Refactor database models and schemas to allow nullable fields; update init_database function for improved initialization.

app/schemas/py_schemas.py

@@ -1,7 +1,7 @@
 from enum import Enum
 from typing import List, Optional
 
-from pydantic import BaseModel, field_validator
+from pydantic import BaseModel, Field, field_validator
 
 
 class InvestmentStage(str, Enum):
@@ -14,98 +14,227 @@ class InvestmentStage(str, Enum):
 
 
 class SectorSchema(BaseModel):
-    id: int
-    name: str
+    """
+    Expert parser: Only extract sector information if clearly identifiable.
+    Leave name empty if uncertain about the sector classification.
+    """
+
+    id: int = Field(
+        ge=0, description="Sector ID, must be 0 or greater. Use 0 if uncertain."
+    )
+    name: str = Field(
+        description="Sector name. Leave empty string if not clearly identifiable from the data."
+    )
 
     class Config:
         from_attributes = True
 
 
 class InvestorMemberSchema(BaseModel):
-    id: int
-    name: str
-    role: str
-    email: str
-    investor_id: int
+    """
+    Expert parser: Only extract team member information if clearly identifiable.
+    Leave fields empty if uncertain about the member details.
+    """
+
+    id: int = Field(
+        ge=0, description="Member ID, must be 0 or greater. Use 0 if uncertain."
+    )
+    name: str = Field(
+        description="Team member name. Leave empty string if not clearly identifiable."
+    )
+    role: str = Field(
+        description="Team member role/title. Leave empty string if not clearly identifiable."
+    )
+    email: str = Field(
+        description="Team member email. Leave empty string if not clearly identifiable or not provided."
+    )
+    investor_id: int = Field(
+        ge=0, description="Investor ID, must be 0 or greater. Use 0 if uncertain."
+    )
 
     class Config:
         from_attributes = True
 
 
 class CompanyMemberSchema(BaseModel):
-    id: int
-    name: Optional[str] = None
-    linkedin: Optional[str] = None
-    role: Optional[str] = None
-    company_id: int
+    """
+    Expert parser: Only extract company member information if clearly identifiable.
+    Leave fields empty if uncertain about the member details.
+    """
+
+    id: int = Field(
+        ge=0, description="Member ID, must be 0 or greater. Use 0 if uncertain."
+    )
+    name: Optional[str] = Field(
+        default="",
+        description="Company member name. Leave empty if not clearly identifiable.",
+    )
+    linkedin: Optional[str] = Field(
+        default="",
+        description="LinkedIn profile URL. Leave empty if not provided or uncertain.",
+    )
+    role: Optional[str] = Field(
+        default="",
+        description="Company member role/title. Leave empty if not clearly identifiable.",
+    )
+    company_id: int = Field(
+        ge=0, description="Company ID, must be 0 or greater. Use 0 if uncertain."
+    )
 
     class Config:
         from_attributes = True
 
 
 class CompanySchema(BaseModel):
-    id: int
-    name: str
-    industry: str
-    location: str
-    description: Optional[str] = None  # Fixed typo from 'nullabel'
-    founded_year: Optional[int] = None  # Changed from str to int to match model
-    website: Optional[str] = None
+    """
+    Expert parser: Only extract company information if clearly identifiable.
+    Leave optional fields empty if uncertain. Integer values must be 0 or greater.
+    """
+
+    id: int = Field(
+        ge=0, description="Company ID, must be 0 or greater. Use 0 if uncertain."
+    )
+    name: str = Field(
+        description="Company name. Leave empty string if not clearly identifiable."
+    )
+    industry: str = Field(
+        description="Company industry/sector. Leave empty string if not clearly identifiable."
+    )
+    location: str = Field(
+        description="Company location/address. Leave empty string if not clearly identifiable."
+    )
+    description: Optional[str] = Field(
+        default="",
+        description="Company description. Leave empty if not clearly available or uncertain.",
+    )
+    founded_year: Optional[int] = Field(
+        default=None,
+        ge=0,
+        description="Year company was founded, must be 0 or greater. Leave None if not clearly identifiable or uncertain.",
+    )
+    website: Optional[str] = Field(
+        default="",
+        description="Company website URL. Leave empty if not provided or uncertain.",
+    )
 
