app.py

import os
import gradio as gr
import requests
import pandas as pd
from smolagents import CodeAgent, InferenceClientModel, DuckDuckGoSearchTool, VisitWebpageTool
from smolagents import OpenAIServerModel

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

import os
from smolagents import CodeAgent, InferenceClientModel, DuckDuckGoSearchTool, VisitWebpageTool

class GAIAAgent:
    def __init__(self):
        api_key = os.getenv("NEBIUS_API_KEY")
        if not api_key:
            raise ValueError("NEBIUS_API_KEY environment variable is not set. Please set this to your Hugging Face API key.")
        
        # self.model = InferenceClientModel(
        #     model_id="deepseek-ai/DeepSeek-R1",
        #     api_key=api_key
        # )

        # from smolagents import InferenceClientModel

        self.model = InferenceClientModel(
            model_id="Qwen/Qwen3-235B-A22B",
            provider="nebius")
        
        # self.model = OpenAIServerModel(
        #     model_id="Qwen/Qwen3-235B-A22B",
        #     api_base="https://api.studio.nebius.com/", # Leave this blank to query OpenAI servers.
        #     api_key=api_key, # Switch to the API key for the server you're targeting.
        # )
        
        self.tools = [DuckDuckGoSearchTool(), VisitWebpageTool()]
        self.agent = CodeAgent(tools=self.tools, model=self.model, max_steps=10)

    def __call__(self, question: str, file_path: str = None) -> str:
        try:
            if file_path:
                question += f"\nAttached file: {file_path}"
            response = self.agent.run(question)
            return response
        except Exception as e:
            print(f"Error running agent: {e}")
            return f"AGENT ERROR: {e}"


def run_and_submit_all(profile: gr.OAuthProfile | None):
    if not profile:
        return "Please Login to Hugging Face with the button.", None

    username = profile.username

    api_url = DEFAULT_API_URL
    questions_url = f"{api_url}/questions"
    submit_url = f"{api_url}/submit"

    agent = GAIAAgent()
    agent_code = f"https://huggingface.co/spaces/{os.getenv('ArunKr/Assignment_Agents')}/tree/main"

    response = requests.get(questions_url, timeout=15)
    questions_data = response.json()

    results_log = []
    answers_payload = []

    for item in questions_data:
        task_id = item.get("task_id")
        question_text = item.get("question")
        file_name = item.get("file_name", None)
        submitted_answer = agent(question_text, file_name)
        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})

    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}

    try:
        submission_response = requests.post(submit_url, json=submission_data, timeout=60)
        result_data = submission_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.')}"
        )
        results_df = pd.DataFrame(results_log)
        return final_status, results_df
    except Exception as e:
        status_message = f"Submission Failed: {e}"
        results_df = pd.DataFrame(results_log)
        return status_message, results_df


# Gradio Interface
with gr.Blocks() as demo:
    gr.Markdown("# GAIA Benchmark 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,
        inputs=None,
        outputs=[status_output, results_table]
    )

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