feat: DB migrations and DB setup

lending-poc/.gitignore

@@ -9,3 +9,4 @@ build/
 .mypy_cache/
 .pytest_cache/
 .ruff_cache/
+venv/

lending-poc/app/config.py

@@ -9,7 +9,7 @@ class Settings(BaseSettings):
     APP_NAME: str = "lending-poc"
     APP_VERSION: str = "0.1.0"
     DEBUG: bool = False
-    DATABASE_URL: str = "postgresql+asyncpg://postgres:postgres@localhost:5432/lending_poc"
+    DATABASE_URL: str
     LOG_LEVEL: str = "INFO"
 
 

lending-poc/alembic.ini → lending-poc/db/alembic.ini

@@ -1,6 +1,6 @@
 [alembic]
-script_location = alembic
-prepend_sys_path = .
+script_location = %(here)s/migrations
+prepend_sys_path = %(here)s/..
 sqlalchemy.url = driver://user:pass@localhost/dbname
 
 [loggers]

lending-poc/db/config.py

@@ -0,0 +1,12 @@
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+
+class Settings(BaseSettings):
+    model_config = SettingsConfigDict(env_file=".env", env_file_encoding="utf-8", extra="ignore")
+
+    DEBUG: bool = False
+    DATABASE_URL: str
+    ENCRYPTION_KEY: str = ""
+
+
+settings = Settings()

lending-poc/db/database.py

@@ -0,0 +1,26 @@
+from collections.abc import AsyncGenerator
+
+from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
+from sqlalchemy.orm import DeclarativeBase
+
+from db.config import settings
+
+engine = create_async_engine(settings.DATABASE_URL, echo=settings.DEBUG)
+
+async_session = async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False)
+
+
+class Base(DeclarativeBase):
+    pass
+
+
+async def get_db() -> AsyncGenerator[AsyncSession, None]:
+    session = async_session()
+    try:
+        yield session
+        await session.commit()
+    except Exception:
+        await session.rollback()
+        raise
+    finally:
+        await session.close()

lending-poc/alembic/env.py → lending-poc/db/migrations/env.py

@@ -4,8 +4,9 @@
 from alembic import context
 from sqlalchemy.ext.asyncio import create_async_engine
 
-from app.config import settings
-from app.database import Base
+from db.config import settings
+from db.database import Base
+import db.models  # noqa: F401  (registers models on Base.metadata for autogenerate)
 
 config = context.config
 

lending-poc/db/migrations/versions/0001_add_cases.py

@@ -0,0 +1,41 @@
+"""add cases
+
+Revision ID: 0001_add_cases
+Revises:
+Create Date: 2026-08-10 11:51:33.283278
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision: str = "0001_add_cases"
+down_revision: Union[str, None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.execute("CREATE EXTENSION IF NOT EXISTS vector")
+    op.create_table(
+        "cases",
+        sa.Column("id", sa.UUID(), nullable=False),
+        sa.Column("applicant_ref", sa.String(), nullable=False),
+        sa.Column(
+            "status",
+            sa.Enum("RECEIVED", "RUNNING", "PASS", "FAIL", "NEEDS_REVIEW", name="case_status"),
+            nullable=False,
+        ),
+        sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
+        sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index(op.f("ix_cases_applicant_ref"), "cases", ["applicant_ref"], unique=True)
+
+
+def downgrade() -> None:
+    op.drop_index(op.f("ix_cases_applicant_ref"), table_name="cases")
+    op.drop_table("cases")
+    op.execute("DROP TYPE IF EXISTS case_status")

