Refactor investor and company schemas to allow optional fields; update filtering logic in read_companies function and add find_similar_investors endpoint; change LLM model in InvestorProcessor and QueryProcessor for improved performance.

app/routers/companies.py

@@ -34,6 +34,10 @@ def read_companies(db: Session = Depends(get_db)):
     """Get all companies with their investor relationships"""
     companies = (
         db.query(CompanyTable)
+        .filter(
+            CompanyTable.name.isnot(None),
+            CompanyTable.description.isnot(None)
+        )
         .options(
             selectinload(CompanyTable.investors),
             selectinload(CompanyTable.members),

app/routers/investors.py

@@ -7,6 +7,7 @@ from fastapi import APIRouter, Depends, HTTPException, Query
 from schemas.router_schemas import InvestmentStage, InvestorData
 from pydantic import BaseModel
 from sqlalchemy.orm import Session, selectinload
+from services.querying import QueryProcessor
 
 router = APIRouter(tags=["Investor Routes"])
 
@@ -234,3 +235,70 @@ def delete_investor(investor_id: int, db: Session = Depends(get_db)):
     return {"message": "Investor deleted successfully"}
 
 
+@router.get("/investors/{investor_id}/similar", response_model=List[InvestorData])
+def find_similar_investors(investor_id: int, db: Session = Depends(get_db)):
+    """Find investors similar to a given investor"""
+    
+    # First, get the target investor
+    target_investor = (
+        db.query(InvestorTable)
+        .options(
+            selectinload(InvestorTable.portfolio_companies),
+            selectinload(InvestorTable.team_members),
+            selectinload(InvestorTable.sectors),
+        )
+        .filter(InvestorTable.id == investor_id)
+        .first()
+    )
+    
+    if not target_investor:
+        raise HTTPException(status_code=404, detail="Investor not found")
+    
+    # Build query to find similar investors
+    query = db.query(InvestorTable).options(
+        selectinload(InvestorTable.portfolio_companies),
+        selectinload(InvestorTable.team_members),
+        selectinload(InvestorTable.sectors),
+    ).filter(InvestorTable.id != investor_id)  # Exclude the target investor
+    
+    # Filter by same stage focus
+    query = query.filter(InvestorTable.stage_focus == target_investor.stage_focus)
+    
+    # Filter by similar geographic focus (partial match)
+    query = query.filter(InvestorTable.geographic_focus.ilike(f"%{target_investor.geographic_focus}%"))
+    
+    # Filter by overlapping check size ranges
+    query = query.filter(
+        InvestorTable.check_size_upper >= target_investor.check_size_lower,
+        InvestorTable.check_size_lower <= target_investor.check_size_upper
+    )
+    
+    # Filter by similar AUM (within 50% range)
+    aum_lower = int(target_investor.aum * 0.5)
+    aum_upper = int(target_investor.aum * 1.5)
+    query = query.filter(
+        InvestorTable.aum >= aum_lower,
+        InvestorTable.aum <= aum_upper
+    )
+    
+    # Filter by common sectors
+    target_sector_names = [sector.name for sector in target_investor.sectors]
+    if target_sector_names:
+        query = query.join(InvestorTable.sectors).filter(
+            SectorTable.name.in_(target_sector_names)
+        )
+    
+    investors = query.all()
+    
+    # Transform to InvestorData format
+    investor_data_list = []
+    for investor in investors:
+        investor_data = InvestorData(
+            investor=investor,
+            portfolio_companies=investor.portfolio_companies,
+            team_members=investor.team_members,
+            sectors=investor.sectors,
+        )
+        investor_data_list.append(investor_data)
+    
+    return investor_data_list