wlchee's picture
Upload app.py
a003b2e verified
raw
history blame
10.7 kB
import os
import gradio as gr
import requests
import pandas as pd
from transformers import Tool, HfAgent
from datetime import datetime
import random
import wikipediaapi
import wolframalpha
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
# --- Enhanced Agent Definition ---
class EnhancedAgent:
def __init__(self):
print("EnhancedAgent initialized with tools.")
# Initialize tools
self.tools = {
"calculator": self.calculator,
"time": self.get_current_time,
"wikipedia": self.wikipedia_search,
"random_choice": self.random_choice
}
# Initialize external APIs (would need proper API keys in production)
self.wiki_wiki = wikipediaapi.Wikipedia('en')
self.wolfram_client = wolframalpha.Client('YOUR_WOLFRAM_APP_ID') # Replace with actual ID
def calculator(self, expression: str) -> str:
"""Evaluate mathematical expressions"""
try:
return str(eval(expression))
except:
return "Error: Could not evaluate the expression"
def get_current_time(self) -> str:
"""Get current UTC time"""
return datetime.utcnow().strftime("%Y-%m-%d %H:%M:%S UTC")
def wikipedia_search(self, term: str) -> str:
"""Search Wikipedia for information"""
page = self.wiki_wiki.page(term)
if page.exists():
return page.summary[:500] # Return first 500 chars of summary
return f"No Wikipedia page found for '{term}'"
def random_choice(self, items: str) -> str:
"""Randomly select from a list of comma-separated items"""
try:
options = [x.strip() for x in items.split(",")]
return f"I choose: {random.choice(options)}"
except:
return "Error: Please provide comma-separated options"
def __call__(self, question: str) -> str:
print(f"Agent processing question: {question[:100]}...")
# Simple question classification and routing
question_lower = question.lower()
# Math questions
if any(word in question_lower for word in ["calculate", "what is", "how much is", "+", "-", "*", "/"]):
try:
# Extract math expression
expr = question.replace("?", "").replace("what is", "").replace("calculate", "").strip()
return self.tools["calculator"](expr)
except:
pass
# Time questions
if any(word in question_lower for word in ["time", "current time", "what time is it"]):
return self.tools["time"]()
# Wikipedia questions
if any(word in question_lower for word in ["who is", "what is a", "tell me about", "explain"]):
# Extract search term
term = question.replace("?", "").replace("who is", "").replace("what is a", "").replace("tell me about", "").strip()
return self.tools["wikipedia"](term)
# Random choice questions
if " or " in question_lower and not any(word in question_lower for word in ["who", "what", "when", "where", "why", "how"]):
return self.tools["random_choice"](question.replace("?", "").replace(" or ", ","))
# Fallback to HF Agent for complex questions
try:
agent = HfAgent(
"https://api-inference.huggingface.co/models/bigcode/starcoder",
max_new_tokens=150,
temperature=0.5
)
return agent.run(question)
except:
return "I couldn't find an answer to that question."
def run_and_submit_all(profile: gr.OAuthProfile | None):
"""
Fetches all questions, runs the EnhancedAgent 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 Agent
try:
agent = EnhancedAgent()
except Exception as e:
print(f"Error instantiating agent: {e}")
return f"Error initializing agent: {e}", None
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
except requests.exceptions.JSONDecodeError as e:
print(f"Error decoding JSON response from questions endpoint: {e}")
print(f"Response text: {response.text[:500]}")
return f"Error decoding server response for questions: {e}", None
except Exception as e:
print(f"An unexpected error occurred fetching questions: {e}")
return f"An unexpected error occurred fetching questions: {e}", None
# 3. Run your Agent
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:
print(f"Skipping item with missing task_id or question: {item}")
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:
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}"})
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.HTTPError as e:
error_detail = f"Server responded with status {e.response.status_code}."
try:
error_json = e.response.json()
error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
except requests.exceptions.JSONDecodeError:
error_detail += f" Response: {e.response.text[:500]}"
status_message = f"Submission Failed: {error_detail}"
print(status_message)
results_df = pd.DataFrame(results_log)
return status_message, results_df
except requests.exceptions.Timeout:
status_message = "Submission Failed: The request timed out."
print(status_message)
results_df = pd.DataFrame(results_log)
return status_message, results_df
except requests.exceptions.RequestException as e:
status_message = f"Submission Failed: Network error - {e}"
print(status_message)
results_df = pd.DataFrame(results_log)
return status_message, results_df
except Exception as e:
status_message = f"An unexpected error occurred during submission: {e}"
print(status_message)
results_df = pd.DataFrame(results_log)
return status_message, results_df
# --- Build Gradio Interface using Blocks ---
with gr.Blocks() as demo:
gr.Markdown("# Enhanced Agent Evaluation Runner")
gr.Markdown(
"""
**Instructions:**
1. Log in to your Hugging Face account using the button below.
2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run the enhanced agent, submit answers, and see the score.
This agent includes:
- Math calculation capabilities
- Time lookup
- Wikipedia integration
- Random choice selection
- Fallback to HF's StarCoder model for complex questions
"""
)
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" + "-"*30 + " App Starting " + "-"*30)
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 should be: https://{space_host_startup}.hf.space")
if space_id_startup:
print(f"✅ SPACE_ID found: {space_id_startup}")
print(f" Repo URL: https://huggingface.co/spaces/{space_id_startup}")
print("-"*(60 + len(" App Starting ")) + "\n")
print("Launching Gradio Interface for Enhanced Agent Evaluation...")
demo.launch(debug=True, share=False)