Spaces:
Sleeping
Sleeping
| import os | |
| import gradio as gr | |
| import requests | |
| import inspect | |
| import pandas as pd | |
| import aiohttp | |
| import asyncio | |
| import json | |
| from agent import MagAgent | |
| from token_bucket import Limiter, MemoryStorage | |
| import aiofiles | |
| from typing import Optional | |
| import time | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| # Rate limiting configuration | |
| MAX_MODEL_CALLS_PER_MINUTE = 14 # Conservative buffer below 15 RPM | |
| TOKEN_BUCKET_CAPACITY = MAX_MODEL_CALLS_PER_MINUTE | |
| TOKEN_BUCKET_REFILL_RATE = MAX_MODEL_CALLS_PER_MINUTE / 60.0 # Tokens per second | |
| # Initialize global token bucket with MemoryStorage | |
| storage = MemoryStorage() | |
| token_bucket = Limiter(rate=TOKEN_BUCKET_REFILL_RATE, capacity=TOKEN_BUCKET_CAPACITY, storage=storage) | |
| async def check_n_load_attach(session: aiohttp.ClientSession, task_id: str, question: str, api_url: str = "https://agents-course-unit4-scoring.hf.space") -> Optional[str]: | |
| file_url = f"{api_url}/files/{task_id}" | |
| try: | |
| async with session.get(file_url | |
| , timeout=15) as response: | |
| if response.status == 200: | |
| content_type = str(response.headers.get("Content-Type", "")).lower() | |
| content = await response.read() # Read the file content | |
| # Determine extension based on content_type, content, or question | |
| extension = await determine_extension(content_type, content, question) | |
| if extension: | |
| filename = f"{task_id}{extension}" | |
| local_file_path = os.path.join("downloads", filename) | |
| os.makedirs("downloads", exist_ok=True) | |
| async with aiofiles.open(local_file_path, "wb") as file: | |
| await file.write(content) | |
| print(f"File downloaded successfully: {local_file_path}") | |
| return local_file_path | |
| else: | |
| print(f"Unsupported content type: {content_type} for task {task_id}") | |
| return None | |
| else: | |
| print(f"Failed to download file for task {task_id}: HTTP {response.status}") | |
| return None | |
| except aiohttp.ClientError as e: | |
| print(f"Error downloading attachment for task {task_id}: {str(e)}") | |
| return None | |
| async def determine_extension(content_type: str, content: bytes, question | |
| : str) -> Optional[str]: | |
| # Check if the question mentions Excel | |
| if "excel" in question.lower(): | |
| # Check for XLS signature | |
| if content.startswith(b'\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1'): | |
| return ".xls" | |
| # Check for XLSX signature (ZIP archive) | |
| elif content.startswith(b'\x50\x4B\x03\x04'): | |
| return ".xlsx" | |
| else: | |
| return ".xlsx" # Default to XLSX if unsure | |
| # Standard MIME type checks | |
| if "image/png" in content_type: | |
| return ".png" | |
| elif "jpeg" in content_type or "jpg" in content_type: | |
| return ".jpg" | |
| elif "spreadsheetml.sheet" in content_type: | |
| return ".xlsx" | |
| elif "vnd.ms-excel" in content_type: | |
| return ".xls" | |
| elif "audio/mpeg" in content_type: | |
| return ".mp3" | |
| elif "application/pdf" in content_type: | |
| return ".pdf" | |
| elif "text/x-python" in content_type: | |
| return ".py" | |
| else: | |
| return None | |
| async def fetch_questions(session: aiohttp.ClientSession, questions_url: str) -> list: | |
| """Fetch questions asynchronously.""" | |
| try: | |
| async with session.get(questions_url, timeout=15) as response: | |
| response.raise_for_status() | |
| questions_data = await response.json() | |
| if not questions_data: | |
| print("Fetched questions list is empty.") | |
| return [] | |
| print(f"Fetched {len(questions_data)} questions.") | |
| return questions_data | |
| except aiohttp.ClientError as e: | |
| print(f"Error fetching questions: {e}") | |
| return None | |
| except Exception as e: | |
| print(f"An unexpected error occurred fetching questions: {e}") | |
| return None | |
| async def submit_answers(session: aiohttp.ClientSession, submit_url: str, submission_data: dict) -> dict: | |
| """Submit answers asynchronously.""" | |
| try: | |
| async with session.post(submit_url, json=submission_data, timeout=60) as response: | |
| response.raise_for_status() | |
| return await response.json() | |
| except aiohttp.ClientResponseError as e: | |
| print(f"Submission Failed: Server responded with status {e.status}. Detail: {e.message}") | |
| return None | |
| except aiohttp.ClientError as e: | |
| print(f"Submission Failed: Network error - {e}") | |
| return None | |
| except Exception as e: | |
| print(f"An unexpected error occurred during submission: {e}") | |
