made version 2

2025-09-25 17:00:38 +01:00
parent b1b1c5ea1e
commit 0f7beca5e1
42 changed files with 660 additions and 2036 deletions
@@ -9,7 +9,7 @@ from sqlalchemy.orm import Session, sessionmaker
 Base = declarative_base()

 # Database configuration
-DATABASE_URL = os.getenv("DATABASE_URL", "sqlite:///investors.db")
+DATABASE_URL = os.getenv("DATABASE_URL", "sqlite:///./investors.db")

 # Create engine
 engine = create_engine(DATABASE_URL, echo=False)
@@ -38,3 +38,7 @@ def init_database():
 def get_session_sync() -> Session:
    """Get a database session for synchronous operations"""
    return SessionLocal()
+
+def get_db_session():
+    """Get a database session for direct use."""
+    return SessionLocal()
@@ -1,11 +1,17 @@
-import datetime
 import enum

-from sqlalchemy import Column, DateTime, ForeignKey, Integer, String, Table, Text
-from sqlalchemy.orm import relationship
+from db.db import Base
+from sqlalchemy import Column, DateTime, ForeignKey, Integer, String, Table, Text, func
+from sqlalchemy.orm import declarative_mixin, relationship
 from sqlalchemy.types import Enum

-from db.db import Base
+
+@declarative_mixin
+class TimestampMixin:
+    created_at = Column(
+        DateTime(timezone=True), server_default=func.now(), nullable=False
+    )
+    updated_at = Column(DateTime(timezone=True), onupdate=func.now())


 class InvestmentStage(enum.Enum):
@@ -16,6 +22,7 @@ class InvestmentStage(enum.Enum):
    GROWTH = "GROWTH"
    LATE_STAGE = "LATE_STAGE"

+
 # Association table for many-to-many relationship between investors and companies
 investor_company_association = Table(
    "investor_companies",
@@ -34,7 +41,15 @@ investor_sector_association = Table(
 )


-class InvestorTable(Base):
+company_sector_association = Table(
+    "company_sector",
+    Base.metadata,
+    Column("company_id", Integer, ForeignKey("companies.id")),
+    Column("sector_id", Integer, ForeignKey("sectors.id")),
+)
+
+
+class InvestorTable(Base, TimestampMixin):
    __tablename__ = "investors"

    id = Column(Integer, primary_key=True, index=True)
@@ -46,12 +61,6 @@ class InvestorTable(Base):
    geographic_focus = Column(String, nullable=False)
    stage_focus = Column(Enum(InvestmentStage), nullable=False)
    number_of_investments = Column(Integer, default=0)
-    created_at = Column(DateTime, default=datetime.datetime.now(datetime.UTC))
-    updated_at = Column(
-        DateTime,
-        default=datetime.datetime.now(datetime.UTC),
-        onupdate=datetime.datetime.now(datetime.UTC),
-    )

    # Relationship to portfolio companies
    portfolio_companies = relationship(
@@ -59,7 +68,7 @@ class InvestorTable(Base):
        secondary=investor_company_association,
        back_populates="investors",
    )
-    team_members = relationship("InvestorTeamMember", back_populates="investor")
+    team_members = relationship("InvestorMember", back_populates="investor")
    sectors = relationship(
        "SectorTable",
        secondary=investor_sector_association,
@@ -67,22 +76,29 @@ class InvestorTable(Base):
    )


-class CompanyTable(Base):
+class InvestorMember(Base, TimestampMixin):
+    __tablename__ = "investor_members"
+    id = Column(Integer, primary_key=True, index=True)
+    name = Column(String, nullable=False)
+    role = Column(String, nullable=False)
+    email = Column(String, nullable=False)
+
+    investor_id = Column(Integer, ForeignKey("investors.id"))
+    investor = relationship("InvestorTable", back_populates="team_members")
+
+
+class CompanyTable(Base, TimestampMixin):
    __tablename__ = "companies"

    id = Column(Integer, primary_key=True, index=True)
    name = Column(String, nullable=False)
    industry = Column(String, nullable=False)
    location = Column(String, nullable=False)
+    description = Column(String, nullable=True)
    founded_year = Column(Integer, nullable=True)
    website = Column(String, nullable=True)
-    created_at = Column(DateTime, default=datetime.datetime.now(datetime.UTC))
-    updated_at = Column(
-        DateTime,
-        default=datetime.datetime.now(datetime.UTC),
-        onupdate=datetime.datetime.now(datetime.UTC),
-    )

+    members = relationship("CompanyMember", back_populates="company")
    # Relationship back to investors
    investors = relationship(
        "InvestorTable",
@@ -90,8 +106,23 @@ class CompanyTable(Base):
        back_populates="portfolio_companies",
    )

+    sectors = relationship(
+        "SectorTable", secondary=company_sector_association, back_populates="companies"
+    )

