I’m encountering a NameError: name 'userdata' is not defined when trying to use Google Colab’s userdata module to securely store and retrieve my API key. I’m using it to fetch my API key for configuring the Generative AI client library in a Streamlit app. Here’s the relevant portion of my code:

# Used to securely store your API key
from google.colab import userdata

# Or use `os.getenv('GOOGLE_API_KEY')` to fetch an environment variable.
GOOGLE_API_KEY=userdata.get('GOOGLE_API_KEY')

genai.configure(api_key=GOOGLE_API_KEY)

This is my full code:

# Install required packages
!pip install streamlit ngrok
!pip install -q -U google-generativeai

# Import necessary libraries
from google.colab import userdata
import streamlit as st
import google.generativeai as genai

# Used to securely store your API key
GOOGLE_API_KEY = userdata.get('GOOGLE_API_KEY')

# Configure the Generative AI client library
genai.configure(api_key=GOOGLE_API_KEY)

# Write your Streamlit code to a file
code = """
import streamlit as st
import google.generativeai as genai

st.title("JARVIS")

# Select the model
model = genai.GenerativeModel('gemini-pro')

# Initialize chat history
if "messages" not in st.session_state:
    st.session_state.messages = [
        {
            "role": "assistant",
            "content": "Ask me Anything"
        }
    ]

# Display chat messages from history on app rerun
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

# Process and store Query and Response
def llm_function(query):
    response = model.generate_content(query)

    # Displaying the Assistant Message
    with st.chat_message("assistant"):
        st.markdown(response.text)

    # Storing the User Message
    st.session_state.messages.append(
        {
            "role": "user",
            "content": query
        }
    )

    # Storing the Assistant Message
    st.session_state.messages.append(
        {
            "role": "assistant",
            "content": response.text
        }
    )

# Accept user input
query = st.chat_input("What's up?")

# Calling the Function when Input is Provided
if query:
    # Displaying the User Message
    with st.chat_message("user"):
        st.markdown(query)

    llm_function(query)
"""

with open('app.py', 'w') as f:
    f.write(code)

# Import required libraries
from pyngrok import ngrok

# Set ngrok authtoken
authtoken = "2gwvvKEWTmfybIwG9UNTMjLbwaS_peD9yUo2YNNYXN71ReEd"
ngrok.set_auth_token(authtoken)

# Get list of existing ngrok tunnels
existing_tunnels = ngrok.get_tunnels()

# Stop existing tunnels if any are running
if existing_tunnels:
    print("Stopping existing ngrok tunnels...")
    for tunnel in existing_tunnels:
        ngrok.disconnect(tunnel.public_url)
    print("Existing ngrok tunnels stopped.")

# Start a new ngrok tunnel
try:
    # Connect a new ngrok tunnel
    public_url = ngrok.connect(8501).public_url
    print("New ngrok tunnel started. Public URL:", public_url)
except Exception as e:
    print("Error starting ngrok tunnel:", e)

I’ve verified that I’m running my code in a Google Colab environment, so userdata should be available. I have also put my key in Google Colab Secrets. However, I keep getting the mentioned NameError. How can I resolve this issue and properly use userdata to fetch my API key?

Any insights or suggestions would be greatly appreciated. Thank you!