Implement find_similar_investors endpoint to enhance investor similarity search; refactor update_investor logic and improve scoring mechanism for better results.

.gitignore

@@ -14,3 +14,4 @@
 
 *.cypython
 
+/preprocessor

app/routers/investors.py

@@ -181,64 +181,15 @@ def create_investor(investor: InvestorCreate, db: Session = Depends(get_db)):
     )
 
 
-@router.put("/investors/{investor_id}", response_model=InvestorData)
-def update_investor(
-    investor_id: int, investor: InvestorUpdate, db: Session = Depends(get_db)
-):
-    """Update an existing investor"""
-    db_investor = (
-        db.query(InvestorTable).filter(InvestorTable.id == investor_id).first()
-    )
-    if not db_investor:
-        raise HTTPException(status_code=404, detail="Investor not found")
-
-    update_data = investor.dict(exclude_unset=True)
-    for field, value in update_data.items():
-        setattr(db_investor, field, value)
-
-    db.commit()
-    db.refresh(db_investor)
-
-    # Reload with relationships
-    investor_with_relations = (
-        db.query(InvestorTable)
-        .options(
-            selectinload(InvestorTable.portfolio_companies),
-            selectinload(InvestorTable.team_members),
-            selectinload(InvestorTable.sectors),
-        )
-        .filter(InvestorTable.id == investor_id)
-        .first()
-    )
-
-    # Transform to InvestorData format
-    return InvestorData(
-        investor=investor_with_relations,
-        portfolio_companies=investor_with_relations.portfolio_companies,
-        team_members=investor_with_relations.team_members,
-        sectors=investor_with_relations.sectors,
-    )
-
-
-@router.delete("/investors/{investor_id}")
-def delete_investor(investor_id: int, db: Session = Depends(get_db)):
-    """Delete an investor"""
-    db_investor = (
-        db.query(InvestorTable).filter(InvestorTable.id == investor_id).first()
-    )
-    if not db_investor:
-        raise HTTPException(status_code=404, detail="Investor not found")
-
-    db.delete(db_investor)
-    db.commit()
-    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)):
+def find_similar_investors(
-    """Find investors similar to a given investor using AI agent"""
+    investor_id: int, 
+    limit: int = Query(10, description="Maximum number of similar investors to return"),
+    db: Session = Depends(get_db)
+):
+    """Find investors similar to a given investor based on characteristics"""
     
-    # First, get the target investor to build the AI query
+    # Get the target investor
     target_investor = (
         db.query(InvestorTable)
         .options(
@@ -253,29 +204,78 @@ def find_similar_investors(investor_id: int, db: Session = Depends(get_db)):
     if not target_investor:
         raise HTTPException(status_code=404, detail="Investor not found")
 
-    # Build a descriptive query for the AI agent based on target investor characteristics
+    # Get target investor's sector IDs for comparison
-    target_sectors = [sector.name for sector in target_investor.sectors]
+    target_sector_ids = {sector.id for sector in target_investor.sectors}
-    sectors_text = ", ".join(target_sectors) if target_sectors else "any sector"
 
-    ai_query = f"""
+    # Query all other investors with their relationships
-    Find investors similar to investor ID {investor_id} with the following characteristics:
+    candidates = (
-    - Stage focus: {target_investor.stage_focus.value if target_investor.stage_focus else "any stage"}
+        db.query(InvestorTable)
-    - Geographic focus: {target_investor.geographic_focus or "any geography"}
+        .options(
-    - Check size range: ${target_investor.check_size_lower or 0:,} to ${target_investor.check_size_upper or 0:,}
+            selectinload(InvestorTable.portfolio_companies),
-    - AUM (Assets Under Management): ${target_investor.aum or 0:,}
+            selectinload(InvestorTable.team_members),
-    - Sectors: {sectors_text}
+            selectinload(InvestorTable.sectors),
+        )
+        .filter(InvestorTable.id != investor_id)
+        .all()
+    )
 
-    Find investors with similar characteristics but exclude investor ID {investor_id}.
+    # Calculate similarity scores
-    Look for investors with:
+    scored_investors = []
-    - Same or similar stage focus
+    for candidate in candidates:
-    - Similar geographic regions
+        score = 0
-    - Overlapping check size ranges
-    - Similar AUM levels (within a reasonable range)
-    - Common sector interests
-    """
         
-    # Use the AI agent to find similar investors
+        # Stage focus match (30 points)
-    query_processor = QueryProcessor()
+        if candidate.stage_focus == target_investor.stage_focus:
-    result = query_processor.process_query(ai_query)
+            score += 30
         
-    return result.investors
+        # Geographic focus match (20 points for exact, 10 for partial)
+        if candidate.geographic_focus and target_investor.geographic_focus:
+            if candidate.geographic_focus.lower() == target_investor.geographic_focus.lower():
+                score += 20
+            elif (candidate.geographic_focus.lower() in target_investor.geographic_focus.lower() or
+                  target_investor.geographic_focus.lower() in candidate.geographic_focus.lower()):
+                score += 10
+        
+        # Check size overlap (20 points max)
+        if (candidate.check_size_lower and candidate.check_size_upper and 
+            target_investor.check_size_lower and target_investor.check_size_upper):
+            # Calculate overlap percentage
+            overlap_start = max(candidate.check_size_lower, target_investor.check_size_lower)
+            overlap_end = min(candidate.check_size_upper, target_investor.check_size_upper)
+            if overlap_end > overlap_start:
+                overlap = overlap_end - overlap_start
+                target_range = target_investor.check_size_upper - target_investor.check_size_lower
+                overlap_ratio = overlap / target_range if target_range > 0 else 0
+                score += int(20 * overlap_ratio)
+        
+        # AUM similarity (15 points max)
+        if candidate.aum and target_investor.aum:
+            aum_diff = abs(candidate.aum - target_investor.aum)
+            max_aum = max(candidate.aum, target_investor.aum)
+            similarity_ratio = 1 - (aum_diff / max_aum) if max_aum > 0 else 0
+            score += int(15 * similarity_ratio)
+        
+        # Sector overlap (30 points max)
+        candidate_sector_ids = {sector.id for sector in candidate.sectors}
+        if target_sector_ids and candidate_sector_ids:
+            common_sectors = target_sector_ids.intersection(candidate_sector_ids)
+            overlap_ratio = len(common_sectors) / len(target_sector_ids)
+            score += int(30 * overlap_ratio)
+        
+        if score > 0:  # Only include investors with some similarity
+            scored_investors.append((score, candidate))
+    
+    # Sort by score (descending) and take top N
+    scored_investors.sort(key=lambda x: x[0], reverse=True)
+    similar_investors = [inv for score, inv in scored_investors[:limit]]
+    
+    # Transform to InvestorData format
+    return [
+        InvestorData(
+            investor=inv,
+            portfolio_companies=inv.portfolio_companies,
+            team_members=inv.team_members,
+            sectors=inv.sectors,
+        )
+        for inv in similar_investors
+    ]