build(db): add Alembic migration environment and initial schema
This commit is contained in:
1
alembic/README
Normal file
1
alembic/README
Normal file
@@ -0,0 +1 @@
|
||||
Generic single-database configuration with an async dbapi.
|
||||
86
alembic/env.py
Normal file
86
alembic/env.py
Normal file
@@ -0,0 +1,86 @@
|
||||
import asyncio
|
||||
from logging.config import fileConfig
|
||||
|
||||
from sqlalchemy import pool
|
||||
from sqlalchemy.engine import Connection
|
||||
from sqlalchemy.ext.asyncio import async_engine_from_config
|
||||
|
||||
from alembic import context
|
||||
from src.config import Settings
|
||||
from src.infrastructure.postgres.models import Base
|
||||
|
||||
# this is the Alembic Config object, which provides
|
||||
# access to the values within the .ini file in use.
|
||||
config = context.config
|
||||
|
||||
# Interpret the config file for Python logging.
|
||||
# This line sets up loggers basically.
|
||||
if config.config_file_name is not None:
|
||||
fileConfig(config.config_file_name)
|
||||
|
||||
# Application models' MetaData, used for 'autogenerate' support. The database
|
||||
# URL is likewise sourced from application settings, not alembic.ini, so both
|
||||
# migrations and the app read the same env-derived configuration (ADR-0009).
|
||||
target_metadata = Base.metadata
|
||||
config.set_main_option("sqlalchemy.url", Settings().postgres.dsn)
|
||||
|
||||
|
||||
def run_migrations_offline() -> None:
|
||||
"""Run migrations in 'offline' mode.
|
||||
|
||||
This configures the context with just a URL
|
||||
and not an Engine, though an Engine is acceptable
|
||||
here as well. By skipping the Engine creation
|
||||
we don't even need a DBAPI to be available.
|
||||
|
||||
Calls to context.execute() here emit the given string to the
|
||||
script output.
|
||||
|
||||
"""
|
||||
url = config.get_main_option("sqlalchemy.url")
|
||||
context.configure(
|
||||
url=url,
|
||||
target_metadata=target_metadata,
|
||||
literal_binds=True,
|
||||
dialect_opts={"paramstyle": "named"},
|
||||
)
|
||||
|
||||
with context.begin_transaction():
|
||||
context.run_migrations()
|
||||
|
||||
|
||||
def do_run_migrations(connection: Connection) -> None:
|
||||
context.configure(connection=connection, target_metadata=target_metadata)
|
||||
|
||||
with context.begin_transaction():
|
||||
context.run_migrations()
|
||||
|
||||
|
||||
async def run_async_migrations() -> None:
|
||||
"""In this scenario we need to create an Engine
|
||||
and associate a connection with the context.
|
||||
|
||||
"""
|
||||
|
||||
connectable = async_engine_from_config(
|
||||
config.get_section(config.config_ini_section, {}),
|
||||
prefix="sqlalchemy.",
|
||||
poolclass=pool.NullPool,
|
||||
)
|
||||
|
||||
async with connectable.connect() as connection:
|
||||
await connection.run_sync(do_run_migrations)
|
||||
|
||||
await connectable.dispose()
|
||||
|
||||
|
||||
def run_migrations_online() -> None:
|
||||
"""Run migrations in 'online' mode."""
|
||||
|
||||
asyncio.run(run_async_migrations())
|
||||
|
||||
|
||||
if context.is_offline_mode():
|
||||
run_migrations_offline()
|
||||
else:
|
||||
run_migrations_online()
|
||||
28
alembic/script.py.mako
Normal file
28
alembic/script.py.mako
Normal file
@@ -0,0 +1,28 @@
|
||||
"""${message}
|
||||
|
||||
Revision ID: ${up_revision}
|
||||
Revises: ${down_revision | comma,n}
|
||||
Create Date: ${create_date}
|
||||
|
||||
"""
|
||||
from typing import Sequence, Union
|
||||
|
||||
from alembic import op
|
||||
import sqlalchemy as sa
|
||||
${imports if imports else ""}
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = ${repr(up_revision)}
|
||||
down_revision: Union[str, Sequence[str], None] = ${repr(down_revision)}
|
||||
branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
|
||||
depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade schema."""
|
||||
${upgrades if upgrades else "pass"}
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade schema."""
