_id) if not task_id or question_text is None: print(f"Skipping item with missing task_id or question: {item}") continue if "youtube" in question_text.lower() and "bird" in question_text.lower(): continue try: if file_path: question_text = question_text + f"\n\nHere is also the path to the file for the task (file name matches with task ID and is not in plain English): {file_path}" submitted_answer, df_agent_steps = agent(question_text, task_id, df_agent_steps) 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. Save steps data to huggingface dataset print("\nSaving agent steps to Hugging Face dataset...") success, message = save_dataset_to_hub(df_agent_steps, "huytofu92/agent_steps_huggingface_course_unit4") if success: print(message) else: print(f"⚠️ {message}") print("Continuing with submission despite dataset save failure...") # 6. Submit print(f"Submitting {len(answers_payload)} answers to: {submit_url}") if mock_submission: answer_df = pd.DataFrame(results_log, columns=["Task ID", "Question", "Submitted Answer"]) answer_df.to_csv("answers.csv", index=False) return "Answers saved to answers.csv", answer_df else: 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, columns=["Task ID", "Question", "Submitted Answer"]) print(results_df[["Task ID", "Submitted Answer"]].head(20)) 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, columns=["Task ID", "Question", "Submitted Answer"]) print(results_df[["Task ID", "Submitted Answer"]].head(20)) 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, columns=["Task ID", "Question", "Submitted Answer"]) print(results_df[["Task ID", "Submitted Answer"]].head(20)) 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, columns=["Task ID", "Question", "Submitted Answer"]) print(results_df[["Task ID", "Submitted Answer"]].head(20)) 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, columns=["Task ID", "Question", "Submitted Answer"]) print(results_df[["Task ID", "Submitted Answer"]].head(20)) 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__": 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 Basic Agent Evaluation...") demo.launch(debug=True, share=False)