Added funds table

app/db/models.py

@@ -2,7 +2,7 @@ import enum
 
 from sqlalchemy import Column, DateTime, ForeignKey, Integer, String, Table, Text, func
 from sqlalchemy.orm import declarative_mixin, relationship
-from sqlalchemy.types import Enum
+from sqlalchemy.types import JSON, Enum
 
 from db.db import Base
 
@@ -77,14 +77,52 @@ class InvestorTable(Base, TimestampMixin):
     id = Column(Integer, primary_key=True, index=True)
     name = Column(String, nullable=False)
     description = Column(Text, nullable=True)
-    aum = Column(Integer, nullable=True)  # Assets Under Management
-    check_size_lower = Column(Integer, nullable=True)  # Lower bound
-    check_size_upper = Column(Integer, nullable=True)  # Upper bound
+
+    # Basic investor info
+    website = Column(String, nullable=True)
+    headquarters = Column(String, nullable=True)
+
+    # AUM fields
+    aum = Column(
+        String, nullable=True
+    )  # Store as string to preserve currency (e.g., "EUR 850,000,000")
+    aum_as_of_date = Column(String, nullable=True)
+    aum_source_url = Column(String, nullable=True)
+
+    # Check size (deprecated in favor of fund-level data, but keeping for backward compatibility)
+    check_size_lower = Column(Integer, nullable=True)
+    check_size_upper = Column(Integer, nullable=True)
+
+    # Geographic focus (deprecated in favor of fund-level, but keeping for backward compatibility)
     geographic_focus = Column(String, nullable=True)
-    stage_focus = Column(Enum(InvestmentStage), nullable=True)
+    stage_focus = Column(
+        Enum(InvestmentStage), nullable=True
+    )  # Deprecated in favor of fund-level
+
+    # Investment thesis and portfolio
+    investment_thesis = Column(JSON, nullable=True)  # Array of thesis statements
+    portfolio_highlights = Column(
+        JSON, nullable=True
+    )  # Array of portfolio company names
+    linked_documents = Column(JSON, nullable=True)  # Array of document URLs
+
+    # Research metadata
+    researcher_notes = Column(Text, nullable=True)
+    missing_important_fields = Column(
+        JSON, nullable=True
+    )  # Array of missing field names
+    sources = Column(JSON, nullable=True)  # JSON object with source URLs
+
+    # Portfolio info
     number_of_investments = Column(Integer, default=0, nullable=True)
 
-    team_members = relationship("InvestorMember", back_populates="investor")
+    # Relationships
+    team_members = relationship(
+        "InvestorMember", back_populates="investor", cascade="all, delete-orphan"
+    )
+    funds = relationship(
+        "FundTable", back_populates="investor", cascade="all, delete-orphan"
+    )
 
     # Relationship to portfolio companies
     portfolio_companies = relationship(
@@ -111,12 +149,39 @@ class InvestorMember(Base, TimestampMixin):
     id = Column(Integer, primary_key=True, index=True)
     name = Column(String, nullable=False)
     role = Column(String, nullable=True)
+    title = Column(String, nullable=True)  # Alternative to role
     email = Column(String, nullable=True)
+    source_url = Column(String, nullable=True)  # URL where member info was found
 
     investor_id = Column(Integer, ForeignKey("investors.id"))
     investor = relationship("InvestorTable", back_populates="team_members")
 
 
+class FundTable(Base, TimestampMixin):
+    __tablename__ = "funds"
+
+    id = Column(Integer, primary_key=True, index=True)
+    investor_id = Column(Integer, ForeignKey("investors.id"), nullable=False)
+
+    # Fund details
+    fund_name = Column(String, nullable=True)
+    fund_size = Column(String, nullable=True)  # Store as string to preserve currency
+    fund_size_source_url = Column(String, nullable=True)
+    estimated_investment_size = Column(
+        String, nullable=True
+    )  # e.g., "EUR 1,000 to 2,000"
+    source_url = Column(String, nullable=True)
+    source_provider = Column(String, nullable=True)  # e.g., "Perplexity"
+
+    # JSON array fields
+    geographic_focus = Column(JSON, nullable=True)  # Array of regions/countries
+    investment_stage_focus = Column(JSON, nullable=True)  # Array of stages
+    sector_focus = Column(JSON, nullable=True)  # Array of sectors
+
+    # Relationships
+    investor = relationship("InvestorTable", back_populates="funds")
+
+
 class CompanyTable(Base, TimestampMixin):
     __tablename__ = "companies"
 
@@ -128,7 +193,9 @@ class CompanyTable(Base, TimestampMixin):
     founded_year = Column(Integer, nullable=True)
     website = Column(String, nullable=True)
 
-    members = relationship("CompanyMember", back_populates="company")
+    members = relationship(
+        "CompanyMember", back_populates="company", cascade="all, delete-orphan"
+    )
     # Relationship back to investors
     investors = relationship(
         "InvestorTable",