Spaces:
Sleeping
Sleeping
| import os | |
| import gradio as gr | |
| import requests | |
| import pandas as pd | |
| from smolagents import CodeAgent, DuckDuckGoSearchTool, OpenAIServerModel | |
| # Constants | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| # Basic Agent | |
| class BasicAgent: | |
| def __init__(self): | |
| OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") | |
| if not OPENAI_API_KEY: | |
| raise ValueError( | |
| "OPENAI_API_KEY not set. Add it in HF → Settings → Secrets." | |
| ) | |
| model = OpenAIServerModel( | |
| model_id="gpt-4o-mini", | |
| api_key=OPENAI_API_KEY | |
| ) | |
| search_tool = DuckDuckGoSearchTool() | |
| self.agent = CodeAgent( | |
| model=model, | |
| tools=[search_tool], | |
| max_steps=3 # prevents infinite loops | |
| ) | |
| def __call__(self, question: str) -> str: | |
| return self.agent.run(question) | |
| # Run + Submit | |
| def run_and_submit_all(profile: gr.OAuthProfile | None): | |
| space_id = os.getenv("SPACE_ID") | |
| if not profile: | |
| return "Please login first.", None | |
| username = profile.username | |
| questions_url = f"{DEFAULT_API_URL}/questions" | |
| submit_url = f"{DEFAULT_API_URL}/submit" | |
| try: | |
| agent = BasicAgent() | |
| except Exception as e: | |
| return f"Error initializing agent: {e}", None | |
| agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" | |
| try: | |
| response = requests.get(questions_url, timeout=15) | |
| response.raise_for_status() | |
| questions_data = response.json() | |
| except Exception as e: | |
| return f"Error fetching questions: {e}", None | |
| results_log = [] | |
| answers_payload = [] | |
| for item in questions_data: | |
| task_id = item.get("task_id") | |
| question_text = item.get("question") | |
| if not task_id or not question_text: | |
| continue | |
| try: | |
| answer = agent(question_text) | |
| except Exception as e: | |
| answer = f"AGENT ERROR: {e}" | |
| answers_payload.append({"task_id": task_id, "submitted_answer": answer}) | |
| results_log.append({ | |
| "Task ID": task_id, | |
| "Question": question_text, | |
| "Submitted Answer": answer | |
| }) | |
| if not answers_payload: | |
| return "No answers generated.", pd.DataFrame(results_log) | |
| submission_data = { | |
| "username": username.strip(), | |
| "agent_code": agent_code, | |
| "answers": answers_payload | |
| } | |
| try: | |
| response = requests.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"Score: {result.get('score', 'N/A')}% " | |
| f"({result.get('correct_count', '?')}/" | |
| f"{result.get('total_attempted', '?')})\n" | |
| f"Message: {result.get('message', '')}" | |
| ) | |
| return final_status, pd.DataFrame(results_log) | |
| except Exception as e: | |
| return f"Submission failed: {e}", pd.DataFrame(results_log) | |
| # Gradio UI | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# 🤖 Basic Agent Evaluation Runner") | |
| gr.Markdown(""" | |
| **Instructions** | |
| 1. Login with your Hugging Face account. | |
| 2. Click **Run Evaluation & Submit All Answers**. | |
| 3. Wait for the agent to finish. | |
| **Requirements** | |
| - Uses **OpenAI (gpt-4o-mini)** | |
| - Requires `OPENAI_API_KEY` in HF Space Secrets | |
| - Agent is **step-limited** (max 3 steps) | |
| """) | |
| gr.LoginButton() | |
| run_button = gr.Button("Run Evaluation & Submit All Answers") | |
| status_output = gr.Textbox(label="Run Status / Submission Result", lines=6, 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) |