File size: 3,395 Bytes
10e9b7d eccf8e4 3c4371f 66a3b62 6576efa f86bd24 6b0e46a e80aab9 baae5a0 6b0e46a baae5a0 31243f4 6b0e46a 31243f4 6b0e46a baae5a0 6576efa baae5a0 6b0e46a baae5a0 6b0e46a c8bf6ed baae5a0 759cedb baae5a0 66a3b62 baae5a0 6b0e46a baae5a0 6b0e46a baae5a0 e80aab9 6b0e46a 7e4a06b baae5a0 6b0e46a baae5a0 6b0e46a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 |
import os
import gradio as gr
import requests
import pandas as pd
from agent_v2 import GaiaAgent
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
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:
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"
try:
agent = GaiaAgent()
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
try:
submitted_answer = agent(question_text, task_id=task_id)
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:
results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
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.')}"
)
results_df = pd.DataFrame(results_log)
return final_status, results_df
except Exception as e:
results_df = pd.DataFrame(results_log)
return f"Submission Failed: {e}", results_df
with gr.Blocks() as demo:
gr.Markdown("# GAIA Agent Submission")
gr.Markdown("""
1. Zaloguj się do Hugging Face.
2. Kliknij przycisk, by uruchomić agenta na wszystkich pytaniach.
3. Wynik pojawi się poniżej.
""")
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])
demo.launch(debug=True)
|