feat: Implement database ingestion for investors and companies

- Added main ingestion logic in main.py to process CSV files for investors and companies.
- Implemented data cleaning functions for names, strings, integers, and websites.
- Established relationships between investors, companies, and sectors using SQLAlchemy ORM.
- Created models for investors, companies, sectors, and their relationships in models.py.
- Set up logging for error tracking during data processing.
- Initialized database and created necessary tables.

.gitignore

@@ -10,8 +10,7 @@
 
 *__pycache__
 
-/*.db
 
 *.cypython
 
-/preprocessor
+

app/db/db.py

@@ -1,4 +1,5 @@
 import os
+from pathlib import Path
 from typing import Annotated
 
 from fastapi import Depends
@@ -9,7 +10,11 @@ from sqlalchemy.orm import Session, sessionmaker
 Base = declarative_base()
 
 # Database configuration
-DATABASE_URL = os.getenv("DATABASE_URL", "sqlite:///./investors.db")
+# Use the preprocessor's database for consistency
+# Get absolute path to the preprocessor database
+# APP_DIR = Path(__file__).parent.parent
+# PREPROCESSOR_DB = APP_DIR.parent / "preprocessor" / "version_two.db"
+DATABASE_URL = os.getenv("DATABASE_URL", "sqlite:///./version_two.db")
 
 # Create engine
 engine = create_engine(DATABASE_URL, echo=False)
@@ -38,6 +43,7 @@ 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()

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
 
@@ -70,6 +70,22 @@ project_company_association = Table(
     Column("company_id", Integer, ForeignKey("companies.id")),
 )
 
+# Association table for fund-stage many-to-many
+fund_investment_stages_association = Table(
+    "fund_investment_stages",
+    Base.metadata,
+    Column("fund_id", Integer, ForeignKey("funds.id")),
+    Column("stage_id", Integer, ForeignKey("investment_stages.id")),
+)
+
+# Association table for fund-sector many-to-many
+fund_sectors_association = Table(
+    "fund_sectors",
+    Base.metadata,
+    Column("fund_id", Integer, ForeignKey("funds.id")),
+    Column("sector_id", Integer, ForeignKey("sectors.id")),
+)
+
 
 class InvestorTable(Base, TimestampMixin):
     __tablename__ = "investors"
@@ -77,14 +93,47 @@ 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
+    # Basic investor info
-    check_size_upper = Column(Integer, nullable=True)  # Upper bound
+    website = Column(String, nullable=True)
+    headquarters = Column(String, nullable=True)
+
+    # AUM fields
+    aum = Column(Integer, nullable=True)  # Store as integer for numerical filtering
+    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)
+
+    # 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 +160,51 @@ 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(
+        Integer, nullable=True
+    )  # Store as integer for numerical filtering
+    fund_size_source_url = Column(String, nullable=True)
+
+    # Check size range (parsed from estimated_investment_size by LLM)
+    check_size_lower = Column(Integer, nullable=True)
+    check_size_upper = Column(Integer, nullable=True)
+
+    source_url = Column(String, nullable=True)
+    source_provider = Column(String, nullable=True)  # e.g., "Perplexity"
+
+    # Geographic focus as simple string
+    geographic_focus = Column(String, nullable=True)
+
+    # Relationships
+    investor = relationship("InvestorTable", back_populates="funds")
+    investment_stages = relationship(
+        "InvestmentStageTable",
+        secondary=fund_investment_stages_association,
+        back_populates="funds",
+    )
+    sectors = relationship(
+        "SectorTable",
+        secondary=fund_sectors_association,
+        back_populates="funds",
+    )
+
+
 class CompanyTable(Base, TimestampMixin):
     __tablename__ = "companies"
 
@@ -128,7 +216,9 @@ 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",
@@ -158,26 +248,43 @@ class CompanyMember(Base, TimestampMixin):
     company = relationship("CompanyTable", back_populates="members")
 
 
+class InvestmentStageTable(Base, TimestampMixin):
+    __tablename__ = "investment_stages"
+
+    id = Column(Integer, primary_key=True, index=True)
+    name = Column(String, nullable=False, unique=True)
+
+    # Relationships
+    funds = relationship(
+        "FundTable",
+        secondary=fund_investment_stages_association,
+        back_populates="investment_stages",
+    )
+
+
 class SectorTable(Base, TimestampMixin):
     __tablename__ = "sectors"
 
     id = Column(Integer, primary_key=True, index=True)
     name = Column(String, nullable=False)
 
-    # Add relationship back to investors
+    # Relationships
     investors = relationship(
         "InvestorTable",
         secondary=investor_sector_association,
         back_populates="sectors",
     )
-
     companies = relationship(
         "CompanyTable", secondary=company_sector_association, back_populates="sectors"
     )
-
     projects = relationship(
         "ProjectTable", secondary=project_sector_association, back_populates="sector"
     )
+    funds = relationship(
+        "FundTable",
+        secondary=fund_sectors_association,
+        back_populates="sectors",
+    )
 
 
 class ProjectTable(Base, TimestampMixin):

app/main.py

@@ -44,6 +44,27 @@ def health():
 async def parse_csv(
     db: db_dependency, file: UploadFile = File(...), is_investor: int = Form(...)
 ):
+    """
+    Parse and import CSV data into the database.
+
+    **For investors:**
+    - Expected columns: Name, Website, Final Investor Profile, Final Profile sourcing
+    - Manually parses JSON profiles for efficiency
+    - Uses LLM only for currency conversion to USD
+    - Handles AUM, fund sizes, and check sizes as integers
+
+    **For companies:**
+    - Expected columns: Name, Website, Investor, Final Investor Profile (company profile)
+    - 100% manual JSON parsing - no LLM needed
+    - Extracts company details, executives, investors, and client categories
+    - Automatically links companies to investors in database
+
+    **Benefits:**
+    - Fast processing (5-10s per record)
+    - Low cost (minimal or no LLM usage)
+    - Accurate data extraction
+    - Automatic database persistence
+    """
     # Read uploaded CSV with pandas
     content = await file.read()
     df = pd.read_csv(io.StringIO(content.decode("utf-8")))
@@ -52,12 +73,15 @@ async def parse_csv(
     processor = InvestorProcessor()
 
     if is_investor == 1:
-        results = await processor.parse_investors(df)
+        # Manual parser with LLM currency conversion
+        results = await processor.parse_investors(df, save_to_db=True)
+        # Results are already dicts from the new parser
+        return results
     else:
-        results = await processor.parse_companies(df)
+        # Manual parser for companies (no LLM needed)
-
+        results = await processor.parse_companies(df, save_to_db=True)
-    # Convert Pydantic objects to dictionaries
+        # Results are already dicts from the new parser
-    return [r.model_dump() for r in results]
+        return results
 
 
 @app.post("/query", response_model=InvestorList, tags=["Querying"])

app/routers/investors.py

@@ -4,8 +4,11 @@ from db.db import get_db
 from db.models import InvestorTable, SectorTable
 from fastapi import APIRouter, Depends, HTTPException, Query
 from pydantic import BaseModel
-from schemas.router_schemas import InvestmentStage, InvestorData
+from schemas.router_schemas import (
-from services.querying import QueryProcessor
+    InvestmentStage,
+    InvestorData,
+    InvestorFundData,
+)
 from sqlalchemy.orm import Session, selectinload
 
 router = APIRouter(tags=["Investor Routes"])
@@ -34,34 +37,95 @@ class InvestorUpdate(BaseModel):
     number_of_investments: Optional[int] = None
 
 
-@router.get("/investors", response_model=List[InvestorData])
+@router.get("/investors", response_model=List[InvestorFundData])
 def read_investors(db: Session = Depends(get_db)):
-    """Get all investors with their related data"""
+    """Get all investors with their funds as separate entries
+
+    Each investor-fund combination is returned as a separate row.
+    An investor with 3 funds will appear as 3 entries.
+    """
     investors = (
         db.query(InvestorTable)
         .options(
             selectinload(InvestorTable.portfolio_companies),
             selectinload(InvestorTable.team_members),
             selectinload(InvestorTable.sectors),
+            selectinload(InvestorTable.funds),
         )
         .all()
     )
 
