test_enhanced_search.py

#!/usr/bin/env python3
"""
Test Enhanced Search for Pension Rules Query
Demonstrates improved search results for "What are the pension rules?" with 1500+ documents
"""

import asyncio
import logging
import sys
import os

# Setup logging
logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
logger = logging.getLogger(__name__)

async def test_pension_search():
    """Test enhanced search vs original search for pension rules"""
    
    print("🔍 Testing Enhanced Search for Large Document Collection (1500+ docs)")
    print("=" * 70)
    
    # Test query that was giving wrong results
    test_query = "What are the pension rules?"
    
    try:
        # Import after adding to path
        from enhanced_search_service import enhanced_search_service
        from lancedb_service import lancedb_service
        
        print(f"📝 Query: '{test_query}'")
        print(f"📊 Document collection size: ~1500 documents")
        print()
        
        # Test enhanced search
        print("🚀 Testing Enhanced Search Strategy:")
        print("-" * 40)
        
        enhanced_results = await enhanced_search_service.enhanced_pension_search(test_query, limit=5)
        
        if enhanced_results:
            print(f"✅ Enhanced search found {len(enhanced_results)} relevant documents:")
            
            for i, result in enumerate(enhanced_results[:3], 1):
                content = result.get('content', '')
                filename = result.get('filename', 'Unknown')
                
                # Show snippet with pension-related content
                lines = content.split('\n')
                pension_lines = [line.strip() for line in lines if 'pension' in line.lower()]
                
                print(f"\n{i}. Document: {filename}")
                if pension_lines:
                    print(f"   Pension content preview:")
                    for line in pension_lines[:2]:  # Show first 2 pension-related lines
                        if line:
                            print(f"   • {line[:80]}{'...' if len(line) > 80 else ''}")
                else:
                    # Show general content preview
                    preview = content[:150].replace('\n', ' ').strip()
                    print(f"   Content preview: {preview}{'...' if len(content) > 150 else ''}")
        else:
            print("❌ Enhanced search found no results")
        
        print("\n" + "=" * 70)
        
        # Test fallback to original search
        print("⚠️  Original Search Strategy (for comparison):")
        print("-" * 40)
        
        try:
            original_results = await lancedb_service.search_documents(test_query, limit=5)
            
            if original_results:
                print(f"📄 Original search found {len(original_results)} documents:")
                
                for i, result in enumerate(original_results[:3], 1):
                    content = result.get('content', '')
                    filename = result.get('filename', 'Unknown')
                    
                    print(f"\n{i}. Document: {filename}")
                    preview = content[:150].replace('\n', ' ').strip()
                    print(f"   Content preview: {preview}{'...' if len(content) > 150 else ''}")
                    
                    # Check if it's actually pension-related
                    if 'pension' in content.lower():
                        print(f"   ✅ Contains pension content")
                    else:
                        print(f"   ❌ No pension content detected")
                        
            else:
                print("❌ Original search found no results")
                
        except Exception as e:
            print(f"❌ Original search failed: {e}")
        
        print("\n" + "=" * 70)
        print("📊 Search Comparison Summary:")
        print(f"   Enhanced Search: Better targeting of pension-specific content")
        print(f"   Original Search: Generic results that might miss relevant docs")
        print(f"   Expected Result: Enhanced search should return actual pension rules")
        
    except ImportError as e:
        print(f"❌ Import error: {e}")
        print("💡 Make sure you're running from the PensionBot directory")
    except Exception as e:
        print(f"❌ Test error: {e}")

async def test_query_enhancement():
    """Test query enhancement strategies"""
    
    print("\n🎯 Testing Query Enhancement Strategies:")
    print("=" * 50)
    
    test_queries = [
        "What are the pension rules?",
        "How to calculate pension?",
        "Pension eligibility criteria",
        "Family pension benefits",
        "Commutation of pension"
    ]
    
    try:
        from enhanced_search_service import enhanced_search_service
        
        for query in test_queries:
            enhanced_query = enhanced_search_service._enhance_query(query)
            print(f"Original: {query}")
            print(f"Enhanced: {enhanced_query}")
            print()
            
    except Exception as e:
        print(f"❌ Query enhancement test error: {e}")

if __name__ == "__main__":
    print("🎯 Enhanced Search Test for Large Document Collections")
    print("Testing improved search for pension rules with 1500+ documents")
    print()
    
    # Run the tests
    asyncio.run(test_pension_search())
    asyncio.run(test_query_enhancement())