lending-poc/db/migrations/versions/0002_add_documents.py

@@ -0,0 +1,43 @@
+"""add documents
+
+Revision ID: 0002_add_documents
+Revises: 0001_add_cases
+Create Date: 2026-08-10 11:51:33.283278
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision: str = "0002_add_documents"
+down_revision: Union[str, None] = "0001_add_cases"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "documents",
+        sa.Column("id", sa.UUID(), nullable=False),
+        sa.Column("case_id", sa.UUID(), nullable=False),
+        sa.Column(
+            "doc_type",
+            sa.Enum("AADHAAR", "PAN", "ADDRESS_PROOF", "SALARY_SLIP", "BANK_STATEMENT", name="doc_type"),
+            nullable=False,
+        ),
+        sa.Column("extracted_fields", postgresql.JSONB(astext_type=sa.Text()), nullable=False),
+        sa.Column("source_file_ref", sa.String(), nullable=False),
+        sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
+        sa.ForeignKeyConstraint(["case_id"], ["cases.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index(op.f("ix_documents_case_id"), "documents", ["case_id"], unique=False)
+
+
+def downgrade() -> None:
+    op.drop_index(op.f("ix_documents_case_id"), table_name="documents")
+    op.drop_table("documents")
+    op.execute("DROP TYPE IF EXISTS doc_type")

lending-poc/db/migrations/versions/0003_add_golden_records.py

@@ -0,0 +1,49 @@
+"""add golden_records
+
+Revision ID: 0003_add_golden_records
+Revises: 0002_add_documents
+Create Date: 2026-08-10 11:51:33.283278
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import pgvector.sqlalchemy
+
+import db.models.types
+
+# revision identifiers, used by Alembic.
+revision: str = "0003_add_golden_records"
+down_revision: Union[str, None] = "0002_add_documents"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "golden_records",
+        sa.Column("id", sa.UUID(), nullable=False),
+        sa.Column("case_id", sa.UUID(), nullable=False),
+        sa.Column("name", sa.String(), nullable=True),
+        sa.Column("address", sa.String(), nullable=True),
+        sa.Column("address_embedding", pgvector.sqlalchemy.vector.VECTOR(dim=384), nullable=True),
+        sa.Column("aadhaar_number", db.models.types.EncryptedString(), nullable=True),
+        sa.Column("pan_number", db.models.types.EncryptedString(), nullable=True),
+        sa.Column("date_of_birth", sa.Date(), nullable=True),
+        sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
+        sa.Column(
+            "updated_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            onupdate=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(["case_id"], ["cases.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("case_id"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("golden_records")

lending-poc/db/migrations/versions/0004_add_pipeline_results.py

@@ -0,0 +1,46 @@
+"""add pipeline_results
+
+Revision ID: 0004_add_pipeline_results
+Revises: 0003_add_golden_records
+Create Date: 2026-08-10 11:51:33.283278
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision: str = "0004_add_pipeline_results"
+down_revision: Union[str, None] = "0003_add_golden_records"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "pipeline_results",
+        sa.Column("id", sa.UUID(), nullable=False),
+        sa.Column("case_id", sa.UUID(), nullable=False),
+        sa.Column("overall_score", sa.Float(), nullable=False),
+        sa.Column("decision", sa.Enum("PASS", "FAIL", "NEEDS_REVIEW", name="decision"), nullable=False),
+        sa.Column("reasons", postgresql.JSONB(astext_type=sa.Text()), nullable=True),
+        sa.Column("reviewer", sa.String(), nullable=True),
+        sa.Column(
+            "review_status", sa.Enum("PENDING", "APPROVED", "REJECTED", name="review_status"), nullable=True
+        ),
+        sa.Column("reviewer_remarks", sa.Text(), nullable=True),
+        sa.Column("reviewed_at", sa.DateTime(timezone=True), nullable=True),
+        sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
+        sa.ForeignKeyConstraint(["case_id"], ["cases.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index(op.f("ix_pipeline_results_case_id"), "pipeline_results", ["case_id"], unique=False)
+
+
+def downgrade() -> None:
+    op.drop_index(op.f("ix_pipeline_results_case_id"), table_name="pipeline_results")
+    op.drop_table("pipeline_results")
+    op.execute("DROP TYPE IF EXISTS decision")
+    op.execute("DROP TYPE IF EXISTS review_status")

