contextquery-api / alembic /versions /04b68bac8d84_initial_schema_with_pgvector.py
RamshaAnwar's picture
feat(db): add sqlalchemy models, pgvector, and alembic migrations (#1)
3e36c5e unverified
Raw History Blame Contribute Delete
5.17 kB
"""initial schema with pgvector
Revision ID: 04b68bac8d84
Revises:
Create Date: 2026-10-18 14:52:32.088121
"""
from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql
import pgvector.sqlalchemy
# revision identifiers, used by Alembic.
revision: str = '04b68bac8d84'
down_revision: Union[str, Sequence[str], None] = None
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
"""Upgrade schema."""
# ### commands auto generated by Alembic - please adjust! ###
op.execute('CREATE EXTENSION IF NOT EXISTS vector;')
op.create_table('users',
sa.Column('id', sa.UUID(), nullable=False),
sa.Column('email', sa.String(length=320), nullable=False),
sa.Column('password_hash', sa.String(length=255), nullable=False),
sa.Column('role', sa.String(length=20), nullable=False),
sa.Column('is_active', sa.Boolean(), nullable=False),
sa.Column('created_at', sa.DateTime(timezone=True), nullable=False),
sa.PrimaryKeyConstraint('id')
)
op.create_table('hubs',
sa.Column('id', sa.UUID(), nullable=False),
sa.Column('owner_id', sa.UUID(), nullable=False),
sa.Column('name', sa.String(length=120), nullable=False),
sa.Column('description', sa.String(length=500), nullable=True),
sa.Column('ai_summary', sa.String(), nullable=True),
sa.Column('suggested_questions', postgresql.JSONB(astext_type=sa.Text()), nullable=False),
sa.Column('created_at', sa.DateTime(timezone=True), nullable=False),
sa.Column('updated_at', sa.DateTime(timezone=True), nullable=False),
sa.ForeignKeyConstraint(['owner_id'], ['users.id'], ondelete='CASCADE'),
sa.PrimaryKeyConstraint('id'),
sa.UniqueConstraint('owner_id', 'name', name='uq_hub_name_per_owner')
)
op.create_table('idempotency_keys',
sa.Column('user_id', sa.UUID(), nullable=False),
sa.Column('key', sa.UUID(), nullable=False),
sa.Column('request_method', sa.String(length=10), nullable=False),
sa.Column('request_path', sa.String(length=255), nullable=False),
sa.Column('request_hash', sa.String(length=64), nullable=False),
sa.Column('status', sa.String(length=20), nullable=False),
sa.Column('response_status', sa.Integer(), nullable=True),
sa.Column('response_body', postgresql.JSONB(astext_type=sa.Text()), nullable=True),
sa.Column('created_at', sa.DateTime(timezone=True), nullable=False),
sa.Column('expires_at', sa.DateTime(timezone=True), nullable=False),
sa.ForeignKeyConstraint(['user_id'], ['users.id'], ondelete='CASCADE'),
sa.PrimaryKeyConstraint('user_id', 'key')
)
op.create_table('documents',
sa.Column('id', sa.UUID(), nullable=False),
sa.Column('hub_id', sa.UUID(), nullable=False),
sa.Column('owner_id', sa.UUID(), nullable=False),
sa.Column('origin', sa.String(length=20), nullable=False),
sa.Column('filename', sa.String(length=255), nullable=False),
sa.Column('mime_type', sa.String(length=100), nullable=False),
sa.Column('size_bytes', sa.Integer(), nullable=False),
sa.Column('checksum_sha256', sa.String(length=64), nullable=False),
sa.Column('status', sa.String(length=20), nullable=False),
sa.Column('error_message', sa.String(), nullable=True),
sa.Column('file_bytes', sa.LargeBinary(), nullable=True),
sa.Column('process_claim', sa.UUID(), nullable=True),
sa.Column('created_at', sa.DateTime(timezone=True), nullable=False),
sa.Column('updated_at', sa.DateTime(timezone=True), nullable=False),
sa.ForeignKeyConstraint(['hub_id'], ['hubs.id'], ondelete='CASCADE'),
sa.ForeignKeyConstraint(['owner_id'], ['users.id'], ondelete='CASCADE'),
sa.PrimaryKeyConstraint('id'),
sa.UniqueConstraint('hub_id', 'checksum_sha256', name='uq_doc_checksum_per_hub')
)
op.create_table('chunks',
sa.Column('id', sa.UUID(), nullable=False),
sa.Column('document_id', sa.UUID(), nullable=False),
sa.Column('hub_id', sa.UUID(), nullable=False),
sa.Column('owner_id', sa.UUID(), nullable=False),
sa.Column('chunk_index', sa.Integer(), nullable=False),
sa.Column('text', sa.String(), nullable=False),
sa.Column('token_count', sa.Integer(), nullable=False),
sa.Column('embedding', pgvector.sqlalchemy.vector.VECTOR(dim=768), nullable=False),
sa.Column('created_at', sa.DateTime(timezone=True), nullable=False),
sa.ForeignKeyConstraint(['document_id'], ['documents.id'], ondelete='CASCADE'),
sa.ForeignKeyConstraint(['hub_id'], ['hubs.id'], ondelete='CASCADE'),
sa.ForeignKeyConstraint(['owner_id'], ['users.id'], ondelete='CASCADE'),
sa.PrimaryKeyConstraint('id')
)
op.create_index('uq_users_email_lower', 'users', [sa.text('lower(email)')], unique=True)
# ### end Alembic commands ###
def downgrade() -> None:
"""Downgrade schema."""
# ### commands auto generated by Alembic - please adjust! ###
op.drop_table('chunks')
op.drop_table('documents')
op.drop_table('idempotency_keys')
op.drop_table('hubs')
op.drop_table('users')
# ### end Alembic commands ###