-    # Transform InvestorTable objects to InvestorData format
+    # Transform to InvestorFundData format (one row per investor-fund combination)
-    investor_data_list = []
+    investor_fund_list = []
     for investor in investors:
-        investor_data = InvestorData(
+        # If investor has funds, create one entry per fund
-            investor=investor,  # This maps to InvestorSchema
+        if investor.funds:
+            for fund in investor.funds:
+                investor_fund_data = InvestorFundData(
+                    # Investor fields
+                    investor_id=investor.id,
+                    investor_name=investor.name,
+                    investor_description=investor.description,
+                    investor_website=investor.website,
+                    investor_headquarters=investor.headquarters,
+                    aum=investor.aum,
+                    aum_as_of_date=investor.aum_as_of_date,
+                    aum_source_url=investor.aum_source_url,
+                    investment_thesis=investor.investment_thesis,
+                    portfolio_highlights=investor.portfolio_highlights,
+                    number_of_investments=investor.number_of_investments,
+                    # Fund fields
+                    fund_id=fund.id,
+                    fund_name=fund.fund_name,
+                    fund_size=fund.fund_size,
+                    fund_size_source_url=fund.fund_size_source_url,
+                    check_size_lower=fund.check_size_lower,
+                    check_size_upper=fund.check_size_upper,
+                    geographic_focus=fund.geographic_focus,
+                    fund_investment_stages=fund.investment_stages,  # Now a relationship
+                    fund_sectors=fund.sectors,  # Now a relationship
+                    # Related data (same for all funds of this investor)
                     portfolio_companies=investor.portfolio_companies,
                     team_members=investor.team_members,
                     sectors=investor.sectors,
                 )
-        investor_data_list.append(investor_data)
+                investor_fund_list.append(investor_fund_data)
+        else:
+            # If no funds, create one entry with null fund fields
+            investor_fund_data = InvestorFundData(
+                # Investor fields
+                investor_id=investor.id,
+                investor_name=investor.name,
+                investor_description=investor.description,
+                investor_website=investor.website,
+                investor_headquarters=investor.headquarters,
+                aum=investor.aum,
+                aum_as_of_date=investor.aum_as_of_date,
+                aum_source_url=investor.aum_source_url,
+                investment_thesis=investor.investment_thesis,
+                portfolio_highlights=investor.portfolio_highlights,
+                number_of_investments=investor.number_of_investments,
+                # Fund fields (null)
+                fund_id=None,
+                fund_name=None,
+                fund_size=None,
+                fund_size_source_url=None,
+                check_size_lower=None,
+                check_size_upper=None,
+                geographic_focus=None,
+                fund_investment_stages=None,
+                fund_sectors=None,
+                # Related data
+                portfolio_companies=investor.portfolio_companies,
+                team_members=investor.team_members,
+                sectors=investor.sectors,
+            )
+            investor_fund_list.append(investor_fund_data)
 
-    return investor_data_list
+    return investor_fund_list
 
 
-@router.get("/investors/filter", response_model=List[InvestorData])
+@router.get("/investors/filter", response_model=List[InvestorFundData])
 def filter_investors(
     stage: Optional[InvestmentStage] = Query(
         None, description="Filter by investment stage"
@@ -76,13 +140,18 @@ def filter_investors(
     max_aum: Optional[int] = Query(None, description="Maximum AUM"),
     db: Session = Depends(get_db),
 ):
-    """Filter investors based on various criteria"""
+    """Filter investors based on various criteria
+
+    Returns investor-fund combinations as separate rows.
+    An investor with 3 funds will appear as 3 entries.
+    """
 
     # Start with base query
     query = db.query(InvestorTable).options(
         selectinload(InvestorTable.portfolio_companies),
         selectinload(InvestorTable.team_members),
         selectinload(InvestorTable.sectors),
+        selectinload(InvestorTable.funds),
     )
 
     # Apply filters
@@ -112,29 +181,86 @@ def filter_investors(
 
     investors = query.all()
 
-    # Transform to InvestorData format
+    # Transform to InvestorFundData format (one row per investor-fund combination)
-    investor_data_list = []
+    investor_fund_list = []
     for investor in investors:
-        investor_data = InvestorData(
+        # If investor has funds, create one entry per fund
-            investor=investor,
+        if investor.funds:
+            for fund in investor.funds:
+                investor_fund_data = InvestorFundData(
+                    # Investor fields
+                    investor_id=investor.id,
+                    investor_name=investor.name,
+                    investor_description=investor.description,
+                    investor_website=investor.website,
+                    investor_headquarters=investor.headquarters,
+                    aum=investor.aum,
+                    aum_as_of_date=investor.aum_as_of_date,
+                    aum_source_url=investor.aum_source_url,
+                    investment_thesis=investor.investment_thesis,
+                    portfolio_highlights=investor.portfolio_highlights,
+                    number_of_investments=investor.number_of_investments,
+                    # Fund fields
+                    fund_id=fund.id,
+                    fund_name=fund.fund_name,
+                    fund_size=fund.fund_size,
+                    fund_size_source_url=fund.fund_size_source_url,
+                    check_size_lower=fund.check_size_lower,
+                    check_size_upper=fund.check_size_upper,
+                    geographic_focus=fund.geographic_focus,
+                    fund_investment_stages=fund.investment_stages,  # Now a relationship
+                    fund_sectors=fund.sectors,  # Now a relationship
+                    # Related data
                     portfolio_companies=investor.portfolio_companies,
                     team_members=investor.team_members,
                     sectors=investor.sectors,
                 )
-        investor_data_list.append(investor_data)
+                investor_fund_list.append(investor_fund_data)
+        else:
+            # If no funds, create one entry with null fund fields
+            investor_fund_data = InvestorFundData(
+                # Investor fields
+                investor_id=investor.id,
+                investor_name=investor.name,
+                investor_description=investor.description,
+                investor_website=investor.website,
+                investor_headquarters=investor.headquarters,
+                aum=investor.aum,
+                aum_as_of_date=investor.aum_as_of_date,
+                aum_source_url=investor.aum_source_url,
+                investment_thesis=investor.investment_thesis,
+                portfolio_highlights=investor.portfolio_highlights,
+                number_of_investments=investor.number_of_investments,
+                # Fund fields (null)
+                fund_id=None,
+                fund_name=None,
+                fund_size=None,
+                fund_size_source_url=None,
+                check_size_lower=None,
+                check_size_upper=None,
+                geographic_focus=None,
+                fund_investment_stages=None,
+                fund_sectors=None,
+                # Related data
+                portfolio_companies=investor.portfolio_companies,
+                team_members=investor.team_members,
+                sectors=investor.sectors,
+            )
+            investor_fund_list.append(investor_fund_data)
 
-    return investor_data_list
+    return investor_fund_list
 
 
 @router.get("/investors/{investor_id}", response_model=InvestorData)
 def read_investor(investor_id: int, db: Session = Depends(get_db)):
-    """Get a specific investor by ID"""
+    """Get a specific investor by ID with all their funds"""
     investor = (
         db.query(InvestorTable)
         .options(
             selectinload(InvestorTable.portfolio_companies),
             selectinload(InvestorTable.team_members),
             selectinload(InvestorTable.sectors),
+            selectinload(InvestorTable.funds),
         )
         .filter(InvestorTable.id == investor_id)
         .first()
@@ -143,12 +269,13 @@ def read_investor(investor_id: int, db: Session = Depends(get_db)):
     if not investor:
         raise HTTPException(status_code=404, detail="Investor not found")
 
-    # Transform to InvestorData format
+    # Transform to InvestorData format (includes funds array)
     return InvestorData(
         investor=investor,
         portfolio_companies=investor.portfolio_companies,
         team_members=investor.team_members,
         sectors=investor.sectors,
+        funds=investor.funds,
     )
 
 
@@ -167,6 +294,7 @@ def create_investor(investor: InvestorCreate, db: Session = Depends(get_db)):
             selectinload(InvestorTable.portfolio_companies),
             selectinload(InvestorTable.team_members),
             selectinload(InvestorTable.sectors),
+            selectinload(InvestorTable.funds),
         )
         .filter(InvestorTable.id == db_investor.id)
         .first()
@@ -178,16 +306,75 @@ def create_investor(investor: InvestorCreate, db: Session = Depends(get_db)):
         portfolio_companies=investor_with_relations.portfolio_companies,
         team_members=investor_with_relations.team_members,
         sectors=investor_with_relations.sectors,
+        funds=investor_with_relations.funds,
     )
 
 
-@router.get("/investors/{investor_id}/similar", response_model=List[InvestorData])
+@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),
+            selectinload(InvestorTable.funds),
+        )
+        .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,
+        funds=investor_with_relations.funds,
+    )
+
+
+@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[InvestorFundData])
 def find_similar_investors(
     investor_id: int,
     limit: int = Query(10, description="Maximum number of similar investors to return"),
-    db: Session = Depends(get_db)
+    db: Session = Depends(get_db),
 ):
-    """Find investors similar to a given investor based on characteristics"""
+    """Find investors similar to a given investor based on characteristics
+
+    Returns investor-fund combinations as separate rows.
+    """
 
     # Get the target investor
     target_investor = (
@@ -196,6 +383,7 @@ def find_similar_investors(
             selectinload(InvestorTable.portfolio_companies),
             selectinload(InvestorTable.team_members),
             selectinload(InvestorTable.sectors),
+            selectinload(InvestorTable.funds),
         )
         .filter(InvestorTable.id == investor_id)
         .first()
@@ -214,6 +402,7 @@ def find_similar_investors(
             selectinload(InvestorTable.portfolio_companies),
             selectinload(InvestorTable.team_members),
             selectinload(InvestorTable.sectors),
+            selectinload(InvestorTable.funds),
         )
         .filter(InvestorTable.id != investor_id)
         .all()
@@ -230,21 +419,38 @@ def find_similar_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():
+            if (
+                candidate.geographic_focus.lower()
+                == target_investor.geographic_focus.lower()
+            ):
                 score += 20
-            elif (candidate.geographic_focus.lower() in target_investor.geographic_focus.lower() or
+            elif (
-                  target_investor.geographic_focus.lower() in candidate.geographic_focus.lower()):
+                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 
+        if (
-            target_investor.check_size_lower and target_investor.check_size_upper):
+            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_start = max(
-            overlap_end = min(candidate.check_size_upper, target_investor.check_size_upper)
+                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
+                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)
 
