|
|
|
|
|
|
|
|
import os |
|
|
import asyncio |
|
|
import pandas as pd |
|
|
import requests |
|
|
import gradio as gr |
|
|
from agent import answer_question |
|
|
|
|
|
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" |
|
|
|
|
|
class GAIALlamaAgent: |
|
|
def __init__(self): |
|
|
print("Initialized LlamaIndex Agent") |
|
|
|
|
|
def __call__(self, question: str) -> str: |
|
|
print(f"Received question: {question[:60]}...") |
|
|
return asyncio.run(answer_question(question)) |
|
|
|
|
|
def run_and_submit_all(profile: gr.OAuthProfile | None): |
|
|
space_id = os.getenv("SPACE_ID") |
|
|
username = profile.username if profile else None |
|
|
if not username: |
|
|
return "Please login to Hugging Face.", None |
|
|
|
|
|
agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "" |
|
|
api_url = DEFAULT_API_URL |
|
|
|
|
|
try: |
|
|
response = requests.get(f"{api_url}/questions", timeout=15) |
|
|
response.raise_for_status() |
|
|
questions_data = response.json() |
|
|
except Exception as e: |
|
|
return f"Error fetching questions: {e}", None |
|
|
|
|
|
answers_payload = [] |
|
|
results_log = [] |
|
|
agent = GAIALlamaAgent() |
|
|
|
|
|
for item in questions_data: |
|
|
q = item.get("question") |
|
|
task_id = item.get("task_id") |
|
|
try: |
|
|
a = agent(q) |
|
|
except Exception as e: |
|
|
a = f"ERROR: {e}" |
|
|
answers_payload.append({"task_id": task_id, "submitted_answer": a}) |
|
|
results_log.append({"Task ID": task_id, "Question": q, "Submitted Answer": a}) |
|
|
|
|
|
submission_data = { |
|
|
"username": username, |
|
|
"agent_code": agent_code, |
|
|
"answers": answers_payload |
|
|
} |
|
|
|
|
|
try: |
|
|
response = requests.post(f"{api_url}/submit", json=submission_data, timeout=60) |
|
|
response.raise_for_status() |
|
|
result_data = response.json() |
|
|
status = ( |
|
|
f"✅ Submission Successful!\n" |
|
|
f"User: {result_data.get('username')}\n" |
|
|
f"Score: {result_data.get('score')}%\n" |
|
|
f"Correct: {result_data.get('correct_count')}/{result_data.get('total_attempted')}\n" |
|
|
f"Message: {result_data.get('message')}" |
|
|
) |
|
|
return 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("# LlamaIndex GAIA Agent – Evaluation Portal") |
|
|
gr.LoginButton() |
|
|
run_btn = gr.Button("Run Evaluation & Submit All Answers") |
|
|
status_box = gr.Textbox(label="Status", lines=5) |
|
|
result_table = gr.DataFrame(label="Agent Answers") |
|
|
run_btn.click(fn=run_and_submit_all, outputs=[status_box, result_table]) |
|
|
|
|
|
demo.launch(debug=True) |