| return None | |
| async def process_question(agent, question_text: str, task_id: str, file_path: Optional[str], results_log: list): | |
| """Process a single question with global rate limiting and retry logic.""" | |
| submitted_answer = None | |
| max_retries = 4 | |
| retry_delay = 20 # Initial retry delay in seconds | |
| atimeout = 300 | |
| for attempt in range(max_retries +1): | |
| try: | |
| while not token_bucket.consume(1): | |
| print(f"Rate limit reached for task {task_id}. Waiting to retry...") | |
| await asyncio.sleep(retry_delay) | |
| print(f"Processing task {task_id} (attempt {attempt + 1})...") | |
| submitted_answer = await asyncio.wait_for( | |
| agent(question_text, file_path), | |
| timeout=atimeout # Increased timeout for audio processing | |
| ) | |
| results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer}) | |
| print(f"Completed task {task_id} with answer: {submitted_answer[:50]}...") | |
| ################### Addl sleep | |
| # await asyncio.sleep(retry_delay) | |
| return {"task_id": task_id, "submitted_answer": submitted_answer} | |
| except aiohttp.ClientResponseError as e: | |
| if e.status == 429: | |
| print(f"Rate limit hit for task {task_id}. Retrying after {retry_delay}s...") | |
| retry_delay *= 2 # Exponential backoff | |
| await asyncio.sleep(retry_delay) | |
| continue | |
| else: | |
| submitted_answer = f"AGENT ERROR: {e}" | |
| results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer}) | |
| print(f"Failed task {task_id}: {submitted_answer}") | |
| return None | |
| except asyncio.TimeoutError: | |
| submitted_answer = f"AGENT ERROR: Timeout after {atimeout} seconds" | |
| results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer}) | |
| print(f"Failed task {task_id}: {submitted_answer}") | |
| return None | |
| except Exception as e: | |
| submitted_answer = f"AGENT ERROR: {e}" | |
| results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer}) | |
| print(f"Failed task {task_id}: {submitted_answer}") | |
| return None | |
| async def run_and_submit_all(profile: gr.OAuthProfile | None): | |
| """ | |
| Fetches all questions asynchronously, runs the MagAgent on them, submits all answers, | |
| and displays the results. | |
| """ | |
| 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 = MagAgent(rate_limiter=token_bucket) | |
| 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) | |
| async with aiohttp.ClientSession() as session: | |
| questions_data = await fetch_questions(session, questions_url) | |
| if questions_data is None: | |
| return "Error fetching questions.", None | |
| if not questions_data: | |
| return "Fetched questions list is empty or invalid format.", 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") | |
| if not task_id or question_text is None: | |
| print(f"Skipping item with missing task_id or question: {item}") | |
| continue | |
| #select question we want to focus | |
| if "sosa11" in question_text.lower() or "bird" in question_text.lower() or "yankee" in question_text.lower(): | |
| file_path = await check_n_load_attach(session, task_id, question_text.lower()) | |
| result = await process_question(agent, question_text, task_id, file_path, results_log) | |
| if result: | |
| answers_payload.append(result) | |
| else: | |
| print("Skipping unrelated question.") | |
| 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) | |
| result_data = await submit_answers(session, submit_url, submission_data) | |
| if result_data is None: | |
| status_message = "Submission Failed." | |
| print(status_message) | |
| results_df = pd.DataFrame(results_log) | |
| return status_message, results_df | |
| 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 | |
| # --- Build Gradio Interface using Blocks --- | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# Magus Agent Evaluation Runner") | |
| gr.Markdown( | |
| """ | |
| **Instructions:** | |
| 1. Log in to your Hugging Face account using the button below. | |
| 2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, and submit answers. | |
| --- | |
| **Notes:** | |
| The agent uses asynchronous operations for efficiency. Answers are processed and submitted asynchronously. | |
| """ | |
| ) | |
| 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 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_HOST environment variable not found (running locally?). Repo URL cannot be determined.") | |
| print("-"*(60 + len(" App Starting ")) + "\n") | |
| print("Launching Gradio Interface for Mag Agent Evaluation...") | |
| demo.launch(debug=True, share=False) |