     @field_validator("founded_year", mode="before")
     @classmethod
     def validate_founded_year(cls, v):
-        if v is None or v == "Not Available" or v == "":
+        """Expert parser: Only accept clearly identifiable founding years"""
+        if v is None or v == "Not Available" or v == "" or v == "Unknown":
             return None
         if isinstance(v, str):
             try:
-                return int(v)
+                year = int(v)
+                return year if year >= 0 else None
             except ValueError:
                 return None
-        return v
+        return v if isinstance(v, int) and v >= 0 else None
 
     class Config:
         from_attributes = True
 
 
 class InvestorSchema(BaseModel):
-    id: int
-    name: str
-    description: Optional[str] = None
-    aum: int
-    check_size_lower: int
-    check_size_upper: int
-    geographic_focus: str
-    stage_focus: InvestmentStage
-    number_of_investments: int = 0
-    
+    """
+    Expert parser: Only extract investor information if clearly identifiable.
+    Leave optional fields empty if uncertain. All numeric values must be 0 or greater.
+    """
+
+    id: int = Field(
+        ge=0, description="Investor ID, must be 0 or greater. Use 0 if uncertain."
+    )
+    name: str = Field(
+        description="Investor name. Leave empty string if not clearly identifiable."
+    )
+    description: Optional[str] = Field(
+        default="",
+        description="Investor description. Leave empty if not clearly available or uncertain.",
+    )
+    aum: int = Field(
+        ge=0,
+        description="Assets Under Management in USD, must be 0 or greater. Use 0 if not clearly identifiable or uncertain.",
+    )
+    check_size_lower: int = Field(
+        ge=0,
+        description="Lower bound of typical investment check size in USD, must be 0 or greater. Use 0 if not clearly identifiable.",
+    )
+    check_size_upper: int = Field(
+        ge=0,
+        description="Upper bound of typical investment check size in USD, must be 0 or greater. Use 0 if not clearly identifiable.",
+    )
+    geographic_focus: str = Field(
+        description="Geographic investment focus. Leave empty string if not clearly identifiable."
+    )
+    stage_focus: InvestmentStage = Field(
+        description="Investment stage focus. Use SEED as default if uncertain."
+    )
+    number_of_investments: int = Field(
+        ge=0,
+        default=0,
+        description="Total number of investments made, must be 0 or greater. Use 0 if not clearly identifiable.",
+    )
 
     class Config:
         from_attributes = True
 
 
 class InvestorData(BaseModel):
-    """Comprehensive investor data schema for LLM processing"""
+    """
+    Expert parser: Comprehensive investor data schema for LLM processing.
+    Only populate fields with clearly identifiable information. Leave lists empty if uncertain.
+    """
 
-    investor: InvestorSchema
-    portfolio_companies: List[CompanySchema] = []
-    team_members: List[InvestorMemberSchema] = []  # Changed from TeamMember
-    sectors: List[SectorSchema] = []
+    investor: InvestorSchema = Field(
+        description="Core investor information. Only populate with clearly identifiable data."
+    )
+    portfolio_companies: List[CompanySchema] = Field(
+        default=[],
+        description="List of portfolio companies. Leave empty if not clearly identifiable.",
+    )
+    team_members: List[InvestorMemberSchema] = Field(
+        default=[],
+        description="List of team members. Leave empty if not clearly identifiable.",
+    )
+    sectors: List[SectorSchema] = Field(
+        default=[],
+        description="List of investment sectors. Leave empty if not clearly identifiable.",
+    )
 
     class Config:
         from_attributes = True
 
 
-class CompanyData(BaseModel):  # Renamed from CompaniesData for consistency
-    company: CompanySchema
-    sectors: List[SectorSchema] = []
-    members: List[CompanyMemberSchema] = []  # Changed to match model relationship name
-    investors: List[InvestorSchema] = []
+class CompanyData(BaseModel):
+    """
+    Expert parser: Comprehensive company data schema for LLM processing.
+    Only populate fields with clearly identifiable information. Leave lists empty if uncertain.
+    """
+
+    company: CompanySchema = Field(
+        description="Core company information. Only populate with clearly identifiable data."
+    )
+    sectors: List[SectorSchema] = Field(
+        default=[],
+        description="List of company sectors. Leave empty if not clearly identifiable.",
+    )
+    members: List[CompanyMemberSchema] = Field(
+        default=[],
+        description="List of company members. Leave empty if not clearly identifiable.",
+    )
+    investors: List[InvestorSchema] = Field(
+        default=[],
+        description="List of investors. Leave empty if not clearly identifiable.",
+    )
 
     class Config:
         from_attributes = True
 
 
 class InvestorList(BaseModel):
-    investors: List[InvestorData] = []
+    """Expert parser: List of investors with clearly identifiable information only."""
 
+    investors: List[InvestorData] = Field(
+        default=[],
+        description="List of investors. Leave empty if no clearly identifiable investors.",
+    )