@@ -269,13 +475,71 @@ def find_similar_investors(
     scored_investors.sort(key=lambda x: x[0], reverse=True)
     similar_investors = [inv for score, inv in scored_investors[:limit]]
 
-    # Transform to InvestorData format
+    # Transform to InvestorFundData format (one row per investor-fund combination)
-    return [
+    investor_fund_list = []
-        InvestorData(
+    for investor in similar_investors:
-            investor=inv,
+        # If investor has funds, create one entry per fund
-            portfolio_companies=inv.portfolio_companies,
+        if investor.funds:
-            team_members=inv.team_members,
+            for fund in investor.funds:
-            sectors=inv.sectors,
+                investor_fund_data = InvestorFundData(
+                    # Investor fields
+                    investor_id=investor.id,
+                    investor_name=investor.name,
+                    investor_description=investor.description,
+                    investor_website=investor.website,
+                    investor_headquarters=investor.headquarters,
+                    aum=investor.aum,
+                    aum_as_of_date=investor.aum_as_of_date,
+                    aum_source_url=investor.aum_source_url,
+                    investment_thesis=investor.investment_thesis,
+                    portfolio_highlights=investor.portfolio_highlights,
+                    number_of_investments=investor.number_of_investments,
+                    # Fund fields
+                    fund_id=fund.id,
+                    fund_name=fund.fund_name,
+                    fund_size=fund.fund_size,
+                    fund_size_source_url=fund.fund_size_source_url,
+                    check_size_lower=fund.check_size_lower,
+                    check_size_upper=fund.check_size_upper,
+                    geographic_focus=fund.geographic_focus,
+                    fund_investment_stages=fund.investment_stages,  # Now a relationship
+                    fund_sectors=fund.sectors,  # Now a relationship
+                    # Related data
+                    portfolio_companies=investor.portfolio_companies,
+                    team_members=investor.team_members,
+                    sectors=investor.sectors,
                 )
-        for inv in similar_investors
+                investor_fund_list.append(investor_fund_data)
-    ]
+        else:
+            # If no funds, create one entry with null fund fields
+            investor_fund_data = InvestorFundData(
+                # Investor fields
+                investor_id=investor.id,
+                investor_name=investor.name,
+                investor_description=investor.description,
+                investor_website=investor.website,
+                investor_headquarters=investor.headquarters,
+                aum=investor.aum,
+                aum_as_of_date=investor.aum_as_of_date,
+                aum_source_url=investor.aum_source_url,
+                investment_thesis=investor.investment_thesis,
+                portfolio_highlights=investor.portfolio_highlights,
+                number_of_investments=investor.number_of_investments,
+                # Fund fields (null)
+                fund_id=None,
+                fund_name=None,
+                fund_size=None,
+                fund_size_source_url=None,
+                check_size_lower=None,
+                check_size_upper=None,
+                geographic_focus=None,
+                fund_investment_stages=None,
+                fund_sectors=None,
+                # Related data
+                portfolio_companies=investor.portfolio_companies,
+                team_members=investor.team_members,
+                sectors=investor.sectors,
+            )
+            investor_fund_list.append(investor_fund_data)
+
+    return investor_fund_list

app/schemas/py_schemas.py

@@ -258,10 +258,6 @@ class InvestorSchema(BaseModel):
         default=None,
         description="Geographic investment focus. Do not return any special characters, Just locations separated by commas. Leave empty if not clearly identifiable.",
     )
-    stage_focus: InvestmentStage = Field(
-        default=InvestmentStage.SEED,
-        description="Investment stage focus. Use SEED as default if uncertain.",
-    )
     number_of_investments: Optional[int] = Field(
         default=None,
         ge=0,

app/schemas/router_schemas.py

@@ -22,6 +22,14 @@ class SectorSchema(BaseModel):
         from_attributes = True
 
 
+class InvestmentStageSchema(BaseModel):
+    id: int
+    name: str
+
+    class Config:
+        from_attributes = True
+
+
 class InvestorMemberSchema(BaseModel):
     id: int
     name: str
@@ -32,6 +40,25 @@ class InvestorMemberSchema(BaseModel):
         from_attributes = True
 
 
+class FundSchema(BaseModel):
+    id: int
+    fund_name: str | None
+    fund_size: int | None  # Changed to int for numerical filtering
+    fund_size_source_url: str | None
+    check_size_lower: int | None  # NEW: Lower bound of check size range
+    check_size_upper: int | None  # NEW: Upper bound of check size range
+    source_url: str | None
+    source_provider: str | None
+    geographic_focus: str | None  # Changed from List[str] to string
+    investment_stages: List[InvestmentStageSchema] | None  # Changed to relationship
+    sectors: List[SectorSchema] | None  # Changed to relationship
+    created_at: Optional[datetime] = None
+    updated_at: Optional[datetime] = None
+
+    class Config:
+        from_attributes = True
+
+
 class CompanyMemberSchema(BaseModel):
     id: int
     name: Optional[str]
@@ -76,12 +103,55 @@ class InvestorSchema(BaseModel):
 
 
 class InvestorData(BaseModel):
-    """Comprehensive investor data schema for LLM processing"""
+    """Comprehensive investor data schema - used for individual investor requests"""
 
     investor: InvestorSchema
     portfolio_companies: List[CompanySchema]
     team_members: List[InvestorMemberSchema]
     sectors: List[SectorSchema]
+    funds: List[FundSchema]
+
+    class Config:
+        from_attributes = True
+
+
+class InvestorFundData(BaseModel):
+    """Investor-Fund combined data - used for list/filter requests
+
+    Each row represents one investor-fund combination.
+    An investor with 3 funds will appear as 3 separate entries.
+    """
+
+    # Investor fields
+    investor_id: int
+    investor_name: str
+    investor_description: Optional[str]
+    investor_website: Optional[str]
+    investor_headquarters: Optional[str]
+    aum: int | None
+    aum_as_of_date: str | None
+    aum_source_url: str | None
+    investment_thesis: List[str] | None
+    portfolio_highlights: List[str] | None
+    number_of_investments: int | None
+
+    # Fund fields
+    fund_id: int | None
+    fund_name: str | None
+    fund_size: int | None  # Changed to int for numerical filtering
+    fund_size_source_url: str | None
+    check_size_lower: int | None  # NEW: Lower bound of check size range
+    check_size_upper: int | None  # NEW: Upper bound of check size range
+    geographic_focus: str | None  # Changed from List[str] to string
+    fund_investment_stages: (
+        List[InvestmentStageSchema] | None
+    )  # Changed to relationship
+    fund_sectors: List[SectorSchema] | None  # Changed to relationship
+
+    # Related data
+    portfolio_companies: List[CompanySchema]
+    team_members: List[InvestorMemberSchema]
+    sectors: List[SectorSchema]
 
     class Config:
         from_attributes = True
@@ -99,3 +169,9 @@ class CompanyData(BaseModel):  # Renamed from CompaniesData for consistency
 
 class InvestorList(BaseModel):
     investors: List[InvestorData]
+
+
+class InvestorFundList(BaseModel):
+    """List of investor-fund combinations"""
+
+    investor_funds: List[InvestorFundData]

app/services/llm_parser.py

@@ -1,5 +1,6 @@
-import asyncio
+import json
 import os
+import re
 from typing import Optional
 
 import pandas as pd
@@ -7,15 +8,35 @@ from db.db import get_db_session
 from db.models import (
     CompanyMember,
     CompanyTable,
+    FundTable,
+    InvestmentStageTable,
     InvestorMember,
     InvestorTable,
     SectorTable,
 )
 from langchain_openai import ChatOpenAI
+from pydantic import BaseModel
 from schemas.py_schemas import CompanyData, InvestorData
 from sqlalchemy.orm import Session
 
 
+class CurrencyConversion(BaseModel):
+    """Schema for LLM currency conversion responses"""
+
+    amount_usd: int = 0
+    confidence: str = "high"  # high, medium, low
+    notes: str = ""
+
+
+class CheckSizeRange(BaseModel):
+    """Schema for LLM check size range parsing from estimated investment size"""
+
+    lower_bound_usd: int = 0
+    upper_bound_usd: int = 0
+    confidence: str = "high"  # high, medium, low
+    notes: str = ""
+
+
 class InvestorProcessor:
     def __init__(self):
         self.llm = ChatOpenAI(
@@ -25,9 +46,508 @@ class InvestorProcessor:
             temperature=0,
         )
 
+        # Structured LLMs for specific parsing tasks
+        self.currency_converter_llm = self.llm.with_structured_output(
+            CurrencyConversion
+        )
+        self.check_size_parser_llm = self.llm.with_structured_output(CheckSizeRange)
+
+        # Keep legacy structured LLMs for backward compatibility
         self.investor_structured_llm = self.llm.with_structured_output(InvestorData)
         self.company_structured_llm = self.llm.with_structured_output(CompanyData)
 
