app.py

import os
import gradio as gr
import requests
import pandas as pd

from tools import AnswerTool
from smolagents import CodeAgent, OpenAIServerModel

# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

class BasicAgent:
    def __init__(self):
        # Initialize CodeAgent with an OpenAI model and custom AnswerTool
        model = OpenAIServerModel(model_id="gpt-3.5-turbo")
        answer_tool = AnswerTool()
        self.agent = CodeAgent(
            model=model,
            tools=[answer_tool],
            add_base_tools=False,
            max_steps=1,
            verbosity_level=0
        )

    def __call__(self, question: str) -> str:
        # Execute a single step to call the AnswerTool
        return self.agent.run(question)


def run_and_submit_all(username):
    # Username provided manually by the user
    if not username:
        return "Please enter your Hugging Face username.", None

    # Fetch questions
    try:
        resp = requests.get(f"{DEFAULT_API_URL}/questions", timeout=15)
        if resp.status_code == 429:
            return "Server rate limited the requests. Please wait a moment and try again.", None
        resp.raise_for_status()
        questions = resp.json()
    except Exception as e:
        return f"Error fetching questions: {e}", None

    # Run agent on all questions
    agent = BasicAgent()
    results = []
    payload = []
    for q in questions:
        tid = q.get('task_id')
        text = q.get('question')
        if not (tid and text):
            continue
        try:
            ans = agent(text)
        except Exception as e:
            ans = f"ERROR: {e}"
        results.append({'Task ID': tid, 'Question': text, 'Answer': ans})
        payload.append({'task_id': tid, 'submitted_answer': ans})

    if not payload:
        return "Agent returned no answers.", pd.DataFrame(results)

    # Submit answers
    submission = {
        'username': username,
        'agent_code': f"https://huggingface.co/spaces/{os.getenv('SPACE_ID')}/tree/main",
        'answers': payload
    }
    try:
        sub_resp = requests.post(f"{DEFAULT_API_URL}/submit", json=submission, timeout=60)
        sub_resp.raise_for_status()
        data = sub_resp.json()
        status = (
            f"Submission Successful!\n"
            f"User: {data.get('username')}\n"
            f"Score: {data.get('score')}% ({data.get('correct_count')}/{data.get('total_attempted')})\n"
            f"Message: {data.get('message')}"
        )
    except Exception as e:
        status = f"Submission Failed: {e}"

    return status, pd.DataFrame(results)


def test_random_question(username):
    if not username:
        return "Please enter your Hugging Face username.", ""
    try:
        q = requests.get(f"{DEFAULT_API_URL}/random-question", timeout=15).json()
        question = q.get('question', '')
        ans = BasicAgent()(question)
        return question, ans
    except Exception as e:
        return f"Error during test: {e}", ""

# --- Gradio UI ---
with gr.Blocks() as demo:
    gr.Markdown("# Basic Agent Evaluation Runner")
    gr.Markdown(
        """
        **Instructions:**
        1. Enter your Hugging Face username.
        2. Use **Test Random Question** to check a single question.
        3. Use **Run Evaluation & Submit All Answers** to evaluate on all questions.
        """
    )

    username_input = gr.Textbox(label="Hugging Face Username", placeholder="your-username")
    run_btn = gr.Button("Run Evaluation & Submit All Answers")
    test_btn = gr.Button("Test Random Question")

    status_out = gr.Textbox(label="Status / Result", lines=5, interactive=False)
    table_out = gr.DataFrame(label="Full Results Table", wrap=True)
    question_out = gr.Textbox(label="Random Question", lines=3, interactive=False)
    answer_out = gr.Textbox(label="Agent Answer", lines=3, interactive=False)

    run_btn.click(fn=run_and_submit_all, inputs=[username_input], outputs=[status_out, table_out])
    test_btn.click(fn=test_random_question, inputs=[username_input], outputs=[question_out, answer_out])

if __name__ == "__main__":
    demo.launch(debug=True, share=False)