Update rag_utils.py

rag_utils.py

@@ -1,73 +1,136 @@
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.vectorstores import FAISS
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-import streamlit as st
+# knowledge_base.py
 
-class RAGSystem:
-    def __init__(self):
-        self.embeddings = HuggingFaceEmbeddings(
-            model_name="sentence-transformers/all-mpnet-base-v2"
-        )
-        self.vector_store = None
-        self.text_splitter = RecursiveCharacterTextSplitter(
-            chunk_size=500,
-            chunk_overlap=50
-        )
-        
-    def initialize_knowledge_base(self, knowledge_base):
-        """Initialize vector store with construction knowledge"""
-        documents = []
-        
-        for damage_type, cases in knowledge_base.items():
-            for case in cases:
-                doc_text = f"""
-                Damage Type: {damage_type}
-                Severity: {case['severity']}
-                Description: {case['description']}
-                Repair Methods: {', '.join(case['repair_method'])}
-                Cost: {case['estimated_cost']}
-                Timeframe: {case['timeframe']}
-                Location: {case['location']}
-                Required Expertise: {case['required_expertise']}
-                Immediate Action: {case['immediate_action']}
-                Prevention: {case['prevention']}
-                """
-                documents.append(doc_text)
-        
-        splits = self.text_splitter.create_documents(documents)
-        self.vector_store = FAISS.from_documents(splits, self.embeddings)
-        
-    def query_knowledge_base(self, query, k=3):
-        """Query the vector store for relevant information"""
-        if not self.vector_store:
-            raise ValueError("Vector store not initialized")
-            
-        results = self.vector_store.similarity_search(query, k=k)
-        return results
-    
-    def get_enhanced_analysis(self, damage_type, confidence, custom_query=None):
-        """Get enhanced analysis based on damage type and confidence"""
-        if not custom_query:
-            query = f"What are the key considerations and recommendations for {damage_type} with {confidence}% confidence?"
-        else:
-            query = custom_query
-            
-        relevant_docs = self.query_knowledge_base(query)
-        
-        enhanced_info = {
-            "technical_details": [],
-            "safety_considerations": [],
-            "expert_recommendations": []
+import logging
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
+# Knowledge base containing structural damage information
+KNOWLEDGE_BASE = {
+    "spalling": [
+        {
+            "severity": "Critical",
+            "description": "Severe concrete spalling with exposed reinforcement and section loss",
+            "repair_method": [
+                "Install temporary support",
+                "Remove deteriorated concrete",
+                "Clean and treat reinforcement",
+                "Apply corrosion inhibitor",
+                "Apply bonding agent",
+                "High-strength repair mortar"
+            ],
+            "estimated_cost": "Very High ($15,000+)",
+            "timeframe": "3-4 weeks",
+            "location": "Primary structural elements",
+            "required_expertise": "Structural Engineer + Specialist Contractor",
+            "immediate_action": "Evacuate area, install temporary support, prevent access",
+            "prevention": "Regular inspections, waterproofing, chloride protection"
+        },
+        {
+            "severity": "High",
+            "description": "Surface spalling with visible reinforcement",
+            "repair_method": [
+                "Remove damaged concrete",
+                "Treat reinforcement",
+                "Apply repair mortar",
+                "Surface treatment"
+            ],
+            "estimated_cost": "High ($8,000-$15,000)",
+            "timeframe": "2-3 weeks",
+            "location": "Structural elements",
+            "required_expertise": "Structural Engineer",
+            "immediate_action": "Area isolation, temporary support assessment",
+            "prevention": "Protective coatings, drainage improvement"
+        }
+    ],
+    "reinforcement_corrosion": [
+        {
+            "severity": "Critical",
+            "description": "Severe corrosion with >30% section loss",
+            "repair_method": [
+                "Structural support",
+                "Remove concrete",
+                "Replace reinforcement",
+                "Corrosion protection",
+                "Concrete repair"
+            ],
+            "estimated_cost": "Critical ($20,000+)",
+            "timeframe": "4-6 weeks",
+            "location": "Load-bearing elements",
+            "required_expertise": "Senior Structural Engineer",
+            "immediate_action": "Immediate evacuation, emergency shoring",
+            "prevention": "Waterproofing, cathodic protection"
+        }
+    ],
+    "structural_crack": [
+        {
+            "severity": "High",
+            "description": "Cracks >5mm in structural elements",
+            "repair_method": [
+                "Structural analysis",
+                "Epoxy injection",
+                "Carbon fiber reinforcement",
+                "Crack monitoring"
+            ],
+            "estimated_cost": "High ($10,000-$20,000)",
+            "timeframe": "2-4 weeks",
+            "location": "Primary structure",
+            "required_expertise": "Structural Engineer",
+            "immediate_action": "Install crack monitors, load restriction",
+            "prevention": "Load management, joint maintenance"
         }
-        
-        for doc in relevant_docs:
-            content = doc.page_content
-            
-            if "severity" in content.lower() or "description" in content.lower():
-                enhanced_info["technical_details"].append(content)
-            elif "immediate action" in content.lower() or "prevention" in content.lower():
-                enhanced_info["safety_considerations"].append(content)
-            elif "repair" in content.lower() or "expertise" in content.lower():
-                enhanced_info["expert_recommendations"].append(content)
-                
-        return enhanced_info
+    ],
+    "dampness": [
+        {
+            "severity": "Medium",
+            "description": "Active water penetration with efflorescence",
+            "repair_method": [
+                "Water source identification",
+                "Drainage improvement",
+                "Waterproof membrane",
+                "Ventilation"
+            ],
+            "estimated_cost": "Medium ($5,000-$10,000)",
+            "timeframe": "1-2 weeks",
+            "location": "Various",
+            "required_expertise": "Waterproofing Specialist",
+            "immediate_action": "Dehumidification, efflorescence cleaning",
+            "prevention": "Proper drainage, vapor barriers"
+        }
+    ],
+    "no_damage": [
+        {
+            "severity": "Low",
+            "description": "No significant structural issues",
+            "repair_method": [
+                "Regular inspection",
+                "Preventive maintenance"
+            ],
+            "estimated_cost": "Low ($500-$2,000)",
+            "timeframe": "1-2 days",
+            "location": "General",
+            "required_expertise": "Building Inspector",
+            "immediate_action": "Continue monitoring",
+            "prevention": "Regular maintenance schedule"
+        }
+    ]
+}
+
+# Damage type metadata
+DAMAGE_TYPES = {
+    0: {'name': 'spalling', 'risk': 'High', 'color': '#ff4d4d'},
+    1: {'name': 'reinforcement_corrosion', 'risk': 'Critical', 'color': '#800000'},
+    2: {'name': 'structural_crack', 'risk': 'High', 'color': '#ff6b6b'},
+    3: {'name': 'dampness', 'risk': 'Medium', 'color': '#4dabf7'},
+    4: {'name': 'no_damage', 'risk': 'Low', 'color': '#40c057'}
+}
+
+# Validation for knowledge base
+required_keys = ['severity', 'description', 'repair_method', 'estimated_cost', 'timeframe', 'location', 'required_expertise', 'immediate_action', 'prevention']
+for damage_type, cases in KNOWLEDGE_BASE.items():
+    for case in cases:
+        for key in required_keys:
+            if key not in case:
+                logging.error(f"Missing required field '{key}' in {damage_type}")
+                raise ValueError(f"Missing required field '{key}' in {damage_type}")
+logging.info("Knowledge base validation passed.")