Update app.py

app.py

@@ -1,4 +1,3 @@
-# app.py
 import streamlit as st
 from transformers import ViTForImageClassification, ViTImageProcessor
 from PIL import Image
@@ -6,19 +5,26 @@ import torch
 import time
 import gc
 import logging
-from knowledge_base import KNOWLEDGE_BASE, DAMAGE_TYPES
+from knowledge_base import KNOWLEDGE_BASE, DAMAGE_TYPES, validate_knowledge_base
 from rag_utils import RAGSystem
 import structlog
 from typing import Optional, Dict, Any
 from functools import lru_cache
+from dynaconf import Dynaconf
+
+# Configure settings
+settings = Dynaconf(
+    settings_files=['settings.yaml', '.secrets.yaml'],
+    environments=True
+)
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
 logger = structlog.get_logger()
 
 # Constants
-MAX_FILE_SIZE = 5 * 1024 * 1024  # 5MB
-MAX_IMAGE_SIZE = 1024  # Maximum dimension for images
+MAX_FILE_SIZE = settings.get('max_file_size', 5 * 1024 * 1024)  # 5MB default
+MAX_IMAGE_SIZE = settings.get('max_image_size', 1024)  # Maximum dimension default
 MODEL = None
 PROCESSOR = None
 RAG_SYSTEM = None
@@ -47,10 +53,12 @@ def init_session_state():
         st.session_state.history = []
     if 'dark_mode' not in st.session_state:
         st.session_state.dark_mode = False
+    if 'analysis_count' not in st.session_state:
+        st.session_state.analysis_count = 0
 
 @st.cache_resource(show_spinner="Loading AI model...", ttl=3600*24)
 def load_model():
-    """Load and cache the model and processor"""
+    """Load and cache the model with daily refresh"""
     try:
         model_name = "google/vit-base-patch16-224"
         processor = ViTImageProcessor.from_pretrained(model_name)
@@ -78,7 +86,7 @@ def validate_upload(file) -> bool:
         return False
     
     if file.size > MAX_FILE_SIZE:
-        st.error("File too large. Maximum size is 5MB.")
+        st.error(f"File too large. Maximum size is {MAX_FILE_SIZE/1024/1024:.1f}MB.")
         return False
     
     if file.type not in ['image/jpeg', 'image/png']:
@@ -134,12 +142,49 @@ def analyze_damage(image: Image.Image, model: ViTForImageClassification,
             st.error(f"Error analyzing image: {str(e)}")
         return None
 
+def generate_downloadable_report(analysis_results: Dict):
+    """Generate a downloadable PDF report"""
+    try:
+        import io
+        from reportlab.lib import colors
+        from reportlab.lib.pagesizes import letter
+        from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
+        from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
+
+        buffer = io.BytesIO()
+        doc = SimpleDocTemplate(buffer, pagesize=letter)
+        styles = getSampleStyleSheet()
+        story = []
+
+        # Add title
+        story.append(Paragraph("Structural Damage Analysis Report", styles['Title']))
+        story.append(Spacer(1, 12))
+
+        # Add analysis results
+        for damage_type, details in analysis_results.items():
+            story.append(Paragraph(f"Damage Type: {damage_type}", styles['Heading1']))
+            story.append(Paragraph(f"Confidence: {details['confidence']}%", styles['Normal']))
+            story.append(Paragraph("Recommendations:", styles['Heading2']))
+            for rec in details['recommendations']:
+                story.append(Paragraph(f"• {rec}", styles['Normal']))
+            story.append(Spacer(1, 12))
+
+        doc.build(story)
+        pdf = buffer.getvalue()
+        buffer.close()
+        return pdf
+    except Exception as e:
+        logger.error(f"Error generating report: {str(e)}")
+        return None
+
 def display_analysis_results(predictions: torch.Tensor, analysis_time: float):
     """Display analysis results with damage details"""
     st.markdown("### 📊 Analysis Results")
     st.markdown(f"*Analysis completed in {analysis_time:.2f} seconds*")
     
+    analysis_results = {}
     detected = False
+    
     for idx, prob in enumerate(predictions):
         confidence = float(prob) * 100
         if confidence > 15:
@@ -165,9 +210,24 @@ def display_analysis_results(predictions: torch.Tensor, analysis_time: float):
                 with tabs[2]:
                     for safety in analysis['safety_considerations']:
                         st.warning(safety)
+                
+                analysis_results[damage_type] = {
+                    'confidence': confidence,
+                    'recommendations': analysis['expert_recommendations']
+                }
     
     if not detected:
         st.info("No significant structural damage detected. Regular maintenance recommended.")
+    else:
+        # Generate download button for report
+        pdf_report = generate_downloadable_report(analysis_results)
+        if pdf_report:
+            st.download_button(
+                label="Download Analysis Report",
+                data=pdf_report,
+                file_name="damage_analysis_report.pdf",
+                mime="application/pdf"
+            )
 
 def main():
     """Main application function"""
@@ -208,6 +268,11 @@ def main():
         RAG_SYSTEM = RAGSystem()
         RAG_SYSTEM.initialize_knowledge_base(KNOWLEDGE_BASE)
     
+    # Validate knowledge base
+    if not validate_knowledge_base():
+        st.error("Knowledge base validation failed. Please check the logs.")
+        return
+    
     # File upload
     uploaded_file = st.file_uploader(
         "Upload an image for analysis",
@@ -234,6 +299,7 @@ def main():
                     analysis_time = time.time() - start_time
                     display_analysis_results(predictions, analysis_time)
                     st.session_state.history.append(f"Analyzed {uploaded_file.name}")
+                    st.session_state.analysis_count += 1
         
         except Exception as e:
             logger.error("Error in main processing loop", error=str(e))