File size: 4,546 Bytes
10e9b7d eccf8e4 3c4371f f86bd24 6576efa 91cad6f 6bd91c5 91cad6f 10e9b7d 6576efa 91cad6f 31243f4 6576efa 91cad6f 6576efa 91cad6f 6576efa 91cad6f 6576efa 91cad6f 6576efa 91cad6f f86bd24 91cad6f f86bd24 6576efa f86bd24 91cad6f f86bd24 4021bf3 6576efa 7e4a06b 6576efa 3c4371f 7e4a06b 7d65c66 3c4371f 7e4a06b 31243f4 e80aab9 31243f4 6576efa 31243f4 6576efa 36ed51a 6576efa 3c4371f eccf8e4 31243f4 7d65c66 31243f4 7d65c66 6576efa e80aab9 7d65c66 6576efa 31243f4 6576efa 31243f4 7d65c66 6576efa 31243f4 6576efa 31243f4 6576efa 31243f4 6576efa e80aab9 7d65c66 e80aab9 31243f4 e80aab9 6576efa e80aab9 6576efa 7d65c66 6576efa e80aab9 6576efa e80aab9 6576efa 7e4a06b 31243f4 6576efa e80aab9 6576efa e80aab9 6576efa 3c4371f |
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 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 |
import os
import gradio as gr
import requests
import pandas as pd
import openai
from smolagents.agents import ToolCallingAgent
from langchain_community.tools import PythonREPLTool as CodeInterpreterTool
from langchain_community.tools import DuckDuckGoSearchRun
# Constants
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
# --- Agent Definition with Tools ---
class SmartGAIAAgent:
def __init__(self):
self.api_key = os.getenv("OPENAI_API_KEY")
if not self.api_key:
raise ValueError("Missing OPENAI_API_KEY")
openai.api_key = self.api_key
# Define tools
self.search = DuckDuckGoSearchRun()
self.calculator = CodeInterpreterTool()
# Create tool-using agent
self.agent = ToolCallingAgent(
tools=[self.search, self.calculator],
model="gpt-4",
max_steps=8,
system_prompt=(
"You are a helpful assistant solving complex reasoning and factual questions. "
"Use tools only if needed. Return only the final answer. Do not add explanations or formatting."
)
)
def __call__(self, question: str) -> str:
try:
result = self.agent.run(question)
return result.strip()
except Exception as e:
print(f"Agent error: {e}")
return "error"
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:
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 = SmartGAIAAgent()
except Exception as e:
return f"Error initializing agent: {e}", None
agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
print(f"Code link: {agent_code}")
try:
response = requests.get(questions_url, 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 = []
for item in questions_data:
task_id = item.get("task_id")
question_text = item.get("question")
if not task_id or not question_text:
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"ERROR: {e}"
})
if not answers_payload:
return "No answers were submitted.", pd.DataFrame(results_log)
submission_data = {
"username": username,
"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"Score: {result_data.get('score')}% "
f"({result_data.get('correct_count')}/{result_data.get('total_attempted')})\n"
f"Message: {result_data.get('message')}"
)
return final_status, pd.DataFrame(results_log)
except Exception as e:
return f"Submission failed: {e}", pd.DataFrame(results_log)
# --- Gradio Interface ---
with gr.Blocks() as demo:
gr.Markdown("# GAIA Agent Evaluation")
gr.Markdown("""
**Instructions:**
1. Log in to Hugging Face
2. Click 'Run Evaluation' to generate and submit answers
3. Wait for the results
""")
gr.LoginButton()
run_button = gr.Button("Run Evaluation & Submit All Answers")
status_output = gr.Textbox(label="Submission Status", lines=5)
results_table = gr.DataFrame(label="Results")
run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
if __name__ == "__main__":
print("Launching Gradio Interface...")
demo.launch(debug=True, share=False) |