Spaces:
Sleeping
Sleeping
| import os | |
| import gradio as gr | |
| import requests | |
| import inspect | |
| import pandas as pd | |
| import random | |
| import time | |
| from smolagents import CodeAgent, LiteLLMModel, DuckDuckGoSearchTool, VisitWebpageTool | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| # --- Basic Agent Definition --- | |
| # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ | |
| class BasicAgent: | |
| def __init__(self): | |
| gemini_key = os.getenv("GEMINI_API_KEY") or os.getenv("GOOGLE_API_KEY") | |
| # 1. ๊ธฐ์กด์ ์ ์ ๊ตฌ๋์ด ํ์ธ๋ ๊ฒ์ฆ๋ ๋ชจ๋ธ ์๋ณ์๋ก ์์ ๋ณต๊ตฌ | |
| base_model = LiteLLMModel( | |
| model_id="gemini/gemini-2.5-flash", | |
| api_key=gemini_key | |
| ) | |
| # 2. ๋ผ์ด๋ธ๋ฌ๋ฆฌ ์ถฉ๋์ ๋ง๊ธฐ ์ํด ๋ชจ๋ธ ํธ์ถ ์์ฒด๋ฅผ ์ธํฐ์ ํธํ์ฌ 10์ด ํ์ด์ฑ(Pacing) ๊ฐ์ ์ฃผ์ | |
| original_call = base_model.__call__ | |
| def paced_call(*args, **kwargs): | |
| print("โณ [RPM Guard] Free tier burst protection sleep (10s)...") | |
| time.sleep(10.0) | |
| return original_call(*args, **kwargs) | |
| base_model.__call__ = paced_call | |
| self.model = base_model | |
| self.search_tool = DuckDuckGoSearchTool() | |
| self.visit_tool = VisitWebpageTool() | |
| # 45์ ๋ฒ ์ด์ค๋ผ์ธ ์ํคํ ์ฒ ๊ท๊ฒฉ ๊ณ ์ | |
| self.alfred = CodeAgent( | |
| tools=[self.search_tool, self.visit_tool], | |
| model=self.model, | |
| add_base_tools=True, | |
| planning_interval=3 | |
| ) | |
| def __call__(self, question: str) -> str: | |
| try: | |
| # ๋ฌธ์ ์ ๋ฌธ์ ์ฌ์ด์ ์์ ํ ์ธ์ ์ด๊ธฐํ๋ฅผ ์ํด 5์ด ์ถ๊ฐ ๋๊ธฐ | |
| time.sleep(5.0) | |
| result = self.alfred.run(question) | |
| if result is None: | |
| return "unknown" | |
| return str(result).strip() | |
| except Exception as e: | |
| print(f"Error during agent runtime execution: {e}") | |
| return "unknown" | |
| def run_and_submit_all( profile: gr.OAuthProfile | None): | |
| """ | |
| Fetches all questions, runs the BasicAgent 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 = 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) | |
| 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 | |
| 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 | |
| try: | |
| 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}) | |
| 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) | |
| 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) | |
| 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 | |
| # --- 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. | |
| """ | |
| ) | |
| 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__": | |
| demo.launch(debug=True, share=False) |