|
||||
${downgrades if downgrades else "pass"}
|
||||
@@ -0,0 +1,156 @@
|
||||
"""create tenants, api_keys, source_files, ingestion_jobs, ingestion_job_events
|
||||
|
||||
Revision ID: bfc6c81c2542
|
||||
Revises:
|
||||
Create Date: 2026-08-16 11:39:02.649094
|
||||
|
||||
"""
|
||||
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 = 'bfc6c81c2542'
|
||||
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.create_table('tenants',
|
||||
sa.Column('id', sa.Uuid(), nullable=False),
|
||||
sa.Column('slug', sa.String(length=80), nullable=False),
|
||||
sa.Column('name', sa.String(length=200), nullable=False),
|
||||
sa.Column('status', sa.String(length=20), server_default='active', nullable=False),
|
||||
sa.Column('settings', postgresql.JSONB(astext_type=sa.Text()), server_default='{}', 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.Column('deleted_at', sa.DateTime(timezone=True), nullable=True),
|
||||
sa.CheckConstraint("status IN ('active', 'suspended', 'deleted')", name='ck_tenants_status'),
|
||||
sa.PrimaryKeyConstraint('id')
|
||||
)
|
||||
op.create_index(op.f('ix_tenants_slug'), 'tenants', ['slug'], unique=True)
|
||||
op.create_table('api_keys',
|
||||
sa.Column('id', sa.Uuid(), nullable=False),
|
||||
sa.Column('tenant_id', sa.Uuid(), nullable=False),
|
||||
sa.Column('name', sa.String(length=200), nullable=False),
|
||||
sa.Column('key_prefix', sa.String(length=32), nullable=False),
|
||||
sa.Column('key_hash', sa.String(length=255), nullable=False),
|
||||
sa.Column('scopes', postgresql.JSONB(astext_type=sa.Text()), server_default='[]', nullable=False),
|
||||
sa.Column('actor_type', sa.String(length=20), server_default='backend', nullable=False),
|
||||
sa.Column('status', sa.String(length=20), server_default='active', nullable=False),
|
||||
sa.Column('expires_at', sa.DateTime(timezone=True), nullable=True),
|
||||
sa.Column('revoked_at', sa.DateTime(timezone=True), nullable=True),
|
||||
sa.Column('last_used_at', sa.DateTime(timezone=True), nullable=True),
|
||||
sa.Column('created_by', sa.String(length=200), 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()'), nullable=False),
|
||||
sa.CheckConstraint("actor_type IN ('backend', 'admin', 'worker')", name='ck_api_keys_actor_type'),
|
||||
sa.CheckConstraint("status IN ('active', 'revoked', 'expired')", name='ck_api_keys_status'),
|
||||
sa.ForeignKeyConstraint(['tenant_id'], ['tenants.id'], ondelete='CASCADE'),
|
||||
sa.PrimaryKeyConstraint('id')
|
||||
)
|
||||
op.create_index(op.f('ix_api_keys_key_prefix'), 'api_keys', ['key_prefix'], unique=True)
|
||||
op.create_index(op.f('ix_api_keys_tenant_id'), 'api_keys', ['tenant_id'], unique=False)
|
||||
op.create_index('ix_api_keys_tenant_id_status', 'api_keys', ['tenant_id', 'status'], unique=False)
|
||||
op.create_table('source_files',
|
||||
sa.Column('id', sa.Uuid(), nullable=False),
|
||||
sa.Column('tenant_id', sa.Uuid(), nullable=False),
|
||||
sa.Column('domain', sa.String(length=80), nullable=False),
|
||||
sa.Column('source_filename', sa.String(length=500), nullable=False),
|
||||
sa.Column('source_type', sa.String(length=10), nullable=False),
|
||||
sa.Column('content_sha256', sa.String(length=64), nullable=False),
|
||||
sa.Column('byte_size', sa.BigInteger(), nullable=False),
|
||||
sa.Column('storage_uri', sa.String(length=1000), nullable=True),
|
||||
sa.Column('status', sa.String(length=20), server_default='active', nullable=False),
|
||||
sa.Column('created_by_api_key_id', sa.Uuid(), 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()'), nullable=False),
|
||||
sa.Column('deleted_at', sa.DateTime(timezone=True), nullable=True),
|
||||
sa.CheckConstraint("source_type IN ('csv', 'xlsx', 'docx', 'doc')", name='ck_source_files_source_type'),
|
||||
sa.CheckConstraint("status IN ('active', 'superseded', 'soft_deleted', 'purged')", name='ck_source_files_status'),
|
||||
sa.ForeignKeyConstraint(['created_by_api_key_id'], ['api_keys.id'], ondelete='SET NULL'),
|
||||
sa.ForeignKeyConstraint(['tenant_id'], ['tenants.id'], ondelete='CASCADE'),
|
