Spaces:
Sleeping
Sleeping
import os | |
import gradio as gr | |
import requests | |
import pandas as pd | |
# ---- Constants ---- | |
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
# ---- Smolagents imports ---- | |
from smolagents import WikipediaSearchTool, DuckDuckGoSearchTool | |
# ---- Agent Definition ---- | |
class SmolAgent: | |
def __init__(self): | |
self.wiki = WikipediaSearchTool() | |
self.duck = DuckDuckGoSearchTool() | |
def __call__(self, question: str) -> str: | |
# Try Wikipedia first, fall back to DuckDuckGo if nothing useful. | |
wiki_result = "" | |
duck_result = "" | |
try: | |
wiki_result = self.wiki.run(question) | |
except Exception as e: | |
wiki_result = f"(Wiki error: {e})" | |
# If Wikipedia yields nothing or too short, use DuckDuckGo as fallback | |
if wiki_result and len(str(wiki_result)) > 40: | |
return str(wiki_result) | |
try: | |
duck_result = self.duck.run(question) | |
except Exception as e: | |
duck_result = f"(DuckDuckGo error: {e})" | |
if duck_result: | |
return str(duck_result) | |
# If both fail, return error info | |
return f"Wikipedia: {wiki_result}\nDuckDuckGo: {duck_result}\n(No answer found.)" | |
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 = SmolAgent() | |
except Exception as e: | |
return f"Error initializing agent: {e}", None | |
agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" | |
print(agent_code) | |
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: | |
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 = [] | |
print(f"Running agent on {len(questions_data)} questions...") | |
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) | |
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} | |
status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..." | |
print(status_update) | |
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 | |
# --- Build Gradio Interface using Blocks --- | |
with gr.Blocks() as demo: | |
gr.Markdown("# SmolAgent Evaluation Runner") | |
gr.Markdown( | |
""" | |
**Instructions:** | |
1. Clone and modify this space to improve your agent logic as you see fit. | |
2. Log in to your Hugging Face account with the button below. | |
3. Click 'Run Evaluation & Submit All Answers' to begin. | |
--- | |
**Disclaimer:** Submission may take a while depending on the number of questions and agent speed. | |
""" | |
) | |
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("\n--- App Starting ---\n") | |
space_host_startup = os.getenv("SPACE_HOST") | |
space_id_startup = os.getenv("SPACE_ID") | |
if space_host_startup: | |
print(f"✅ SPACE_HOST found: {space_host_startup}") | |
print(f" Runtime URL: https://{space_host_startup}.hf.space") | |
else: | |
print("ℹ️ SPACE_HOST not found (running locally?)") | |
if space_id_startup: | |
print(f"✅ SPACE_ID found: {space_id_startup}") | |
print(f" Repo URL: https://huggingface.co/spaces/{space_id_startup}/tree/main") | |
else: | |
print("ℹ️ SPACE_ID not found") | |
print("--- App Starting ---\n") | |
demo.launch(debug=True, share=False) | |