+    async def convert_to_usd(self, amount_str: str) -> Optional[int]:
+        """
+        Use LLM to convert currency amounts to USD integers.
+        Handles formats like:
+        - "EUR 850,000,000"
+        - "$5M"
+        - "GBP 10-20 million"
+        - "Approximately EUR 100 million"
+        """
+        if not amount_str or amount_str == "Not Available" or amount_str == "0":
+            return None
+
+        try:
+            prompt = f"""Convert this amount to USD as an integer (whole number, no decimals).
+If it's a range, use the midpoint. If already in USD, just extract the number.
+Remove all commas and convert millions/billions to actual numbers.
+
+Amount: {amount_str}
+
+Examples:
+- "EUR 850,000,000" -> 935000000 (assuming EUR to USD rate ~1.10)
+- "$5M" -> 5000000
+- "GBP 10-20 million" -> 18000000 (midpoint 15M * 1.20 rate)
+- "Approximately EUR 100 million" -> 110000000
+
+Return only the USD integer amount with current exchange rates."""
+
+            result = await self.currency_converter_llm.ainvoke(prompt)
+            return result.amount_usd if result.amount_usd > 0 else None
+        except Exception as e:
+            print(f"Error converting currency '{amount_str}': {e}")
+            return None
+
+    async def parse_check_size_range(
+        self, estimated_investment_str: str
+    ) -> tuple[Optional[int], Optional[int]]:
+        """
+        Use LLM to parse check size range from estimated investment size string.
+        Returns tuple of (lower_bound_usd, upper_bound_usd).
+
+        Handles formats like:
+        - "EUR 1,000 to 2,000"
+        - "$100K-$500K"
+        - "Between $1M and $5M"
+        - "Up to EUR 10 million"
+        - "$2M typical"
+        """
+        if (
+            not estimated_investment_str
+            or estimated_investment_str == "Not Available"
+            or estimated_investment_str == "0"
+        ):
+            return None, None
+
+        try:
+            prompt = f"""Parse this check size/investment range into lower and upper bounds in USD as integers.
+
+Input: {estimated_investment_str}
+
+Instructions:
+- If it's a range (e.g., "EUR 1M to 5M"), extract both bounds
+- If it's a single amount (e.g., "$2M typical"), use it as both lower and upper
+- If it says "up to X", use 0 as lower and X as upper
+- Convert all currencies to USD using current exchange rates
+- Return integers (whole numbers, no decimals)
+
+Examples:
+- "EUR 1,000 to 2,000" -> lower: 1100, upper: 2200
+- "$100K-$500K" -> lower: 100000, upper: 500000
+- "Between $1M and $5M" -> lower: 1000000, upper: 5000000
+- "Up to EUR 10 million" -> lower: 0, upper: 11000000
+- "$2M typical" -> lower: 2000000, upper: 2000000
+- "GBP 500K-2M" -> lower: 600000, upper: 2400000
+
+Return the lower and upper bounds in USD."""
+
+            result = await self.check_size_parser_llm.ainvoke(prompt)
+            lower = result.lower_bound_usd if result.lower_bound_usd > 0 else None
+            upper = result.upper_bound_usd if result.upper_bound_usd > 0 else None
+            return lower, upper
+        except Exception as e:
+            print(f"Error parsing check size range '{estimated_investment_str}': {e}")
+            return None, None
+
+    def parse_json_profile(self, json_str: str) -> Optional[dict]:
+        """
+        Manually parse the JSON profile from the CSV.
+        Returns a cleaned dictionary with the investor profile data.
+        """
+        if not json_str or pd.isna(json_str):
+            return None
+
+        try:
+            # Parse JSON string
+            profile = json.loads(json_str)
+            return profile
+        except json.JSONDecodeError as e:
+            print(f"Error parsing JSON: {e}")
+            return None
+
+    async def process_investor_profile(
+        self, name: str, website: str, profile_json: str
+    ) -> Optional[dict]:
+        """
+        Process investor profile from CSV data.
+        Manually extracts fields and uses LLM only for currency conversion.
+        """
+        profile = self.parse_json_profile(profile_json)
+        if not profile:
+            return None
+
+        try:
+            # Extract basic info
+            investor_data = {
+                "name": name.strip() if name else None,
+                "website": website.strip() if website else None,
+                "headquarters": profile.get("headquarters"),
+                "description": profile.get("investorDescription"),
+                "aum": None,
+                "aum_as_of_date": None,
+                "aum_source_url": None,
+                "investment_thesis": profile.get("investmentThesisFocus", []),
+                "portfolio_highlights": profile.get("portfolioHighlights", []),
+                "linked_documents": profile.get("linkedDocuments", []),
+                "researcher_notes": profile.get("researcherNotes"),
+                "missing_important_fields": profile.get("missingImportantFields", []),
+                "sources": profile.get("sources", {}),
+                "team_members": [],
+                "funds": [],
+            }
+
+            # Process AUM
+            aum_data = profile.get("overallAssetsUnderManagement", {})
+            if aum_data and isinstance(aum_data, dict):
+                aum_amount = aum_data.get("aumAmount")
+                if aum_amount and aum_amount != "Not Available":
+                    # Convert AUM to USD integer
+                    aum_usd = await self.convert_to_usd(aum_amount)
+                    investor_data["aum"] = aum_usd
+                    investor_data["aum_as_of_date"] = aum_data.get("asOfDate")
+                    investor_data["aum_source_url"] = aum_data.get("sourceUrl")
+
+            # Process senior leadership
+            senior_leadership = profile.get("seniorLeadership", [])
+            for member in senior_leadership:
+                if isinstance(member, dict) and member.get("name"):
+                    investor_data["team_members"].append(
+                        {
+                            "name": member.get("name"),
+                            "title": member.get("title"),
+                            "role": member.get("title"),  # Use title as role
+                            "email": None,
+                            "source_url": member.get("sourceUrl"),
+                        }
+                    )
+
+            # Process funds
+            funds = profile.get("funds", [])
+            for fund in funds:
+                if isinstance(fund, dict):
+                    fund_data = {
+                        "fund_name": fund.get("fundName"),
+                        "fund_size": None,
+                        "fund_size_source_url": fund.get("fundSizeSourceUrl"),
+                        "check_size_lower": None,
+                        "check_size_upper": None,
+                        "source_url": fund.get("sourceUrl"),
+                        "source_provider": fund.get("sourceProvider"),
+                        "geographic_focus": None,  # Will be converted to string
+                        "investment_stage_names": fund.get("investmentStageFocus", []),
+                        "sector_names": fund.get("sectorFocus", []),
+                    }
+
+                    # Convert geographic focus from array to comma-separated string
+                    geo_focus = fund.get("geographicFocus", [])
+                    if geo_focus and isinstance(geo_focus, list):
+                        fund_data["geographic_focus"] = ", ".join(geo_focus)
+
+                    # Convert fund size to USD integer
+                    fund_size_str = fund.get("fundSize")
+                    if fund_size_str and fund_size_str != "Not Available":
+                        fund_size_usd = await self.convert_to_usd(fund_size_str)
+                        if fund_size_usd:
+                            fund_data["fund_size"] = fund_size_usd  # Store as integer
+
+                    # Parse check size range from estimated investment size
+                    est_size_str = fund.get("estimatedInvestmentSize")
+                    if est_size_str and est_size_str != "Not Available":
+                        check_lower, check_upper = await self.parse_check_size_range(
+                            est_size_str
+                        )
+                        if check_lower is not None:
+                            fund_data["check_size_lower"] = check_lower
+                        if check_upper is not None:
+                            fund_data["check_size_upper"] = check_upper
+
+                    investor_data["funds"].append(fund_data)
+
+            return investor_data
+
+        except Exception as e:
+            print(f"Error processing investor profile for {name}: {e}")
+            return None
+
+    async def process_company_profile(
+        self, name: str, website: str, profile_json: str, investor_names: str = None
+    ) -> Optional[dict]:
+        """
+        Process company profile from CSV data.
+        Manually extracts fields without using LLM.
+        """
+        profile = self.parse_json_profile(profile_json)
+        if not profile:
+            return None
+
+        try:
+            # Extract basic info
+            company_data = {
+                "name": name.strip() if name else None,
+                "website": website.strip() if website else 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:
+                # Try alternative field names
+                key_executives = profile.get("seniorLeadership", [])
+
+            for exec_member in key_executives:
+                if isinstance(exec_member, dict) and exec_member.get("name"):
+                    company_data["key_executives"].append(
+                        {
+                            "name": exec_member.get("name"),
+                            "title": exec_member.get("title"),
+                            "source_url": exec_member.get("sourceUrl"),
+                        }
+                    )
+
+            # Try to extract founding year from description
+            description = company_data.get("description", "")
+            if description:
+                # Look for patterns like "founded in 2020", "Gegründet 2020", "founded 2020"
+                year_patterns = [
+                    r"founded in (\d{4})",
+                    r"founded (\d{4})",
+                    r"Gegründet (\d{4})",
+                    r"established in (\d{4})",
+                    r"since (\d{4})",
+                    r"\((\d{4})\)",  # Year in parentheses
+                ]
+                for pattern in year_patterns:
+                    match = re.search(pattern, description, re.IGNORECASE)
+                    if match:
+                        try:
+                            year = int(match.group(1))
+                            if 1900 <= year <= 2025:  # Sanity check
+                                company_data["founded_year"] = year
+                                break
+                        except Exception:
+                            continue
+
+            return company_data
+
+        except Exception as e:
+            print(f"Error processing company profile for {name}: {e}")
+            return None
+
+    def _save_parsed_company_to_db(
+        self, db: Session, company_data: dict
+    ) -> Optional[CompanyTable]:
+        """Save manually parsed company data to database"""
+        try:
+            # Check if company already exists
+            existing_company = (
+                db.query(CompanyTable).filter_by(name=company_data["name"]).first()
+            )
+
+            if existing_company:
+                # Update 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 = CompanyTable(
+                    name=company_data["name"],
+                    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)
+                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()
+
+            for exec_data in company_data.get("key_executives", []):
+                member = CompanyMember(
+                    name=exec_data.get("name"),
+                    role=exec_data.get("title"),
+                    linkedin=exec_data.get(
+                        "source_url"
+                    ),  # Store source URL in linkedin field
+                    company_id=company.id,
+                )
+                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:
+            print(f"Error saving company to database: {e}")
+            db.rollback()
+            return None
+
+    def _save_parsed_investor_to_db(
+        self, db: Session, investor_data: dict
+    ) -> Optional[InvestorTable]:
+        """Save manually parsed investor data to database"""
+        try:
+            # Check if investor already exists
+            existing_investor = (
+                db.query(InvestorTable).filter_by(name=investor_data["name"]).first()
+            )
+
+            if existing_investor:
+                # Update existing investor
+                investor = existing_investor
+                investor.website = investor_data.get("website") or investor.website
+                investor.headquarters = (
+                    investor_data.get("headquarters") or investor.headquarters
+                )
+                investor.description = (
+                    investor_data.get("description") or investor.description
+                )
+                investor.aum = investor_data.get("aum") or investor.aum
+                investor.aum_as_of_date = (
+                    investor_data.get("aum_as_of_date") or investor.aum_as_of_date
+                )
+                investor.aum_source_url = (
+                    investor_data.get("aum_source_url") or investor.aum_source_url
+                )
+                investor.investment_thesis = (
+                    investor_data.get("investment_thesis") or investor.investment_thesis
+                )
+                investor.portfolio_highlights = (
+                    investor_data.get("portfolio_highlights")
+                    or investor.portfolio_highlights
+                )
+                investor.linked_documents = (
+                    investor_data.get("linked_documents") or investor.linked_documents
+                )
+                investor.researcher_notes = (
+                    investor_data.get("researcher_notes") or investor.researcher_notes
+                )
+                investor.missing_important_fields = (
+                    investor_data.get("missing_important_fields")
+                    or investor.missing_important_fields
+                )
+                investor.sources = investor_data.get("sources") or investor.sources
+            else:
+                # Create new investor
+                investor = InvestorTable(
+                    name=investor_data["name"],
+                    website=investor_data.get("website"),
+                    headquarters=investor_data.get("headquarters"),
+                    description=investor_data.get("description"),
+                    aum=investor_data.get("aum"),
+                    aum_as_of_date=investor_data.get("aum_as_of_date"),
+                    aum_source_url=investor_data.get("aum_source_url"),
+                    investment_thesis=investor_data.get("investment_thesis"),
+                    portfolio_highlights=investor_data.get("portfolio_highlights"),
+                    linked_documents=investor_data.get("linked_documents"),
+                    researcher_notes=investor_data.get("researcher_notes"),
+                    missing_important_fields=investor_data.get(
+                        "missing_important_fields"
+                    ),
+                    sources=investor_data.get("sources"),
+                )
+                db.add(investor)
+                db.flush()
+
+            # Add/update team members
+            # First, remove existing team members if updating
+            if existing_investor:
+                db.query(InvestorMember).filter_by(investor_id=investor.id).delete()
+
+            for member_data in investor_data.get("team_members", []):
+                member = InvestorMember(
+                    name=member_data.get("name"),
+                    role=member_data.get("role"),
+                    title=member_data.get("title"),
+                    email=member_data.get("email"),
+                    source_url=member_data.get("source_url"),
+                    investor_id=investor.id,
+                )
+                db.add(member)
+
+            # Add/update funds
+            # First, remove existing funds if updating
+            if existing_investor:
+                db.query(FundTable).filter_by(investor_id=investor.id).delete()
+
+            for fund_data in investor_data.get("funds", []):
+                fund = FundTable(
+                    investor_id=investor.id,
+                    fund_name=fund_data.get("fund_name"),
+                    fund_size=fund_data.get("fund_size"),  # Now an integer
+                    fund_size_source_url=fund_data.get("fund_size_source_url"),
+                    check_size_lower=fund_data.get("check_size_lower"),
+                    check_size_upper=fund_data.get("check_size_upper"),
+                    source_url=fund_data.get("source_url"),
+                    source_provider=fund_data.get("source_provider"),
+                    geographic_focus=fund_data.get("geographic_focus"),  # Now a string
+                )
+                db.add(fund)
+                db.flush()  # Get the fund ID
+
+                # Add investment stages (many-to-many)
+                for stage_name in fund_data.get("investment_stage_names", []):
+                    stage = self._get_or_create_investment_stage(db, stage_name)
+                    fund.investment_stages.append(stage)
+
+                # Add sectors (many-to-many)
+                for sector_name in fund_data.get("sector_names", []):
+                    sector = self._get_or_create_sector(db, sector_name)
+                    fund.sectors.append(sector)
+
+            return investor
+
+        except Exception as e:
+            print(f"Error saving investor to database: {e}")
+            db.rollback()
+            return None
+
+    def _get_or_create_investment_stage(
+        self, db: Session, stage_name: str
+    ) -> InvestmentStageTable:
+        """Get existing investment stage or create new one"""
+        from db.models import InvestmentStageTable
+
+        stage = (
+            db.query(InvestmentStageTable)
+            .filter(InvestmentStageTable.name == stage_name)
+            .first()
+        )
+        if not stage:
+            stage = InvestmentStageTable(name=stage_name)
+            db.add(stage)
+            db.flush()  # Get the ID without committing
+        return stage
+
     def _get_or_create_sector(self, db: Session, sector_name: str) -> SectorTable:
         """Get existing sector or create new one"""
         sector = db.query(SectorTable).filter(SectorTable.name == sector_name).first()
@@ -49,7 +569,6 @@ class InvestorProcessor:
             check_size_lower=investor_data.investor.check_size_lower,
             check_size_upper=investor_data.investor.check_size_upper,
             geographic_focus=investor_data.investor.geographic_focus,
-            stage_focus=investor_data.investor.stage_focus,
             number_of_investments=investor_data.investor.number_of_investments,
         )
         db.add(investor)
@@ -173,141 +692,219 @@ class InvestorProcessor:
             print(f"Error processing row {row_idx + 1}: {e}")
             return None
 
