| import inspect |
| import os |
| import gradio as gr |
| import pandas as pd |
| import requests |
| from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel |
|
|
| |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" |
|
|
| |
| class BasicAgent: |
| def __init__(self): |
| print("Initializing smolagents CodeAgent...") |
| |
| model = HfApiModel( |
| model_id="Qwen/Qwen2.5-Coder-32B-Instruct", |
| token=os.getenv("HF_TOKEN") |
| ) |
| |
| search_tool = DuckDuckGoSearchTool() |
| |
| self.agent = CodeAgent( |
| tools=[search_tool], |
| model=model, |
| max_steps=5, |
| verbosity_level=1 |
| ) |
| print("BasicAgent initialized successfully.") |
|
|
| def __call__(self, question: str) -> str: |
| print(f"Agent received question: {question[:80]}...") |
| prompt = ( |
| f"Answer the following question concisely and factually. " |
| f"Provide only the final answer without extra conversational text:\n{question}" |
| ) |
| try: |
| answer = self.agent.run(prompt) |
| return str(answer).strip() |
| except Exception as e: |
| print(f"Error during agent execution: {e}") |
| return f"Error: {e}" |
|
|
|
|
| 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(f"Agent Code Repository: {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: |
| return "Fetched questions list is empty or invalid format.", None |
| print(f"Fetched {len(questions_data)} questions.") |
| except Exception as e: |
| return f"Error 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: |
| 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: |
| 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 |
| } |
| print(f"Submitting {len(answers_payload)} answers for user '{username}'...") |
|
|
| |
| 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')}%\n" |
| f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n" |
| f"Message: {result_data.get('message', 'No message received.')}" |
| ) |
| return final_status, pd.DataFrame(results_log) |
| except Exception as e: |
| status_message = f"Submission Failed: {e}" |
| return status_message, pd.DataFrame(results_log) |
|
|
|
|
| |
| with gr.Blocks() as demo: |
| gr.Markdown("# Basic 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 run your agent and record 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) |
