app.py

# app.py
import os
import gradio as gr
import requests
import pandas as pd
from agent import agent, run_with_fallback  # Import run_with_fallback directly
import asyncio
import nest_asyncio
nest_asyncio.apply()

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

# Async helper to run the agent - modified to use run_with_fallback
async def run_agent(agent, question_text):
    """Run the agent in a way that's compatible with asyncio"""
    # Create a new event loop for this function call to avoid nesting issues
    loop = asyncio.get_event_loop()
    # Run the synchronous function in the executor
    return await loop.run_in_executor(None, run_with_fallback, question_text)

# Gradio Agent Interface
def run_and_submit_all(profile: gr.OAuthProfile | None):
    """
    Fetches all questions, runs the LlamaIndexAgent on them, submits all answers,
    and displays the results.
    """
    # --- Determine HF Space Runtime URL and Repo URL ---
    space_id = os.getenv("SPACE_ID")  # Get the SPACE_ID for sending link to the code

    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"

    # 1. Instantiate LlamaIndexAgent
    print("Using imported agent instance.")

    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    print(agent_code)

    # 2. Fetch Questions
    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:
            print("Fetched questions list is empty.")
            return "Fetched questions list is empty or invalid format.", None
        print(f"Fetched {len(questions_data)} questions.")
    except requests.exceptions.RequestException as e:
        print(f"Error fetching questions: {e}")
        return f"Error fetching questions: {e}", None

    # 3. Run your LlamaIndex Agent
    results_log = []
    answers_payload = []
    print(f"Running agent on {len(questions_data)} questions...")
    
    # Create a new event loop for this function
    loop = asyncio.new_event_loop()
    asyncio.set_event_loop(loop)
    
    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:
            print(f"Skipping item with missing task_id or question: {item}")
            continue
        try:
            # Run the async function in the loop
            submitted_answer = loop.run_until_complete(run_agent(agent, question_text))
            
            # Ensure serializable response
            if not isinstance(submitted_answer, (str, dict, list, int, float, bool, type(None))):
                submitted_answer = str(submitted_answer)
                
            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}"})
    
    # Close the loop when done
    loop.close()

    if not answers_payload:
        print("Agent did not produce any answers to submit.")
        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)

    # 4. Prepare Submission
    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
    print(status_update)

    # 5. Submit
    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
    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.')}"
        )
        print("Submission successful.")
        results_df = pd.DataFrame(results_log)
        return final_status, results_df
    except requests.exceptions.RequestException as e:
        print(f"Submission failed: {e}")
        return f"Submission failed: {e}", pd.DataFrame(results_log)


# Gradio Interface
with gr.Blocks() as demo:
    gr.Markdown("# LlamaIndex 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__":
    print("Launching Gradio Interface for LlamaIndex Agent Evaluation...")
    demo.launch(debug=True, share=False)