-    async def parse_investors(self, df, save_to_db: bool = True):
+    async def parse_investors(self, df: pd.DataFrame, save_to_db: bool = True):
-        """Parse investors from DataFrame and optionally save to database"""
+        """
-        investors = []
+        Parse investors from DataFrame using manual JSON parsing and LLM for currency conversion.
-        df = df[20:]
+        Expected CSV columns: Name, Website, Final Investor Profile, Final Profile sourcing
+        """
+        results = []
         db = None
         if save_to_db:
             db = get_db_session()
 
         try:
-            # Process rows in batches asynchronously
+            total_rows = len(df)
-            batch_size = 20  # Adjust batch size as needed
+            print(f"\n🚀 Starting to process {total_rows} investors...")
-            rows = [(idx, row) for idx, row in df.iterrows()]
 
-            for i in range(0, len(rows), batch_size):
+            for idx, row in df.iterrows():
-                batch = rows[i : i + batch_size]
+                try:
+                    name = (
+                        row.get("Name", "").strip()
+                        if pd.notna(row.get("Name"))
+                        else None
+                    )
+                    website = (
+                        row.get("Website", "").strip()
+                        if pd.notna(row.get("Website"))
+                        else None
+                    )
+                    profile_json = (
+                        row.get("Final Investor Profile", "")
+                        if pd.notna(row.get("Final Investor Profile"))
+                        else None
+                    )
 
-                # Process batch asynchronously
+                    if not name or not profile_json:
-                tasks = [
+                        print(f"⚠️  Row {idx + 1}: Skipping - missing name or profile")
-                    self._process_row(row, idx, is_investor=True) for idx, row in batch
-                ]
-
-                batch_results = await asyncio.gather(*tasks, return_exceptions=True)
-
-                # Handle results from batch
-                for (idx, row), result in zip(batch, batch_results):
-                    if isinstance(result, Exception):
-                        print(f"Error processing row {idx}: {result}")
-                        if db:
-                            db.rollback()
                         continue
 
-                    if result:
+                    print(f"\n📊 Processing {idx + 1}/{total_rows}: {name}")
-                        # Convert dict to InvestorData if needed
-                        if isinstance(result, dict):
-                            investor_data = InvestorData(**result)
-                        else:
-                            investor_data = result
 
