import os import gradio as gr import requests import pandas as pd from transformers import pipeline from transformers import GPT2LMHeadModel, GPT2Tokenizer import torch # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # --- Basic Agent Definition --- class GeneralAgent: def __init__(self): print("Initializing BERT-based QA agent...") # Cargar el modelo BERT preentrenado en SQuAD para tareas de Pregunta y Respuesta self.qa_pipeline = pipeline("question-answering", model="bert-large-uncased-whole-word-masking-finetuned-squad") def __call__(self, question: str, context: str = None) -> str: """ Procesa la pregunta y devuelve una respuesta basada en el contexto proporcionado. Si no se proporciona contexto, devuelve un mensaje de error. """ if context is None: return "FINAL ANSWER: No context provided." # Crear un prompt dentro del contexto que estructure la tarea más explícitamente prompt = f""" You are a general AI assistant. I will ask you a question based on the provided context. Please provide the answer in a clear and concise manner. Question: {question} Context: {context} Answer: """ try: # Usar el pipeline para obtener la respuesta de la pregunta con el contexto result = self.qa_pipeline(question=question, context=prompt) answer = result["answer"] except Exception as e: print(f"Error durante QA: {e}") answer = "Error processing question." # Devuelve la respuesta final con el formato requerido return f"FINAL ANSWER: {answer}" def run_and_submit_all(profile: gr.OAuthProfile | None): 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" try: agent = BasicAgent() except Exception as e: print(f"Error instantiating agent: {e}") return f"Error initializing agent: {e}", None agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" print(agent_code) 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: {e}") return f"Error decoding server response: {e}", None except Exception as e: print(f"Unexpected error: {e}") return f"Unexpected error: {e}", None 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") context = item.get("context", question_text) # Usa 'context' si viene, si no, la propia pregunta 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, context) 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) 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) print(f"Submitting 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"HTTP error {e.response.status_code}: {e.response.text[:300]}" return f"Submission Failed: {error_detail}", pd.DataFrame(results_log) except requests.exceptions.Timeout: return "Submission Failed: Timeout.", pd.DataFrame(results_log) except requests.exceptions.RequestException as e: return f"Submission Failed: Network error - {e}", pd.DataFrame(results_log) except Exception as e: return f"Submission Failed: Unexpected error - {e}", pd.DataFrame(results_log) # --- Build Gradio Interface using Blocks --- with gr.Blocks() as demo: gr.Markdown("# Basic Agent Evaluation Runner") gr.Markdown( """ **Instructions:** 1. Clone this space and modify your agent. 2. Log in to Hugging Face with the button below. 3. Click 'Run Evaluation & Submit All Answers' to evaluate. --- **Note**: Submitting can take a while. This space is intentionally basic—improve it! """ ) 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) 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: https://{space_host_startup}.hf.space") else: print("ℹ️ SPACE_HOST 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}") else: print("ℹ️ SPACE_ID not found. Repo URL cannot be determined.") print("-" * 70 + "\n") print("Launching Gradio Interface for Basic Agent Evaluation...") demo.launch(debug=True, share=False)