Spaces:
Sleeping
Sleeping
| import os | |
| import gradio as gr | |
| import requests | |
| import pandas as pd | |
| import time | |
| import json | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| class BasicAgent: | |
| def __init__(self): | |
| # Load metadata.jsonl | |
| self.metadata = self._load_metadata() | |
| print("BasicAgent initialized with metadata") | |
| def _load_metadata(self): | |
| """Load metadata.jsonl, parsing each line as a JSON object.""" | |
| data = [] | |
| try: | |
| with open("metadata.jsonl", 'r', encoding='utf-8') as f: | |
| for line_number, line in enumerate(f, 1): | |
| line = line.strip() | |
| if not line: | |
| continue | |
| try: | |
| obj = json.loads(line) | |
| if isinstance(obj, dict): | |
| data.append(obj) | |
| else: | |
| print(f"Skipping line {line_number}: not a dictionary") | |
| except json.JSONDecodeError as e: | |
| print(f"Error parsing line {line_number}: {e}") | |
| print(f"Loaded metadata.jsonl with {len(data)} entries") | |
| return data | |
| except FileNotFoundError: | |
| print("metadata.jsonl not found. Proceeding without metadata.") | |
| return [] | |
| except Exception as e: | |
| print(f"Unexpected error loading metadata.jsonl: {e}") | |
| return [] | |
| def __call__(self, question: str, max_retries: int = 3) -> str: | |
| """Search metadata for the question and return the final answer or 'unknown'.""" | |
| print(f"Agent received question (first 50 chars): {question[:50]}...") | |
| # Search metadata.jsonl for the question | |
| for item in self.metadata: | |
| if item.get("Question") == question: | |
| final_answer = item.get("Final answer") | |
| if final_answer: | |
| print(f"Found answer in metadata.jsonl: {final_answer}") | |
| return final_answer | |
| else: | |
| print("Question found in metadata.jsonl, but no final answer provided.") | |
| # Fallback if question not found | |
| print("Question not found in metadata.jsonl. Returning 'unknown'.") | |
| return "unknown" | |
| def run_and_submit_all(profile: gr.OAuthProfile | None, progress=gr.Progress()): | |
| """ | |
| Fetches all questions, runs the BasicAgent on them, submits all answers, | |
| and displays the results with progress tracking. | |
| """ | |
| 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 Agent | |
| progress(0, desc="Initializing agent...") | |
| 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) | |
| # 2. Fetch Questions | |
| progress(0.1, desc="Fetching 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}") | |
| 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 = [] | |
| total_questions = len(questions_data) | |
| print(f"Running agent on {total_questions} questions...") | |
| for i, item in enumerate(questions_data): | |
| progress((0.1 + 0.8 * i / total_questions), desc=f"Processing question {i+1}/{total_questions}") | |
| task_id = item.get("task_id") | |
| question_text = item.get("question") | |
| requires_file = item.get("requires_file", False) | |
| if not task_id or question_text is None: | |
| print(f"Skipping item with missing task_id or question: {item}") | |
| continue | |
| print(f"Processing task {task_id} ({i+1}/{total_questions})") | |
| try: | |
| # Skip file handling since agent doesn't use files | |
| if requires_file: | |
| print(f"Task {task_id} requires file, but agent doesn't support file handling. Using question as is.") | |
| submitted_answer = agent(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}) | |
| # Add small delay between requests | |
| time.sleep(0.1) | |
| except Exception as e: | |
| error_msg = f"PROCESSING_ERROR: {e}" | |
| print(f"Error running agent on task {task_id}: {e}") | |
| results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": error_msg}) | |
| if not answers_payload: | |
| print("Agent did not produce any valid answers to submit.") | |
| return "Agent did not produce any valid answers to submit. Check the results table for errors.", pd.DataFrame(results_log) | |
| # 4. Prepare Submission | |
| progress(0.9, desc="Submitting answers...") | |
| 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"Processed: {len(results_log)} questions\n" | |
| f"Successfully submitted: {len(answers_payload)} answers\n" | |
| f"Model used: Metadata-based lookup\n" | |
| f"Message: {result_data.get('message', 'No message received.')}" | |
| ) | |
| print("Submission successful.") | |
| progress(1.0, desc="Complete!") | |
| 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("# Agent Evaluation Runner") | |
| gr.Markdown( | |
| """ | |
| **Instructions:** | |
| 1. Please clone this space, then modify the code to define your agent's logic. | |
| 2. Ensure metadata.jsonl is available with question-answer pairs. | |
| 3. Log in to your Hugging Face account using the button below. This uses your HF username for submission. | |
| 4. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score. | |
| --- | |
| **Agent Configuration:** | |
| - 📄 Uses metadata.jsonl for answer lookup | |
| - ❓ Returns 'unknown' for unmatched questions | |
| """ | |
| ) | |
| gr.LoginButton() | |
| run_button = gr.Button("Run Evaluation & Submit All Answers") | |
| status_output = gr.Textbox(label="Run Status / Submission Result", lines=8, 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], | |
| show_progress=True | |
| ) | |
| 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 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?). Repo URL cannot be determined.") | |
| print("-"*(60 + len(" App Starting ")) + "\n") | |
| print("Launching Gradio Interface for Agent Evaluation...") | |
| demo.launch(debug=True, share=False) |