feat: Simplify company profile processing to only extract founded_year and key_executives

app/services/llm_parser.py

@@ -265,37 +265,20 @@ Return the lower and upper bounds in USD."""
     ) -> Optional[dict]:
         """
         Process company profile from CSV data.
-        Manually extracts fields without using LLM.
+        Only extracts founded_year and key_executives - rest is in base database.
         """
         profile = self.parse_json_profile(profile_json)
         if not profile:
             return None
 
         try:
-            # Extract basic info
+            # Only extract founded_year and key_executives
             company_data = {
                 "name": name.strip() if name else None,
-                "website": website.strip() if website else None,
+                "founded_year": None,
-                "description": profile.get("companyDescription"),
-                "location": profile.get("geographicFocus"),
-                "industry": profile.get("sectorDescription"),
-                "founded_year": None,  # Not typically in the company JSON
                 "key_executives": [],
-                "client_categories": profile.get("clientCategories", []),
-                "product_description": profile.get("productDescription"),
-                "linked_documents": profile.get("linkedDocuments", []),
-                "researcher_notes": profile.get("researcherNotes"),
-                "missing_important_fields": profile.get("missingImportantFields", []),
-                "sources": profile.get("sources", {}),
-                "investor_names": [],
             }
 
-            # Parse investor names from the Investor column
-            if investor_names and pd.notna(investor_names):
-                # Split by comma and clean
-                investors = [inv.strip() for inv in str(investor_names).split(",")]
-                company_data["investor_names"] = [inv for inv in investors if inv]
-
             # Process key executives/leadership
             key_executives = profile.get("keyExecutives", [])
             if not key_executives:
@@ -313,7 +296,7 @@ Return the lower and upper bounds in USD."""
                     )
 
             # Try to extract founding year from description
-            description = company_data.get("description", "")
+            description = profile.get("companyDescription", "")
             if description:
                 # Look for patterns like "founded in 2020", "Gegründet 2020", "founded 2020"
                 year_patterns = [
@@ -344,41 +327,28 @@ Return the lower and upper bounds in USD."""
     def _save_parsed_company_to_db(
         self, db: Session, company_data: dict
     ) -> Optional[CompanyTable]:
-        """Save manually parsed company data to database"""
+        """Save manually parsed company data to database - only updates founded_year and key_executives"""
         try:
-            # Check if company already exists
+            # Check if company already exists (should exist in base database)
             existing_company = (
                 db.query(CompanyTable).filter_by(name=company_data["name"]).first()
             )
 
             if existing_company:
-                # Update existing company
+                # Update only founded_year on existing company
                 company = existing_company
-                company.website = company_data.get("website") or company.website
-                company.location = company_data.get("location") or company.location
-                company.description = (
-                    company_data.get("description") or company.description
-                )
-                company.industry = company_data.get("industry") or company.industry
                 if company_data.get("founded_year"):
                     company.founded_year = company_data["founded_year"]
             else:
-                # Create new company
+                # Company should already be in base database, but if not found, skip
-                company = CompanyTable(
+                print(
-                    name=company_data["name"],
+                    f"⚠️  Company '{company_data['name']}' not found in base database - skipping"
-                    website=company_data.get("website"),
-                    location=company_data.get("location"),
-                    description=company_data.get("description"),
-                    industry=company_data.get("industry"),
-                    founded_year=company_data.get("founded_year"),
                 )
-                db.add(company)
+                return None
-                db.flush()
 
             # Add/update company members (key executives)
             # First, remove existing members if updating
-            if existing_company:
+            db.query(CompanyMember).filter_by(company_id=company.id).delete()
-                db.query(CompanyMember).filter_by(company_id=company.id).delete()
 
             for exec_data in company_data.get("key_executives", []):
                 member = CompanyMember(
@@ -391,19 +361,6 @@ Return the lower and upper bounds in USD."""
                 )
                 db.add(member)
 
-            # Link to investors if provided
-            for investor_name in company_data.get("investor_names", []):
-                # Find investor in database
-                investor = (
-                    db.query(InvestorTable)
-                    .filter_by(name=investor_name.strip())
-                    .first()
-                )
-                if investor:
-                    # Add company to investor's portfolio if not already there
-                    if company not in investor.portfolio_companies:
-                        investor.portfolio_companies.append(company)
-
             return company
 
         except Exception as e: