app.py

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

from smolagents import (
    CodeAgent,
    DuckDuckGoSearchTool,
    WikipediaSearchTool,
    LiteLLMModel,
)

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

GAIA_SYSTEM_PROMPT = """You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template:
FINAL ANSWER: [YOUR FINAL ANSWER].
YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings.
If you are asked for a number, don't use commas to write your number, and don't use units such as $ or percent sign unless specified otherwise.
If you are asked for a string, don't use articles, don't use abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise.
If you are asked for a comma separated list, apply the above rules depending on whether the element to be put in the list is a number or a string."""


class BasicAgent:
    def __init__(self):
        api_key = os.getenv("GEMINI_API_KEY")
        print(f"[BasicAgent] GEMINI_API_KEY loaded: {bool(api_key)}, length: {len(api_key) if api_key else 0}")
        if not api_key:
            raise RuntimeError("GEMINI_API_KEY is not set. Add it in Settings → Variables and secrets, then Factory rebuild.")
        self.agent = CodeAgent(
            tools=[DuckDuckGoSearchTool(), WikipediaSearchTool()],
            model=LiteLLMModel(
                model_id="gemini/gemini-2.0-flash",
                api_key=api_key,
            ),
            max_steps=12,
            additional_authorized_imports=["pandas", "numpy", "datetime", "re", "json", "math"],
        )

    def __call__(self, question: str) -> str:
        try:
            raw = str(self.agent.run(f"{GAIA_SYSTEM_PROMPT}\n\nQuestion: {question}"))
            print(f"[Agent raw, first 300]: {raw[:300]}")
            if "FINAL ANSWER:" in raw:
                return raw.split("FINAL ANSWER:")[-1].strip().rstrip(".").strip()
            return raw.strip()
        except Exception as e:
            err = f"ERR: {type(e).__name__}: {str(e)[:200]}"
            print(f"[Agent exception]: {err}")
            return err


def run_and_submit_all(profile: gr.OAuthProfile | None):
    space_id = os.getenv("SPACE_ID")

    if profile:
        username = f"{profile.username}"
        print(f"User logged in: {username}")
    else:
        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:
        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()
        if not questions_data:
            return "Fetched questions list is empty or invalid format.", None
    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 question_text is None:
            continue
        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})

    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}

    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.')}"
        )
        return final_status, pd.DataFrame(results_log)
    except Exception as e:
        return f"Submission Failed: {e}", pd.DataFrame(results_log)


with gr.Blocks() as demo:
    gr.Markdown("# Basic Agent Evaluation Runner")
    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)