Spaces:
Running
Running
| import os | |
| import gradio as gr | |
| import requests | |
| import inspect | |
| import pandas as pd | |
| from smoleagents_agent import OptimizedSmolagentsGAIAgent as SmolagentsGAIAgent | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| def run_and_submit_all(profile: gr.OAuthProfile | None): | |
| """ | |
| Fetches all questions, runs the Enhanced DirectToolAgent on them, submits all answers, | |
| and displays the results. | |
| """ | |
| # --- Determine HF Space Runtime URL and Repo URL --- | |
| 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" | |
| # 1. Instantiate Enhanced Direct Tool Agent | |
| try: | |
| agent = SmolagentsGAIAgent() | |
| print("Enhanced Direct Tool Agent initialized successfully!") | |
| except Exception as e: | |
| print(f"Error instantiating enhanced direct tool agent: {e}") | |
| return f"Error initializing enhanced direct tool agent: {e}", None | |
| agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" | |
| print(f"Agent code link: {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 Enhanced DirectToolAgent | |
| results_log = [] | |
| answers_payload = [] | |
| print(f"Running enhanced direct tool agent on {len(questions_data)} questions...") | |
| for i, 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 | |
| try: | |
| print(f"\n--- Processing Question {i+1}/{len(questions_data)} ---") | |
| print(f"Task ID: {task_id}") | |
| print(f"Question: {question_text[:100]}...") | |
| # Run the enhanced smolagents agent | |
| submitted_answer = agent.process_question(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 | |
| }) | |
| print(f"Answer: {submitted_answer[:100]}...") | |
| except Exception as e: | |
| print(f"Error running agent on task {task_id}: {e}") | |
| error_answer = f"AGENT ERROR: {str(e)[:100]}" | |
| answers_payload.append({"task_id": task_id, "submitted_answer": error_answer}) | |
| results_log.append({ | |
| "Task ID": task_id, | |
| "Question": question_text, | |
| "Submitted Answer": error_answer | |
| }) | |
| if not answers_payload: | |
| print("Enhanced DirectToolAgent did not produce any answers to submit.") | |
| return "Enhanced DirectToolAgent 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"Enhanced DirectToolAgent 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(title="Enhanced Smolagents GAIA Agent") as demo: | |
| gr.Markdown("# Enhanced Smolagents GAIA Agent Evaluation") | |
| gr.Markdown( | |
| """ | |
| ## Instructions: | |
| 1. **Login** to Hugging Face using the button below | |
| 2. **Click** 'Run Enhanced Evaluation & Submit All Answers' | |
| 3. **Wait** for your enhanced smolagents agent to process all questions | |
| 4. **View** your score and detailed results | |
| ## How the Enhanced Agent Works: | |
| - **Smart Capability Detection**: Automatically detects available tools | |
| - **Fallback Strategy**: Uses basic responses when advanced features unavailable | |
| - **Enhanced Responses**: Leverages Wikipedia, web search, and data tools when possible | |
| - **Zero-Error Operation**: Guaranteed to complete all questions regardless of available features | |
| **Note**: This enhanced version maximizes capabilities while maintaining complete reliability. | |
| """ | |
| ) | |
| gr.LoginButton() | |
| run_button = gr.Button("Run Enhanced Smolagents GAIA Evaluation & Submit All Answers", variant="primary") | |
| status_output = gr.Textbox( | |
| label="📊 Run Status / Submission Result", | |
| lines=10, | |
| 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__ == "__app__": | |
| print("\n" + "="*60 + " Enhanced Smolagents GAIA Agent Starting " + "="*60) | |
| # Check environment variables | |
| space_host_startup = os.getenv("SPACE_HOST") | |
| space_id_startup = os.getenv("SPACE_ID") | |
| if space_host_startup: | |
| print(f"[OK] SPACE_HOST found: {space_host_startup}") | |
| print(f" Runtime URL: https://{space_host_startup}.hf.space") | |
| else: | |
| print("[INFO] SPACE_HOST not found (running locally)") | |
| if space_id_startup: | |
| print(f"[OK] SPACE_ID found: {space_id_startup}") | |
| print(f" Repo URL: https://huggingface.co/spaces/{space_id_startup}") | |
| print(f" Code URL: https://huggingface.co/spaces/{space_id_startup}/tree/main") | |
| else: | |
| print("[INFO] SPACE_ID not found (running locally)") | |
| print("="*(120 + len(" Enhanced Smolagents GAIA Agent Starting ")) + "\n") | |
| print("Launching Enhanced Smolagents GAIA Agent Evaluation Interface...") | |
| demo.launch(debug=True, share=False) |