-                        investors.append(investor_data)
+                    # Process the investor profile
+                    investor_data = await self.process_investor_profile(
+                        name, website, profile_json
+                    )
 
-                        # Save to database if requested
+                    if investor_data:
+                        results.append(investor_data)
+                        print("   ✓ Parsed successfully")
+                        print(f"   - HQ: {investor_data.get('headquarters')}")
+                        print(
+                            f"   - AUM: ${investor_data.get('aum'):,}"
+                            if investor_data.get("aum")
+                            else "   - AUM: Not Available"
+                        )
+                        print(f"   - Funds: {len(investor_data.get('funds', []))}")
+                        print(
+                            f"   - Team: {len(investor_data.get('team_members', []))}"
+                        )
+
+                        # Save to database
                         if save_to_db and db:
                             try:
-                                saved_investor = self._save_investor_to_db(
+                                saved_investor = self._save_parsed_investor_to_db(
                                     db, investor_data
                                 )
+                                if saved_investor:
                                     db.commit()
                                     print(
-                                    f"✅ Saved investor '{saved_investor.name}' to database"
+                                        f"   ✅ Saved to database (ID: {saved_investor.id})"
                                     )
+                                else:
+                                    print("   ❌ Failed to save to database")
                             except Exception as e:
                                 db.rollback()
-                                print(f"❌ Failed to save investor to database: {e}")
+                                print(f"   ❌ Database error: {e}")
+                    else:
+                        print("   ⚠️  Failed to process profile")
 
-                print(
+                    # Commit every 10 investors to avoid memory issues
-                    f"Completed batch {i // batch_size + 1} of {(len(rows) + batch_size - 1) // batch_size}"
+                    if save_to_db and db and (idx + 1) % 10 == 0:
-                )
+                        db.commit()
+                        print(f"\n💾 Committed batch at row {idx + 1}")
 
                 except Exception as e:
-            print(f"Error in batch processing: {e}")
+                    print(f"❌ Error processing row {idx + 1}: {e}")
+                    if db:
+                        db.rollback()
+                    continue
+
+            # Final commit
+            if save_to_db and db:
+                db.commit()
+                print("\n✅ Final commit completed")
+
+        except Exception as e:
+            print(f"❌ Fatal error in parse_investors: {e}")
             if db:
                 db.rollback()
         finally:
             if db:
                 db.close()
 
-        return investors
+        print(f"\n🎉 Completed! Processed {len(results)}/{total_rows} investors")
+        return results
 
-    async def parse_companies(self, df, save_to_db: bool = True):
+    async def parse_companies(self, df: pd.DataFrame, save_to_db: bool = True):
-        """Parse companies from DataFrame and optionally save to database"""
+        """
-        companies = []
+        Parse companies from DataFrame using manual JSON parsing.
-        df = df[20:]
+        Expected CSV columns: Name, Website, Investor, Final Investor Profile (actually company profile)
+        """
+        results = []
         db = None
         if save_to_db:
             db = get_db_session()
 
         try:
-            # Process rows in batches asynchronously
+            total_rows = len(df)
-            batch_size = 20  # Adjust batch size as needed
+            print(f"\n🚀 Starting to process {total_rows} companies...")
-            rows = [(idx, row) for idx, row in df.iterrows()]
 
-            for i in range(0, len(rows), batch_size):
+            for idx, row in df.iterrows():
-                batch = rows[i : i + batch_size]
+                try:
+                    name = (
+                        row.get("Name", "").strip()
+                        if pd.notna(row.get("Name"))
+                        else None
+                    )
+                    website = (
+                        row.get("Website", "").strip()
+                        if pd.notna(row.get("Website"))
+                        else None
+                    )
+                    investor_names = (
+                        row.get("Investor", "").strip()
+                        if pd.notna(row.get("Investor"))
+                        else None
+                    )
+                    profile_json = (
+                        row.get("Final Investor Profile", "")
+                        if pd.notna(row.get("Final Investor Profile"))
+                        else None
+                    )
 
-                # Process batch asynchronously
+                    if not name or not profile_json:
-                tasks = [
+                        print(f"⚠️  Row {idx + 1}: Skipping - missing name or profile")
-                    self._process_row(row, idx, is_investor=False) for idx, row in batch
+                        continue
-                ]
 
-                batch_results = await asyncio.gather(*tasks, return_exceptions=True)
+                    print(f"\n📊 Processing {idx + 1}/{total_rows}: {name}")
 
-                # Handle results from batch
+                    # Process the company profile
-                for (idx, row), result in zip(batch, batch_results):
+                    company_data = await self.process_company_profile(
-                    if isinstance(result, Exception):
+                        name, website, profile_json, investor_names
-                        print(f"Error processing row {idx}: {result}")
+                    )
+
+                    if company_data:
+                        results.append(company_data)
+                        print("   ✓ Parsed successfully")
+                        print(f"   - Location: {company_data.get('location')}")
+                        print(f"   - Industry: {company_data.get('industry')}")
+                        print(
+                            f"   - Founded: {company_data.get('founded_year')}"
+                            if company_data.get("founded_year")
+                            else "   - Founded: Unknown"
+                        )
+                        print(
+                            f"   - Executives: {len(company_data.get('key_executives', []))}"
+                        )
+                        print(
+                            f"   - Investors: {len(company_data.get('investor_names', []))}"
+                        )
+
+                        # Save to database
+                        if save_to_db and db:
+                            try:
+                                saved_company = self._save_parsed_company_to_db(
+                                    db, company_data
+                                )
+                                if saved_company:
+                                    db.commit()
+                                    print(
+                                        f"   ✅ Saved to database (ID: {saved_company.id})"
+                                    )
+                                else:
+                                    print("   ❌ Failed to save to database")
+                            except Exception as e:
+                                db.rollback()
+                                print(f"   ❌ Database error: {e}")
+                    else:
+                        print("   ⚠️  Failed to process profile")
+
+                    # Commit every 10 companies to avoid memory issues
+                    if save_to_db and db and (idx + 1) % 10 == 0:
+                        db.commit()
+                        print(f"\n💾 Committed batch at row {idx + 1}")
+
+                except Exception as e:
+                    print(f"❌ Error processing row {idx + 1}: {e}")
                     if db:
                         db.rollback()
                     continue
 
-                    if result:
+            # Final commit
-                        # Convert dict to CompanyData if needed
-                        if isinstance(result, dict):
-                            company_data = CompanyData(**result)
-                        else:
-                            company_data = result
-
-                        companies.append(company_data)
-
-                        # Save to database if requested
             if save_to_db and db:
-                            try:
-                                saved_company = self._save_company_to_db(
-                                    db, company_data
-                                )
                 db.commit()
-                                print(
+                print("\n✅ Final commit completed")
-                                    f"✅ Saved company '{saved_company.name}' to database"
-                                )
-                            except Exception as e:
-                                db.rollback()
-                                print(f"❌ Failed to save company to database: {e}")
-
-                    print(
-                        f"Completed batch {i // batch_size + 1} of {(len(rows) + batch_size - 1) // batch_size}"
-                    )
 
         except Exception as e:
-            print(f"Error processing row {idx}: {e}")
+            print(f"❌ Fatal error in parse_companies: {e}")
             if db:
                 db.rollback()
         finally:
             if db:
                 db.close()
 
-        return companies
+        print(f"\n🎉 Completed! Processed {len(results)}/{total_rows} companies")
+        return results
 
 
 # async def main():

app/services/querying.py

@@ -95,6 +95,7 @@ class QueryProcessor:
                     selectinload(InvestorTable.portfolio_companies),
                     selectinload(InvestorTable.team_members),
                     selectinload(InvestorTable.sectors),
+                    selectinload(InvestorTable.funds),
                 )
                 .filter(InvestorTable.id.in_(investor_ids))
             )
@@ -109,6 +110,7 @@ class QueryProcessor:
                     portfolio_companies=investor.portfolio_companies,
                     team_members=investor.team_members,
                     sectors=investor.sectors,
+                    funds=investor.funds,
                 )
                 investor_data_list.append(investor_data)
 

