app_lite.py

"""
🚀 NAVADA 2.0 - Advanced AI Computer Vision Application (Lite Version)
Streamlit Version for Hugging Face Spaces Deployment

Enhanced Edition by Lee Akpareva | AI Consultant & Computer Vision Specialist
"""

import streamlit as st
import time
from datetime import datetime
import plotly.graph_objects as go
import plotly.express as px
from PIL import Image
import numpy as np
import os

# Configure Streamlit page (MUST be first!)
st.set_page_config(
    page_title="🚀 NAVADA 2.0 - AI Computer Vision",
    page_icon="🚀",
    layout="wide",
    initial_sidebar_state="expanded"
)

# Backend imports - Lite version (no face recognition)
try:
    from backend.yolo import detect_objects
    from backend.openai_client import explain_detection
except ImportError as e:
    st.error(f"⚠️ Import error: {e}")
    st.error("📦 Please install dependencies: pip install -r requirements.txt")
    st.stop()

# Custom CSS for enhanced styling
st.markdown("""
<style>
    .main-header {
        background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
        padding: 2rem;
        border-radius: 10px;
        color: white;
        text-align: center;
        margin-bottom: 2rem;
    }

    .feature-card {
        background: linear-gradient(135deg, #f093fb 0%, #f5576c 100%);
        padding: 1.5rem;
        border-radius: 10px;
        color: white;
        margin: 1rem 0;
    }

    .stats-card {
        background: linear-gradient(135deg, #4facfe 0%, #00f2fe 100%);
        padding: 1rem;
        border-radius: 8px;
        color: white;
        text-align: center;
        margin: 0.5rem;
    }
</style>
""", unsafe_allow_html=True)

def create_detection_chart(detected_objects):
    """Create an interactive chart showing detection statistics"""

    # Count object types
    object_counts = {}
    for obj in detected_objects:
        object_counts[obj] = object_counts.get(obj, 0) + 1

    if not object_counts:
        # Create empty chart
        fig = go.Figure()
        fig.add_annotation(
            text="No objects detected",
            xref="paper", yref="paper",
            x=0.5, y=0.5, showarrow=False,
            font=dict(size=20, color="gray")
        )
        fig.update_layout(
            height=300,
            showlegend=False,
            paper_bgcolor='rgba(0,0,0,0)',
            plot_bgcolor='rgba(0,0,0,0)'
        )
        return fig

    # Create bar chart
    objects = list(object_counts.keys())
    counts = list(object_counts.values())

    fig = go.Figure(data=[
        go.Bar(
            x=objects,
            y=counts,
            marker_color='rgba(50, 171, 96, 0.6)',
            marker_line_color='rgba(50, 171, 96, 1.0)',
            marker_line_width=2,
            text=counts,
            textposition='auto'
        )
    ])

    fig.update_layout(
        title="Detected Objects",
        xaxis_title="Object Type",
        yaxis_title="Count",
        height=400,
        showlegend=False,
        paper_bgcolor='rgba(0,0,0,0)',
        plot_bgcolor='rgba(0,0,0,0)'
    )

    return fig

def main():
    # Main header
    st.markdown("""
    <div class="main-header">
        <h1>🚀 NAVADA 2.0 - Advanced AI Computer Vision</h1>
        <p><strong>Lite Version - Object Detection & AI Analysis</strong></p>
        <p>Built with YOLOv8 • OpenAI • Streamlit</p>
    </div>
    """, unsafe_allow_html=True)

    # Sidebar
    with st.sidebar:
        st.markdown("### 🎯 Detection Settings")

        # Detection confidence threshold
        confidence = st.slider(
            "Detection Confidence",
            min_value=0.1,
            max_value=1.0,
            value=0.5,
            step=0.05,
            help="Minimum confidence for object detection"
        )

        st.markdown("### 📊 Features")
        st.markdown("""
        - 🎯 **Object Detection**: YOLOv8 powered
        - 🤖 **AI Explanations**: OpenAI integration
        - 📈 **Interactive Charts**: Real-time analytics
        - 🎨 **Visual Results**: Annotated images
        """)

        st.markdown("### ℹ️ About")
        st.markdown("""
        This is the **Lite Version** optimized for Hugging Face Spaces.

