Spaces:
Sleeping
Sleeping
| import os | |
| import re | |
| import base64 | |
| from enum import Enum | |
| from pydantic import BaseModel | |
| from io import BytesIO | |
| from tempfile import SpooledTemporaryFile | |
| from typing import Optional | |
| import logging | |
| import gradio as gr | |
| import requests | |
| import pandas as pd | |
| from langchain_core.messages import HumanMessage | |
| from concurrent.futures import ThreadPoolExecutor, as_completed | |
| from agent import gaia_agent | |
| logging.basicConfig(level=logging.INFO) | |
| logger = logging.getLogger(__name__) | |
| class ContentType(Enum): | |
| IMAGE = "image" | |
| PDF = "pdf" | |
| AUDIO = "audio" | |
| TEXT = "text" | |
| # (Keep Constants as is) | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| MAX_WORKERS = 8 | |
| class LLMFile(BaseModel): | |
| filename: str | |
| file: bytes | |
| mime: str | |
| content_type: ContentType | |
| # --- Basic Agent Definition --- | |
| # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ | |
| class BasicAgent: | |
| def __init__(self): | |
| print("BasicAgent initialized.") | |
| def __call__(self, question: str, content: Optional[LLMFile]) -> str: | |
| print(f"Agent received question (first 50 chars): {question[:50]}...") | |
| message_content = [{"type": "text", "text": question}] | |
| if content: | |
| if content.content_type == ContentType.AUDIO: | |
| media = { | |
| "type": "input_audio", | |
| "input_audio": {"data": base64.b64encode(content.file).encode("ascii"), "format": "wav"} | |
| } | |
| elif content.content_type == ContentType.IMAGE: | |
| media = { | |
| "type": "image", | |
| "image_url": {"url": f"data:image/jpeg;base64,{base64.b64encode(content.file).encode("ascii")}"} | |
| } | |
| elif content.content_type == ContentType.PDF: | |
| media = { | |
| "type": "file", | |
| "file": { | |
| "filename": content.filename, | |
| "file_data": f"data:application/pdf;base64,{base64.b64encode(content.file).encode("ascii")}", | |
| } | |
| } | |
| message_content.append(media) | |
| messages = gaia_agent.invoke({"messages": [ | |
| HumanMessage(content=message_content) | |
| ]}) | |
| message = messages['messages'][-1].content | |
| match = re.search(r'FINAL ANSWER:\s*(.*)', message) | |
| if match: | |
| answer = match.group(1) | |
| else: | |
| answer = "ERROR" | |
| print(f"Agent returning answer: {answer}") | |
| return answer | |
| def run_and_submit_all(profile: Optional[gr.OAuthProfile]): | |
| if not profile: | |
| logger.warning("User not logged in.") | |
| return "Please Login to Hugging Face with the button.", None | |
| username = profile.username.strip() | |
| logger.info(f"User logged in: {username}") | |
| session = requests.Session() | |
| space_id = os.getenv("SPACE_ID") | |
| agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" | |
| # --- Fetch questions --- | |
| questions_url = f"{DEFAULT_API_URL}/questions" | |
| try: | |
| response = session.get(questions_url, timeout=15) | |
| response.raise_for_status() | |
| questions_data = response.json() | |
| if not questions_data: | |
| raise ValueError("Fetched questions list is empty or invalid.") | |
| logger.info(f"Fetched {len(questions_data)} questions.") | |
| except Exception as e: | |
| logger.exception("Error fetching questions.") | |
| return f"Error fetching questions: {e}", None | |
| # --- Instantiate agent --- | |
| try: | |
| agent = BasicAgent() | |
| except Exception as e: | |
| logger.exception("Error initializing agent.") | |
| return f"Error initializing agent: {e}", None | |
| # --- Run agent in parallel --- | |
| def process_question(item): | |
| task_id = item.get("task_id") | |
| question = item.get("question") | |
| if not task_id or question is None: | |
| return None, {"Task ID": task_id, "Question": question, "Submitted Answer": "INVALID QUESTION FORMAT"} | |
| if item.get("filename", None): | |
| # --- Fetch file --- | |
| file_url = f"{DEFAULT_API_URL}/files/{task_id}" | |
| try: | |
| response = session.get(file_url, timeout=15) | |
| response.raise_for_status() | |
| content_disposition = response.headers.get("content-disposition", "") | |
| filename = task_id + ".bin" | |
| if "filename=" in content_disposition: | |
