Refactor investor and fund schemas to support new check size range

- Removed deprecated `stage_focus` column from `InvestorTable` and `InvestorSchema`.
- Updated `FundTable` to change `fund_size` from VARCHAR to INTEGER and added `check_size_lower` and `check_size_upper` columns.
- Modified API routes to return investor-fund combinations as separate entries.
- Created new `InvestorFundData` schema for combined investor-fund responses.
- Implemented LLM parsing for check size range from estimated investment size.
- Updated database migration script to reflect schema changes and ensure data integrity.
- Removed obsolete verification and test scripts related to the old schema.

app/schemas/router_schemas.py

@@ -32,6 +32,25 @@ 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: List[str] | None
+    investment_stage_focus: List[str] | None
+    sector_focus: List[str] | None
+    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 +95,53 @@ 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: List[str] | None
+    investment_stage_focus: List[str] | None
+    sector_focus: List[str] | None
+
+    # Related data
+    portfolio_companies: List[CompanySchema]
+    team_members: List[InvestorMemberSchema]
+    sectors: List[SectorSchema]
 
     class Config:
         from_attributes = True
@@ -99,3 +159,9 @@ 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]