Spaces:
Runtime error
Runtime error
| import os | |
| import gradio as gr | |
| import requests | |
| import inspect | |
| import pandas as pd | |
| from agent import build_graph | |
| from langchain_core.messages import HumanMessage | |
| import time | |
| # (Keep Constants as is) | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| # --- Improved Agent Definition --- | |
| class BasicAgent: | |
| def __init__(self): | |
| print("BasicAgent initialized.") | |
| try: | |
| self.graph = build_graph() | |
| print("Graph built successfully.") | |
| except Exception as e: | |
| print(f"Error building graph: {e}") | |
| raise e | |
| def __call__(self, question: str) -> str: | |
| print(f"Agent received question (first 100 chars): {question[:100]}...") | |
| try: | |
| # Clean the question | |
| question = question.strip() | |
| # Wrap the question in a HumanMessage | |
| messages = [HumanMessage(content=question)] | |
| # Invoke the graph with retry mechanism | |
| max_retries = 3 | |
| for attempt in range(max_retries): | |
| try: | |
| result = self.graph.invoke({"messages": messages}) | |
| if 'messages' in result and result['messages']: | |
| answer = result['messages'][-1].content | |
| # Clean up the answer | |
| if isinstance(answer, str): | |
| # Remove the "FINAL ANSWER: " prefix if it exists | |
| if "FINAL ANSWER:" in answer: | |
| answer = answer.split("FINAL ANSWER:")[-1].strip() | |
| # Additional cleanup | |
| answer = answer.replace("Assistant: ", "").strip() | |
| print(f"Agent answer (first 100 chars): {answer[:100]}...") | |
| return answer | |
| else: | |
| return str(answer) | |
| else: | |
| return "No response generated" | |
| except Exception as e: | |
| print(f"Attempt {attempt + 1} failed: {e}") | |
| if attempt == max_retries - 1: | |
| return f"Error processing question: {str(e)}" | |
| time.sleep(1) # Brief pause before retry | |
| except Exception as e: | |
| print(f"Error in agent call: {e}") | |
| return f"Agent error: {str(e)}" | |
| 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: | |
| print("Initializing agent...") | |
| agent = BasicAgent() | |
| print("Agent initialized successfully.") | |
| 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 | |
| agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" | |
| print(f"Agent code URL: {agent_code}") | |
| # 2. Fetch Questions | |
| print(f"Fetching questions from: {questions_url}") | |
| try: | |
| response = requests.get(questions_url, timeout=30) | |
| 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 with better error handling | |
| results_log = [] | |
| answers_payload = [] | |
| print(f"Running 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 | |
| print(f"Processing question {i+1}/{len(questions_data)}: {task_id}") | |
| try: | |
| # Add timeout and better error handling for individual questions | |
| start_time = time.time() | |
| submitted_answer = agent(question_text) | |
| end_time = time.time() | |
| print(f"Question {i+1} completed in {end_time - start_time:.2f} seconds") | |
| # Validate the answer | |
| if not submitted_answer or submitted_answer.strip() == "": | |
| submitted_answer = "No answer generated" | |
| answers_payload.append({ | |
| "task_id": task_id, | |
| "submitted_answer": str(submitted_answer).strip() | |
| }) | |
| results_log.append({ | |
| "Task ID": task_id, | |
| "Question": question_text[:200] + "..." if len(question_text) > 200 else question_text, | |
| "Submitted Answer": str(submitted_answer).strip() | |
| }) | |
| except Exception as e: | |
| print(f"Error running agent on task {task_id}: {e}") | |
| error_answer = f"AGENT ERROR: {str(e)}" | |
| answers_payload.append({ | |
| "task_id": task_id, | |
| "submitted_answer": error_answer | |
| }) | |
| results_log.append({ | |
| "Task ID": task_id, | |
| "Question": question_text[:200] + "..." if len(question_text) > 200 else question_text, | |
| "Submitted Answer": error_answer | |
| }) | |
| 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 with better error handling | |
| print(f"Submitting {len(answers_payload)} answers to: {submit_url}") | |
| try: | |
| response = requests.post(submit_url, json=submission_data, timeout=120) | |
| response.raise_for_status() | |
| result_data = response.json() | |
| final_status = ( | |
| f"Submission Successful!\n" | |
| f"User: {result_data.get('username', 'Unknown')}\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.") | |
| print(f"Score: {result_data.get('score', 'N/A')}%") | |
| 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() as demo: | |
| gr.Markdown("# Enhanced Agent Evaluation Runner") | |
| gr.Markdown( | |
| """ | |
| **Instructions:** | |
| 1. Please clone this space, then modify the code to define your agent's logic, tools, and necessary packages. | |
| 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. | |
| **Improvements in this version:** | |
| - Enhanced mathematical tools (factorial, gcd, lcm, compound interest, etc.) | |
| - Better search tools with error handling | |
| - Improved HuggingFace model integration | |
| - Better answer processing and cleanup | |
| - Enhanced error handling and retry mechanisms | |
| --- | |
| **Note:** The evaluation process may take some time as the agent processes all questions systematically. | |
| """ | |
| ) | |
| gr.LoginButton() | |
| run_button = gr.Button("Run 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) | |
| run_button.click( | |
| fn=run_and_submit_all, | |
| outputs=[status_output, results_table] | |
| ) | |
| if __name__ == "__main__": | |
| print("\n" + "-"*30 + " Enhanced App Starting " + "-"*30) | |
| # Check for environment variables | |
| space_host_startup = os.getenv("SPACE_HOST") | |
| space_id_startup = os.getenv("SPACE_ID") | |
| hf_token = os.getenv("HUGGINGFACE_INFERENCE_TOKEN") | |
| 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(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?).") | |
| if hf_token: | |
| print("✅ HUGGINGFACE_INFERENCE_TOKEN found") | |
| else: | |
| print("⚠️ HUGGINGFACE_INFERENCE_TOKEN not found - this may cause issues") | |
| print("-"*(60 + len(" Enhanced App Starting ")) + "\n") | |
| print("Launching Enhanced Gradio Interface for Agent Evaluation...") | |
| demo.launch(debug=True, share=False) |