Code Editor for app.py

import streamlit as st
import tensorflow as tf
from PIL import Image
import numpy as np

# Set page title
st.title("Cloud Architecture Component Detector")

# Add description
st.write("""
Upload an architecture diagram and this app will attempt to detect cloud components in it.
The model is trained to recognize common cloud architecture components like:
- Servers/VMs
- Databases
- Storage
- Load Balancers
- Containers
""")

# File uploader
uploaded_file = st.file_uploader("Choose an architecture diagram...", type=['png', 'jpg', 'jpeg'])

if uploaded_file is not None:
    # Display the uploaded image
    image = Image.open(uploaded_file)
    st.image(image, caption='Uploaded Architecture Diagram', use_column_width=True)
    
    # Add processing button
    if st.button('Detect Components'):
        # Show processing message
        with st.spinner('Processing image...'):
            try:
                # Prepare the image
                img = image.resize((224, 224))  # Resize to model input size
                img_array = np.array(img)
                img_array = img_array / 255.0  # Normalize
                img_array = np.expand_dims(img_array, axis=0)
                
                # For demo purposes, we'll simulate detections
                # In a real app, you would:
                # 1. Load a trained model
                # 2. Run inference on the image
                # 3. Process the results
                
                # Simulated detections
                detections = {
                    "VM/Server": 0.92,
                    "Database": 0.85,
                    "Storage": 0.78,
                    "Load Balancer": 0.65,
                    "Container": 0.89
                }
                
                # Display results
                st.subheader("Detected Components:")
                for component, confidence in detections.items():
                    st.write(f"{component}: {confidence*100:.1f}% confidence")
                
                # Add some visual flair for successful processing
                st.success("Processing complete!")
                st.balloons()
                
            except Exception as e:
                st.error(f"Error processing image: {str(e)}")

# Add usage instructions
st.markdown("""
### Instructions:
1. Upload an architecture diagram in PNG, JPG, or JPEG format
2. Click 'Detect Components' to analyze the image
3. View the detected components and their confidence scores

### Note:
This is a demo application. In a production environment, you would need:
- A properly trained deep learning model
- More robust image processing
- Additional component types
- Proper error handling
""")