| filename = content_disposition.split("filename=")[-1].strip('"') | |
| mime = response.headers.get("content-type", "") | |
| if mime.startswith("audio/"): | |
| media = LLMFile(filename=filename, mime=mime, content_type=ContentType.AUDIO, file=response.content) | |
| elif mime.startswith("image/"): | |
| media = LLMFile(filename=filename, mime=mime, content_type=ContentType.IMAGE, file=response.content) | |
| elif mime.startswith("image/"): | |
| media = LLMFile(filename=filename, mime=mime, content_type=ContentType.IMAGE, file=response.content) | |
| elif mime.startswith("text/"): | |
| media = LLMFile(filename=filename, mime=mime, content_type=ContentType.TEXT, file=response.content) | |
| except Exception as e: | |
| logger.exception("Error fetching file for task id %s.", str(task_id)) | |
| return f"Error fetching file for task id ({task_id}): {e}", None | |
| try: | |
| answer = agent(question, media if item.get("filename", None) else None) | |
| return {"task_id": task_id, "submitted_answer": answer}, { | |
| "Task ID": task_id, "Question": question, "Submitted Answer": answer | |
| } | |
| except Exception as e: | |
| logger.warning(f"Agent error on task {task_id}: {e}") | |
| return None, { | |
| "Task ID": task_id, "Question": question, "Submitted Answer": f"AGENT ERROR: {e}" | |
| } | |
| answers_payload = [] | |
| results_log = [] | |
| with ThreadPoolExecutor(max_workers=MAX_WORKERS) as executor: | |
| futures = [executor.submit(process_question, item) for item in questions_data] | |
| for future in as_completed(futures): | |
| answer, log = future.result() | |
| if answer: | |
| answers_payload.append(answer) | |
| results_log.append(log) | |
| if not answers_payload: | |
| return "Agent did not produce any answers to submit.", pd.DataFrame(results_log) | |
| # --- Submit answers --- | |
| submit_url = f"{DEFAULT_API_URL}/submit" | |
| submission_data = { | |
| "username": username, | |
| "agent_code": agent_code, | |
| "answers": answers_payload, | |
| } | |
| logger.info(f"Submitting {len(answers_payload)} answers to: {submit_url}") | |
| try: | |
| response = session.post(submit_url, json=submission_data, timeout=60) | |
| response.raise_for_status() | |
| result = response.json() | |
| final_status = ( | |
| f"Submission Successful!\n" | |
| f"User: {result.get('username')}\n" | |
| f"Overall Score: {result.get('score', 'N/A')}% " | |
| f"({result.get('correct_count', '?')}/{result.get('total_attempted', '?')} correct)\n" | |
| f"Message: {result.get('message', 'No message received.')}" | |
| ) | |
| return final_status, pd.DataFrame(results_log) | |
| except requests.exceptions.HTTPError as e: | |
| try: | |
| error_detail = e.response.json().get("detail", e.response.text) | |
| except Exception: | |
| error_detail = e.response.text[:500] | |
| status_message = f"Submission Failed: {error_detail}" | |
| except requests.exceptions.Timeout: | |
| status_message = "Submission Failed: The request timed out." | |
| except requests.exceptions.RequestException as e: | |
| status_message = f"Submission Failed: Network error - {e}" | |
| except Exception as e: | |
| status_message = f"Unexpected error during submission: {e}" | |
| logger.error(status_message) | |
| return status_message, pd.DataFrame(results_log) | |
| # --- Build Gradio Interface using Blocks --- | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# Basic Agent Evaluation Runner") | |
| gr.Markdown( | |
| """ | |
| **Instructions:** | |
| 1. Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ... | |
| 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. | |
| --- | |
| **Disclaimers:** | |
| Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions). | |
| This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async. | |
| """ | |
| ) | |
| gr.LoginButton() | |
| run_button = gr.Button("Run Evaluation & Submit All Answers") | |
| status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False) | |
| # Removed max_rows=10 from DataFrame constructor | |
| 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) | |
| # 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 Gradio Interface for Basic Agent Evaluation...") | |
| demo.launch(debug=True, share=False) |