-class SectorTable(Base):
+
+class CompanyMember(Base, TimestampMixin):
+    __tablename__ = "company_members"
+    id = Column(Integer, primary_key=True)
+    name = Column(String)
+    linkedin = Column(String)
+    role = Column(String)
+    company_id = Column(Integer, ForeignKey("companies.id"), nullable=False)
+
+    company = relationship("CompanyTable", back_populates="members")
+
+
+class SectorTable(Base, TimestampMixin):
    __tablename__ = "sectors"

    id = Column(Integer, primary_key=True, index=True)
@@ -104,13 +135,6 @@ class SectorTable(Base):
        back_populates="sectors",
    )

-
-class InvestorTeamMember(Base):
-    __tablename__ = "investor_team"
-    id = Column(Integer, primary_key=True, index=True)
-    name = Column(String, nullable=False)
-    role = Column(String, nullable=False)
-    email = Column(String, nullable=False)
-
-    investor_id = Column(Integer, ForeignKey("investors.id"))
-    investor = relationship("InvestorTable", back_populates="team_members")
+    companies = relationship(
+        "CompanyTable", secondary=company_sector_association, back_populates="sectors"
+    )
@@ -1,115 +0,0 @@
-import json
-from typing import List, Optional
-
-from pydantic import BaseModel
-from sqlalchemy import JSON, Column, DateTime, Integer, String, Text
-from sqlalchemy.ext.declarative import declarative_base
-from sqlalchemy.sql import func
-
-Base = declarative_base()
-
-
-class Investor(Base):
-    __tablename__ = "investors"
-
-    id = Column(Integer, primary_key=True, autoincrement=True)
-    name = Column(String(500), nullable=False)
-    website = Column(String(1000))
-
-    # Core investment information
-    investor_description = Column(Text)
-    investment_thesis_focus = Column(JSON)  # List of focus areas
-    headquarters = Column(String(1000))
-
-    # AUM information
-    aum_amount = Column(String(200))
-    aum_as_of_date = Column(String(100))
-    aum_source_url = Column(String(1000))
-
-    # Fund information
-    funds_info = Column(JSON)  # Complex fund data
-
-    # Raw data columns for reference
-    crunchbase_urls = Column(Text)
-    crunchbase_extract = Column(Text)
-    linkedin_profile = Column(Text)
-    source_truth_profile = Column(Text)
-
-    # Metadata
-    created_at = Column(DateTime(timezone=True), server_default=func.now())
-    updated_at = Column(DateTime(timezone=True), onupdate=func.now())
-
-    def __repr__(self):
-        return f"<Investor(name='{self.name}', website='{self.website}')>"
-
-
-# Pydantic models for data validation and parsing
-class AUMInfo(BaseModel):
-    aumAmount: Optional[str] = None
-    asOfDate: Optional[str] = None
-    sourceUrl: Optional[str] = None
-
-
-class FundInfo(BaseModel):
-    fundName: Optional[str] = None
-    fundSize: Optional[str] = None
-    vintage: Optional[str] = None
-    status: Optional[str] = None
-    description: Optional[str] = None
-
-
-class InvestorProfile(BaseModel):
-    websiteURL: Optional[str] = None
-    investorDescription: Optional[str] = None
-    investmentThesisFocus: Optional[List[str]] = None
-    headquarters: Optional[str] = None
-    overallAssetsUnderManagement: Optional[AUMInfo] = None
-    funds: Optional[List[FundInfo]] = None
-
-
-class CSVRow(BaseModel):
-    name: str
-    website: Optional[str] = None
-    investment_firm_profile: Optional[str] = None
-    crunchbase_linkedin_urls: Optional[str] = None
-    crunchbase_firm_extract: Optional[str] = None
-    linkedin_investment_profile: Optional[str] = None
-    source_of_truth_profile: Optional[str] = None
-
-    def get_combined_description(self) -> str:
-        """Combine all description fields for vector embedding"""
-        descriptions = []
-
-        if self.investment_firm_profile:
-            try:
-                profile_data = json.loads(self.investment_firm_profile)
-                if isinstance(profile_data, dict):
-                    desc = profile_data.get("investorDescription", "")
-                    if desc:
-                        descriptions.append(desc)
-            except (json.JSONDecodeError, TypeError):
-                pass
-
-        if self.crunchbase_firm_extract:
-            descriptions.append(self.crunchbase_firm_extract)
-
-        if self.linkedin_investment_profile:
-            descriptions.append(self.linkedin_investment_profile)
-
-        if self.source_of_truth_profile:
-            descriptions.append(self.source_of_truth_profile)
-
-        return " ".join(descriptions)
-
-    def get_investment_focus(self) -> List[str]:
-        """Extract investment thesis focus"""
-        if self.investment_firm_profile:
-            try:
-                profile_data = json.loads(self.investment_firm_profile)
-                if isinstance(profile_data, dict):
-                    focus = profile_data.get("investmentThesisFocus", [])
-                    if isinstance(focus, list):
-                        return focus
-            except (json.JSONDecodeError, TypeError):
-                pass
-        return []