base_db_generator/main.py

@@ -0,0 +1,315 @@
+import logging
+import re
+import unicodedata
+
+import pandas as pd
+from models import CompanyTable, InvestorTable, SectorTable, engine, init_database
+from sqlalchemy.orm import sessionmaker
+
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Import the schema
+init_database()
+
+
+# ===================== Ingesting Original Data =====================#
+def parse_investor_names(investor_names_str):
+    """Parse comma-separated investor names and return a list"""
+    if pd.isna(investor_names_str) or investor_names_str == "":
+        return []
+
+    # Split by comma and clean whitespace
+    # investors = [name.strip() for name in str(investor_names_str).split(",")]
+    investors = [
+        clean_name(name.strip()) for name in str(investor_names_str).split(",")
+    ]
+    return [investor for investor in investors if investor]
+
+
+def parse_industries(industries_str):
+    """Parse comma-separated industries and return a list"""
+    if pd.isna(industries_str) or industries_str == "":
+        return []
+
+    # Split by comma and clean whitespace
+    industries = [industry.strip() for industry in str(industries_str).split(",")]
+    return [industry for industry in industries if industry]
+
+
+def clean_special_characters(text):
+    """Clean special characters from text, converting to ASCII equivalents"""
+    if not text:
+        return text
+
+    # First remove ellipses and other problematic patterns
+    text = str(text).replace("...", "").replace("..", "")
+
+    # Normalize unicode characters to their closest ASCII equivalents
+    normalized = unicodedata.normalize("NFKD", text)
+
+    # Remove accents and convert to ASCII
+    ascii_text = normalized.encode("ascii", "ignore").decode("ascii")
+
+    # Remove any remaining non-alphanumeric characters except spaces, hyphens, and periods
+    cleaned = re.sub(r"[^a-zA-Z0-9\s\-\.]", "", ascii_text)
+
+    # Clean up multiple spaces
+    cleaned = re.sub(r"\s+", " ", cleaned).strip()
+
+    return cleaned
+
+
+def clean_string(value):
+    """Clean string values, converting empty/null/nan/0 to None and removing special characters"""
+    if (
+        pd.isna(value)
+        or value == ""
+        or str(value).lower() in ["nan", "null", "none", "0", "0.0"]
+    ):
+        return None
+
+    # First clean special characters
+    cleaned = clean_special_characters(str(value).strip())
+
+    # Check if result is just "0" after cleaning
+    if cleaned in ["0", "0.0", "null", "nan", "none"]:
+        return None
+
+    return cleaned if cleaned else None
+
+
+def clean_name(value):
+    """Clean names (companies, investors) with special character handling"""
+    if (
+        pd.isna(value)
+        or value == ""
+        or str(value).lower() in ["nan", "null", "none", "0", "0.0"]
+    ):
+        return None
+
+    # Clean special characters but be more permissive for names
+    text = str(value).strip()
+    # First remove ellipses and other problematic patterns
+    # text = text.replace("...", "").replace("..", "")
+
+    # Normalize unicode characters
+    normalized = unicodedata.normalize("NFKD", text)
+
+    # Convert to ASCII but keep more characters for business names
+    ascii_text = normalized.encode("ascii", "ignore").decode("ascii")
+
+    # Allow alphanumeric, spaces, hyphens, periods, parentheses, and ampersands
+    cleaned = re.sub(r"[^a-zA-Z0-9\s\-\.\(\)&]", "", ascii_text)
+
+    # Clean up multiple spaces
+    cleaned = re.sub(r"\s+", " ", cleaned).strip()
+
+    # Remove any trailing or leading periods
+    cleaned = cleaned.strip(".")
+
+    cleaned = cleaned.replace("..", "").replace("...", "")
+    # Check if result is just "0" after cleaning
+    if cleaned in ["0", "0.0", "null", "nan", "none"]:
+        return None
+
+    return cleaned if cleaned else None
+
+
+def clean_integer(value):
+    """Clean integer values, converting empty/null/nan/0 to None"""
+    if pd.isna(value) or str(value).lower() in ["nan", "null", "none", "", "0", "0.0"]:
+        return None
+    try:
+        cleaned_val = int(float(value))
+        return cleaned_val if cleaned_val > 0 else None
+    except (ValueError, TypeError):
+        return None
+
+
+def parse_website(website_str: str):
+    try:
+        _, end = website_str.split(":")
+
+        if end == "0":
+            return None
+        return "https:" + end
+    except Exception:
+        return None
+
+
+def ingest_data():
+    # Create database engine and session
+    Session = sessionmaker(bind=engine)
+    session = Session()
+
+    # Load CSV files
+    print("Loading CSV files...")
+    companies_df = pd.read_csv("companies.csv")
+    investors_df = pd.read_csv("investors.csv")
+
+    print(f"📊 Companies CSV: {len(companies_df)} rows")
+    print(f"📊 Investors CSV: {len(investors_df)} rows")
+
+    # Step 1: Ingest Investors
+    print("\n🔄 Step 1: Ingesting Investors...")
+    investors_processed = 0
+
+    for index, row in investors_df.iterrows():
+        try:
+            investor_name = clean_name(row.get("Filtered investor names", ""))
+
+            if investor_name:
+                # Check if investor already exists
+                existing_investor = (
+                    session.query(InvestorTable).filter_by(name=investor_name).first()
+                )
+                if not existing_investor:
+                    investor = InvestorTable(
+                        name=investor_name,
+                        description=clean_string(row.get("Business model", "")),
+                        headquarters=clean_string(row.get("HQ", "")),
+                        website=parse_website(str(row.get("Website", "")).strip()),
+                        number_of_investments=clean_integer(
+                            row.get("Number of investments")
+                        ),
+                    )
+                    session.add(investor)
+                    investors_processed += 1
+
+                    if investors_processed % 1000 == 0:
+                        session.commit()
+                        print(f"  Committed {investors_processed} investors")
+
+        except Exception as e:
+            logger.error(f"Error processing investor {index}: {e}")
+            continue
+
+    session.commit()
+    print(f"✅ Investors completed: {investors_processed} processed")
+
+    # Step 2: Ingest Companies and Rounds
+    print("\n🔄 Step 2: Ingesting Companies and Sectors...")
+    companies_processed = 0
+    sectors_created = set()
+
+    for index, row in companies_df.iterrows():
+        try:
+            # Process company
+            company_name = clean_name(row.get("Organization Name", ""))
+            if not company_name:
+                continue
+
+            # Check if company already exists
+            existing_company = (
+                session.query(CompanyTable).filter_by(name=company_name).first()
+            )
+            if existing_company:
+                company = existing_company
+            else:
+                # Create company
+                company = CompanyTable(
+                    name=company_name,
+                    description=clean_string(row.get("Organization Description", "")),
+                    location=clean_string(row.get("Organization Location", "")),
+                    industry=clean_string(row.get("Organization Industries", "")),
+                    website=clean_string(row.get("Organization Website", "")),
+                )
+                session.add(company)
+                session.flush()  # Get the company ID
+                companies_processed += 1
+
+            # Process investor relationships
+            investor_names_str = row.get("Investor Names", "")
+            if pd.notna(investor_names_str) and investor_names_str:
+                investor_names = parse_investor_names(investor_names_str)
+
+                for investor_name in investor_names:
+                    # Find investor in database
+                    investor = (
+                        session.query(InvestorTable)
+                        .filter_by(name=investor_name.strip())
+                        .first()
+                    )
+
+                    if investor:
+                        # Add investor-company relationship
+                        if company not in investor.portfolio_companies:
+                            investor.portfolio_companies.append(company)
+                    else:
+                        print("This company has an investor not in DB:", investor_name)
+
+            # Process sectors/industries
+            industries_str = row.get("Organization Industries", "")
+            if pd.notna(industries_str) and industries_str:
+                industries = parse_industries(industries_str)
+
+                for industry_name in industries:
+                    industry_name = industry_name.strip()
+                    if industry_name:
+                        # Check if sector exists
+                        sector = (
+                            session.query(SectorTable)
+                            .filter_by(name=industry_name)
+                            .first()
+                        )
+                        if not sector:
+                            sector = SectorTable(name=industry_name)
+                            session.add(sector)
+                            session.flush()
+                            sectors_created.add(industry_name)
+
+                        # Add company-sector relationship
+                        if sector not in company.sectors:
+                            company.sectors.append(sector)
+
+            # Commit every 100 companies
+            if companies_processed % 100 == 0 and companies_processed > 0:
+                session.commit()
+                print(f"  Processed {companies_processed} companies...")
+
+        except Exception as e:
+            logger.error(f"Error processing company {index}: {e}")
+            session.rollback()
+            continue
+
+    # Step 3: Link investors to sectors based on portfolio companies
+    print("\n🔄 Step 3: Linking Investors to Sectors...")
+    investors_linked_to_sectors = 0
+    all_investors = session.query(InvestorTable).all()
+    for investor in all_investors:
+        sectors = set()
+        for company in investor.portfolio_companies:
+            for sector in company.sectors:
+                sectors.add(sector)
+        # Add sectors to investor if not already present
+        for sector in sectors:
+            if sector not in investor.sectors:
+                investor.sectors.append(sector)
+        if sectors:
+            investors_linked_to_sectors += 1
+    session.commit()
+    print(f"✅ Linked {investors_linked_to_sectors} investors to sectors")
+
+    # Final commit
+    session.commit()
+
+    # Final counts
+    final_investors = session.query(InvestorTable).count()
+    final_companies = session.query(CompanyTable).count()
+    final_sectors = session.query(SectorTable).count()
+
+    print("\n🎉 Ingestion Complete!")
+    print(f"   Investors: {final_investors}")
+    print(f"   Companies: {final_companies}")
+    print(f"   Sectors: {final_sectors}")
+
+    session.close()
+
+
+if __name__ == "__main__":
+    ingest_data()
+    # print(clean_name("A... Energi"))
+    # print(clean_name("B.. Tech"))
+    # print(clean_name("A... Energi"))