lending-poc/db/migrations/versions/0005_add_validation_results.py

@@ -0,0 +1,61 @@
+"""add validation_results
+
+Revision ID: 0005_add_validation_results
+Revises: 0004_add_pipeline_results
+Create Date: 2026-08-10 11:51:33.283278
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision: str = "0005_add_validation_results"
+down_revision: Union[str, None] = "0004_add_pipeline_results"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "validation_results",
+        sa.Column("id", sa.UUID(), nullable=False),
+        sa.Column("case_id", sa.UUID(), nullable=False),
+        sa.Column("document_id", sa.UUID(), nullable=True),
+        sa.Column(
+            "check_type",
+            sa.Enum(
+                "NAME",
+                "ADDRESS",
+                "AADHAAR",
+                "PAN",
+                "DOB",
+                "EMPLOYER",
+                "SALARY_DATE",
+                "SALARY_CREDIT_COUNT",
+                "MANDATORY_PRESENCE",
+                name="check_type",
+            ),
+            nullable=False,
+        ),
+        sa.Column("passed", sa.Boolean(), nullable=False),
+        sa.Column("score", sa.Float(), nullable=False),
+        sa.Column("evidence", postgresql.JSONB(astext_type=sa.Text()), nullable=True),
+        sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
+        sa.ForeignKeyConstraint(["case_id"], ["cases.id"], ondelete="CASCADE"),
+        sa.ForeignKeyConstraint(["document_id"], ["documents.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index(op.f("ix_validation_results_case_id"), "validation_results", ["case_id"], unique=False)
+    op.create_index(
+        op.f("ix_validation_results_document_id"), "validation_results", ["document_id"], unique=False
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(op.f("ix_validation_results_document_id"), table_name="validation_results")
+    op.drop_index(op.f("ix_validation_results_case_id"), table_name="validation_results")
+    op.drop_table("validation_results")
+    op.execute("DROP TYPE IF EXISTS check_type")

lending-poc/db/models/__init__.py

@@ -0,0 +1,19 @@
+from db.models.case import Case, CaseStatus
+from db.models.document import Document
+from db.models.enums import CheckType, Decision, DocType
+from db.models.golden_record import GoldenRecord
+from db.models.pipeline_result import PipelineResult, ReviewStatus
+from db.models.validation_result import ValidationResult
+
+__all__ = [
+    "Case",
+    "CaseStatus",
+    "CheckType",
+    "Decision",
+    "Document",
+    "DocType",
+    "GoldenRecord",
+    "PipelineResult",
+    "ReviewStatus",
+    "ValidationResult",
+]

lending-poc/db/models/case.py

@@ -0,0 +1,42 @@
+import uuid
+from datetime import datetime
+from enum import Enum
+
+from sqlalchemy import DateTime, Enum as SAEnum, String, func
+from sqlalchemy.dialects.postgresql import UUID
+from sqlalchemy.orm import Mapped, mapped_column, relationship
+
+from db.database import Base
+
+
+class CaseStatus(str, Enum):
+    RECEIVED = "RECEIVED"
+    RUNNING = "RUNNING"
+    PASS = "PASS"
+    FAIL = "FAIL"
+    NEEDS_REVIEW = "NEEDS_REVIEW"
+
+
+class Case(Base):
+    __tablename__ = "cases"
+
+    id: Mapped[uuid.UUID] = mapped_column(UUID(as_uuid=True), primary_key=True, default=uuid.uuid4)
+    applicant_ref: Mapped[str] = mapped_column(String, unique=True, index=True, nullable=False)
+    status: Mapped[CaseStatus] = mapped_column(
+        SAEnum(CaseStatus, name="case_status"), nullable=False, default=CaseStatus.RECEIVED
+    )
+    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, server_default=func.now())
+    updated_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, server_default=func.now(), onupdate=func.now()
+    )
+
+    documents: Mapped[list["Document"]] = relationship(back_populates="case", cascade="all, delete-orphan")
+    golden_record: Mapped["GoldenRecord | None"] = relationship(
+        back_populates="case", cascade="all, delete-orphan", uselist=False
+    )
+    validation_results: Mapped[list["ValidationResult"]] = relationship(
+        back_populates="case", cascade="all, delete-orphan"
+    )
+    pipeline_results: Mapped[list["PipelineResult"]] = relationship(
+        back_populates="case", cascade="all, delete-orphan"
+    )