Spaces:
Runtime error
Runtime error
| import os | |
| import gradio as gr | |
| import requests | |
| import inspect | |
| import pandas as pd | |
| # Import GAIA system from separate module | |
| from gaia_system import BasicAgent, MultiModelGAIASystem | |
| # (Keep Constants as is) | |
| # --- 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 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 = [] | |
| print(f"Running GAIA-optimized agent on {len(questions_data)} questions...") | |
| for item in 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: | |
| # Get raw answer from agent (should be clean already) | |
| raw_answer = agent(question_text) | |
| # Final cleanup for API submission - ensure no extra formatting | |
| submitted_answer = clean_for_api_submission(raw_answer) | |
| 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"Task {task_id}: {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. 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 | |
| def clean_for_api_submission(answer: str) -> str: | |
| """ | |
| Final cleanup of agent answers for GAIA API submission | |
| Ensures exact match compliance | |
| """ | |
| if not answer: | |
| return "I cannot determine the answer" | |
| # Remove any remaining formatting artifacts | |
| answer = answer.strip() | |
| # Remove markdown formatting | |
| answer = answer.replace('**', '').replace('*', '').replace('`', '') | |
| # Remove any "Answer:" prefixes that might have slipped through | |
| answer = answer.replace('Answer:', '').replace('ANSWER:', '').strip() | |
| # Remove any trailing periods for factual answers (but keep for sentences) | |
| if len(answer.split()) == 1 or answer.replace('.', '').replace(',', '').isdigit(): | |
| answer = answer.rstrip('.') | |
| return answer | |
| # --- Enhanced Gradio Interface --- | |
| with gr.Blocks(title="🚀 GAIA Multi-Agent System") as demo: | |
| gr.Markdown("# 🚀 GAIA Multi-Agent System - BENCHMARK OPTIMIZED") | |
| gr.Markdown( | |
| """ | |
| **GAIA Benchmark-Optimized AI Agent for Exact-Match Evaluation** | |
| This system is specifically optimized for the GAIA benchmark with: | |
| 🎯 **Exact-Match Compliance**: Answers formatted for direct evaluation | |
| 🧮 **Mathematical Precision**: Clean numerical results | |
| 🌍 **Factual Accuracy**: Direct answers without explanations | |
| 🔬 **Scientific Knowledge**: Precise values and facts | |
| 🧠 **Multi-Model Reasoning**: 10+ AI models with intelligent fallback | |
| --- | |
| **GAIA Benchmark Requirements:** | |
| ✅ **Direct answers only** - No "The answer is" prefixes | |
| ✅ **No reasoning shown** - Thinking process completely removed | |
| ✅ **Exact format matching** - Numbers, names, or comma-separated lists | |
| ✅ **No explanations** - Just the final result | |
| **Test Examples:** | |
| - Math: "What is 15 + 27?" → "42" | |
| - Geography: "What is the capital of France?" → "Paris" | |
| - Science: "How many planets are in our solar system?" → "8" | |
| --- | |
| **System Status:** | |
| - ✅ GAIA-Optimized Agent: Active | |
| - 🤖 AI Models: DeepSeek-R1, GPT-4o, Llama-3.3-70B + 7 more | |
| - 🛡️ Fallback System: Enhanced with exact answers | |
| - 📏 Response Cleaning: Aggressive for benchmark compliance | |
| """ | |
| ) | |
| # Test interface for local development | |
| with gr.Row(): | |
| with gr.Column(): | |
| test_input = gr.Textbox( | |
| label="🧪 Test Question (GAIA Style)", | |
| placeholder="Try: What is 15 + 27? or What is the capital of France?", | |
| lines=2 | |
| ) | |
| test_button = gr.Button("🔍 Test Agent", variant="secondary") | |
| with gr.Column(): | |
| test_output = gr.Textbox( | |
| label="🤖 Agent Response (Direct Answer Only)", | |
| lines=3, | |
| interactive=False | |
| ) | |
| gr.LoginButton() | |
| run_button = gr.Button("🚀 Run GAIA Evaluation & Submit All Answers", variant="primary") | |
| status_output = gr.Textbox(label="📊 Run Status / Submission Result", lines=5, interactive=False) | |
| results_table = gr.DataFrame(label="📋 Questions and Agent Answers", wrap=True) | |
| # Test function for local development | |
| def test_agent(question): | |
| try: | |
| agent = BasicAgent() | |
| response = agent(question) | |
| # Clean for display (same as API submission) | |
| cleaned_response = clean_for_api_submission(response) | |
| return f"Direct Answer: {cleaned_response}" | |
| except Exception as e: | |
| return f"Error: {str(e)}" | |
| test_button.click( | |
| fn=test_agent, | |
| inputs=[test_input], | |
| outputs=[test_output] | |
| ) | |
| 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 Enhanced GAIA Multi-Agent System...") | |
| demo.launch(debug=True, share=False) |