        **Created by:** Lee Akpareva
        **AI Consultant & Computer Vision Specialist**
        """)

    # Main content
    col1, col2 = st.columns([2, 1])

    with col1:
        st.markdown("### 📸 Upload Image for Analysis")

        uploaded_file = st.file_uploader(
            "Choose an image...",
            type=['png', 'jpg', 'jpeg'],
            help="Upload an image to detect objects and get AI analysis"
        )

        if uploaded_file is not None:
            # Display uploaded image
            image = Image.open(uploaded_file)
            st.image(image, caption="Uploaded Image", use_column_width=True)

            # Analysis button
            if st.button("🚀 Analyze Image", type="primary"):
                with st.spinner("🔍 Detecting objects..."):
                    # Perform object detection
                    results = detect_objects(image, confidence_threshold=confidence)

                    if results and len(results['detections']) > 0:
                        # Extract detected objects
                        detected_objects = [det['class'] for det in results['detections']]

                        # Display results
                        st.success(f"✅ Detected {len(detected_objects)} objects!")

                        # Show annotated image
                        st.markdown("### 🎯 Detection Results")
                        if 'annotated_image' in results:
                            st.image(results['annotated_image'], caption="Detected Objects", use_column_width=True)

                        # Show detection details
                        st.markdown("### 📋 Detected Objects")
                        for i, detection in enumerate(results['detections']):
                            col_a, col_b, col_c = st.columns(3)
                            with col_a:
                                st.metric("Object", detection['class'])
                            with col_b:
                                st.metric("Confidence", f"{detection['confidence']:.2%}")
                            with col_c:
                                st.metric("Count", f"#{i+1}")

                        # AI Explanation
                        if os.getenv("OPENAI_API_KEY"):
                            st.markdown("### 🤖 AI Analysis")
                            with st.spinner("🧠 Generating AI explanation..."):
                                try:
                                    explanation = explain_detection(detected_objects)
                                    st.markdown(f"**AI Insight:** {explanation}")
                                except Exception as e:
                                    st.warning(f"AI analysis unavailable: {str(e)}")
                        else:
                            st.warning("🔑 Add OPENAI_API_KEY in settings for AI explanations")

                    else:
                        st.warning("❌ No objects detected. Try adjusting the confidence threshold.")

    with col2:
        st.markdown("### 📊 Detection Statistics")

        # Sample chart (will be updated with real data)
        sample_data = {
            'Object': ['Person', 'Car', 'Dog', 'Cat'],
            'Count': [3, 2, 1, 1]
        }

        fig = px.bar(
            sample_data,
            x='Object',
            y='Count',
            title="Sample Detection Results",
            color='Count',
            color_continuous_scale='Viridis'
        )
        fig.update_layout(height=300)
        st.plotly_chart(fig, use_container_width=True)

        # Feature highlights
        st.markdown("### ✨ Key Features")

        features = [
            ("🎯", "Object Detection", "Advanced YOLOv8 model"),
            ("🤖", "AI Analysis", "OpenAI explanations"),
            ("📊", "Real-time Charts", "Interactive visualizations"),
            ("🚀", "Fast Processing", "Optimized for speed")
        ]

        for icon, title, desc in features:
            st.markdown(f"""
            <div style="display: flex; align-items: center; margin: 1rem 0; padding: 0.5rem; background: #f0f2f6; border-radius: 5px;">
                <div style="font-size: 1.5rem; margin-right: 1rem;">{icon}</div>
                <div>
                    <strong>{title}</strong><br>
                    <small>{desc}</small>
                </div>
            </div>
            """, unsafe_allow_html=True)

    # Footer
    st.markdown("---")
    st.markdown("""
    <div style="text-align: center; padding: 2rem; background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); border-radius: 10px; color: white; margin-top: 2rem;">
        <h3>🎉 Experience Advanced Computer Vision</h3>
        <p><strong>⭐ Built by Lee Akpareva | AI Consultant & Computer Vision Specialist ⭐</strong></p>
        <p>🚀 <em>Powered by YOLOv8 • OpenAI • Streamlit</em></p>
    </div>
    """, unsafe_allow_html=True)

if __name__ == "__main__":
    main()