base_db_generator/models.py

@@ -0,0 +1,381 @@
+import enum
+from typing import Annotated
+
+from fastapi import Depends
+from sqlalchemy import (
+    Column,
+    DateTime,
+    ForeignKey,
+    Integer,
+    String,
+    Table,
+    Text,
+    create_engine,
+    func,
+)
+from sqlalchemy.ext.declarative import declarative_base
+from sqlalchemy.orm import Session, declarative_mixin, relationship, sessionmaker
+from sqlalchemy.types import JSON, Enum
+
+Base = declarative_base()
+
+# Database configuration
+# DATABASE_URL = os.getenv("DATABASE_URL", "sqlite:///./investors.db")
+
+# Create engine
+engine = create_engine("sqlite:///./investors.db", echo=False)
+
+# Create session factory
+SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
+
+
+def get_db():
+    db = SessionLocal()
+    try:
+        yield db
+    finally:
+        db.close()
+
+
+db_dependency = Annotated[Session, Depends(get_db)]
+
+
+def init_database():
+    """Initialize the database by creating all tables"""
+    Base.metadata.create_all(bind=engine)
+
+
+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()
+
+
+@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):
+    SEED = "SEED"
+    SERIES_A = "SERIES_A"
+    SERIES_B = "SERIES_B"
+    SERIES_C = "SERIES_C"
+    GROWTH = "GROWTH"
+    LATE_STAGE = "LATE_STAGE"
+
+
+# Association table for many-to-many relationship between investors and companies
+investor_company_association = Table(
+    "investor_companies",
+    Base.metadata,
+    Column("investor_id", Integer, ForeignKey("investors.id")),
+    Column("company_id", Integer, ForeignKey("companies.id")),
+)
+
+
+# Association table for investor-sector many-to-many
+investor_sector_association = Table(
+    "investor_sectors",
+    Base.metadata,
+    Column("investor_id", Integer, ForeignKey("investors.id")),
+    Column("sector_id", Integer, ForeignKey("sectors.id")),
+)
+
+
+company_sector_association = Table(
+    "company_sector",
+    Base.metadata,
+    Column("company_id", Integer, ForeignKey("companies.id")),
+    Column("sector_id", Integer, ForeignKey("sectors.id")),
+)
+
+project_sector_association = Table(
+    "project_sector",
+    Base.metadata,
+    Column("project_id", Integer, ForeignKey("projects.id")),
+    Column("sector_id", Integer, ForeignKey("sectors.id")),
+)
+
+project_investor_association = Table(
+    "project_investors",
+    Base.metadata,
+    Column("project_id", Integer, ForeignKey("projects.id")),
+    Column("investor_id", Integer, ForeignKey("investors.id")),
+)
+
+project_company_association = Table(
+    "project_companies",
+    Base.metadata,
+    Column("project_id", Integer, ForeignKey("projects.id")),
+    Column("company_id", Integer, ForeignKey("companies.id")),
+)
+
+# Association table for investor-stage many-to-many
+investor_stage_association = Table(
+    "investor_stages",
+    Base.metadata,
+    Column("investor_id", Integer, ForeignKey("investors.id")),
+    Column("stage_id", Integer, ForeignKey("investment_stages.id")),
+)
+
+# Association table for fund-stage many-to-many
+fund_investment_stages_association = Table(
+    "fund_investment_stages",
+    Base.metadata,
+    Column("fund_id", Integer, ForeignKey("funds.id")),
+    Column("stage_id", Integer, ForeignKey("investment_stages.id")),
+)
+
+# Association table for fund-sector many-to-many
+fund_sectors_association = Table(
+    "fund_sectors",
+    Base.metadata,
+    Column("fund_id", Integer, ForeignKey("funds.id")),
+    Column("sector_id", Integer, ForeignKey("sectors.id")),
+)
+
+
+class InvestorTable(Base, TimestampMixin):
+    __tablename__ = "investors"
+
+    id = Column(Integer, primary_key=True, index=True)
+    name = Column(String, nullable=False)
+    description = Column(Text, nullable=True)
+
+    # Basic investor info
+    website = Column(String, nullable=True)
+    headquarters = Column(String, nullable=True)
+
+    # AUM fields
+    aum = Column(Integer, nullable=True)  # Store as integer for numerical filtering
+    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)
+
+    # 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, nullable=True)
+
+    # Relationships
+    team_members = relationship(
+        "InvestorMember", back_populates="investor", cascade="all, delete-orphan"
+    )
+    funds = relationship(
+        "FundTable", back_populates="investor", cascade="all, delete-orphan"
+    )
+
+    # Many-to-many relationship with investment stages
+    investment_stages = relationship(
+        "InvestmentStageTable",
+        secondary=investor_stage_association,
+        back_populates="investors",
+    )
+
+    # Relationship to portfolio companies
+    portfolio_companies = relationship(
+        "CompanyTable",
+        secondary=investor_company_association,
+        back_populates="investors",
+    )
+
+    sectors = relationship(
+        "SectorTable",
+        secondary=investor_sector_association,
+        back_populates="investors",
+    )
+
+    projects = relationship(
+        "ProjectTable",
+        secondary=project_investor_association,
+        back_populates="investors",
+    )
+
+
+class InvestorMember(Base, TimestampMixin):
+    __tablename__ = "investor_members"
+    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(
+        Integer, nullable=True
+    )  # Store as integer for numerical filtering
+    fund_size_source_url = Column(String, nullable=True)
+
+    # Check size range (parsed from estimated_investment_size by LLM)
+    check_size_lower = Column(Integer, nullable=True)
+    check_size_upper = Column(Integer, nullable=True)
+
+    source_url = Column(String, nullable=True)
+    source_provider = Column(String, nullable=True)  # e.g., "Perplexity"
+
+    # Geographic focus as simple string
+    geographic_focus = Column(String, nullable=True)
+
+    # Relationships
+    investor = relationship("InvestorTable", back_populates="funds")
+    investment_stages = relationship(
+        "InvestmentStageTable",
+        secondary=fund_investment_stages_association,
+        back_populates="funds",
+    )
+    sectors = relationship(
+        "SectorTable",
+        secondary=fund_sectors_association,
+        back_populates="funds",
+    )
+
+
+class InvestmentStageTable(Base, TimestampMixin):
+    __tablename__ = "investment_stages"
+
+    id = Column(Integer, primary_key=True, index=True)
+    name = Column(String, nullable=False, unique=True)
+
+    # Relationships
+    investors = relationship(
+        "InvestorTable",
+        secondary=investor_stage_association,
+        back_populates="investment_stages",
+    )
+    funds = relationship(
+        "FundTable",
+        secondary=fund_investment_stages_association,
+        back_populates="investment_stages",
+    )
+
+
+class CompanyTable(Base, TimestampMixin):
+    __tablename__ = "companies"
+
+    id = Column(Integer, primary_key=True, index=True)
+    name = Column(String, nullable=False)
+    industry = Column(String, nullable=True)
+    location = Column(String, nullable=True)
+    description = Column(String, nullable=True)
+    founded_year = Column(Integer, nullable=True)
+    website = Column(String, nullable=True)
+
+    members = relationship(
+        "CompanyMember", back_populates="company", cascade="all, delete-orphan"
+    )
+    # Relationship back to investors
+    investors = relationship(
+        "InvestorTable",
+        secondary=investor_company_association,
+        back_populates="portfolio_companies",
+    )
+
+    sectors = relationship(
+        "SectorTable", secondary=company_sector_association, back_populates="companies"
+    )
+
+    projects = relationship(
+        "ProjectTable",
+        secondary=project_company_association,
+        back_populates="companies",
+    )
+
+
+class CompanyMember(Base, TimestampMixin):
+    __tablename__ = "company_members"
+    id = Column(Integer, primary_key=True)
+    name = Column(String)
+    linkedin = Column(String, nullable=True)
+    role = Column(String, nullable=True)
+    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)
+    name = Column(String, nullable=False)
+
+    # Relationships
+    investors = relationship(
+        "InvestorTable",
+        secondary=investor_sector_association,
+        back_populates="sectors",
+    )
+    companies = relationship(
+        "CompanyTable", secondary=company_sector_association, back_populates="sectors"
+    )
+    projects = relationship(
+        "ProjectTable", secondary=project_sector_association, back_populates="sector"
+    )
+    funds = relationship(
+        "FundTable",
+        secondary=fund_sectors_association,
+        back_populates="sectors",
+    )
+
+
+class ProjectTable(Base, TimestampMixin):
+    __tablename__ = "projects"
+
+    id = Column(Integer, primary_key=True, index=True)
+    name = Column(String, nullable=False)
+    valuation = Column(Integer, nullable=True)
+
+    stage = Column(Enum(InvestmentStage), nullable=True)
+    location = Column(String, nullable=True)
+    description = Column(Text, nullable=True)
+    start_date = Column(DateTime, nullable=True)
+    end_date = Column(DateTime, nullable=True)
+
+    sector = relationship(
+        "SectorTable", secondary=project_sector_association, back_populates="projects"
+    )
+    investors = relationship(
+        "InvestorTable",
+        secondary=project_investor_association,
+        back_populates="projects",
+    )
+    companies = relationship(
+        "CompanyTable", secondary=project_company_association, back_populates="projects"
+    )