||||
sa.PrimaryKeyConstraint('id')
|
||||
)
|
||||
op.create_index(op.f('ix_source_files_tenant_id'), 'source_files', ['tenant_id'], unique=False)
|
||||
op.create_index('ix_source_files_tenant_id_content_sha256', 'source_files', ['tenant_id', 'content_sha256'], unique=False)
|
||||
op.create_index('ix_source_files_tenant_id_domain_created_at', 'source_files', ['tenant_id', 'domain', 'created_at'], unique=False)
|
||||
op.create_table('ingestion_jobs',
|
||||
sa.Column('id', sa.Uuid(), nullable=False),
|
||||
sa.Column('tenant_id', sa.Uuid(), nullable=False),
|
||||
sa.Column('source_file_id', sa.Uuid(), nullable=False),
|
||||
sa.Column('requested_by_api_key_id', sa.Uuid(), nullable=True),
|
||||
sa.Column('status', sa.String(length=20), server_default='queued', nullable=False),
|
||||
sa.Column('chunking_strategy', sa.String(length=20), nullable=True),
|
||||
sa.Column('embedding_model_versions', postgresql.JSONB(astext_type=sa.Text()), server_default='{}', nullable=False),
|
||||
sa.Column('started_at', sa.DateTime(timezone=True), nullable=True),
|
||||
sa.Column('completed_at', sa.DateTime(timezone=True), nullable=True),
|
||||
sa.Column('points_created', sa.Integer(), server_default='0', nullable=False),
|
||||
sa.Column('points_updated', sa.Integer(), server_default='0', nullable=False),
|
||||
sa.Column('points_soft_deleted', sa.Integer(), server_default='0', nullable=False),
|
||||
sa.Column('points_skipped', sa.Integer(), server_default='0', nullable=False),
|
||||
sa.Column('error_code', sa.String(length=100), nullable=True),
|
||||
sa.Column('error_message', sa.Text(), nullable=True),
|
||||
sa.Column('metadata', postgresql.JSONB(astext_type=sa.Text()), server_default='{}', 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.CheckConstraint("chunking_strategy IN ('semantic', 'fixed_size')", name='ck_ingestion_jobs_chunking_strategy'),
|
||||
sa.CheckConstraint("status IN ('queued', 'running', 'succeeded', 'failed', 'cancelled')", name='ck_ingestion_jobs_status'),
|
||||
sa.ForeignKeyConstraint(['requested_by_api_key_id'], ['api_keys.id'], ondelete='SET NULL'),
|
||||
sa.ForeignKeyConstraint(['source_file_id'], ['source_files.id'], ondelete='CASCADE'),
|
||||
sa.ForeignKeyConstraint(['tenant_id'], ['tenants.id'], ondelete='CASCADE'),
|
||||
sa.PrimaryKeyConstraint('id')
|
||||
)
|
||||
op.create_index(op.f('ix_ingestion_jobs_source_file_id'), 'ingestion_jobs', ['source_file_id'], unique=False)
|
||||
op.create_index('ix_ingestion_jobs_source_file_id_created_at', 'ingestion_jobs', ['source_file_id', 'created_at'], unique=False)
|
||||
op.create_index(op.f('ix_ingestion_jobs_tenant_id'), 'ingestion_jobs', ['tenant_id'], unique=False)
|
||||
op.create_index('ix_ingestion_jobs_tenant_id_status_created_at', 'ingestion_jobs', ['tenant_id', 'status', 'created_at'], unique=False)
|
||||
op.create_table('ingestion_job_events',
|
||||
sa.Column('id', sa.Uuid(), nullable=False),
|
||||
sa.Column('tenant_id', sa.Uuid(), nullable=False),
|
||||
sa.Column('ingestion_job_id', sa.Uuid(), nullable=False),
|
||||
sa.Column('level', sa.String(length=10), nullable=False),
|
||||
sa.Column('stage', sa.String(length=20), nullable=False),
|
||||
sa.Column('message', sa.String(length=1000), nullable=False),
|
||||
sa.Column('details', postgresql.JSONB(astext_type=sa.Text()), server_default='{}', nullable=False),
|
||||
sa.Column('created_at', sa.DateTime(timezone=True), server_default=sa.text('now()'), nullable=False),
|
||||
sa.CheckConstraint("level IN ('info', 'warning', 'error')", name='ck_ingestion_job_events_level'),
|
||||
sa.CheckConstraint("stage IN ('received', 'parsed', 'chunked', 'embedded', 'upserted', 'completed')", name='ck_ingestion_job_events_stage'),
|
||||
sa.ForeignKeyConstraint(['ingestion_job_id'], ['ingestion_jobs.id'], ondelete='CASCADE'),
|
||||
sa.ForeignKeyConstraint(['tenant_id'], ['tenants.id'], ondelete='CASCADE'),
|
||||
sa.PrimaryKeyConstraint('id')
|
||||
)
|
||||
op.create_index(op.f('ix_ingestion_job_events_ingestion_job_id'), 'ingestion_job_events', ['ingestion_job_id'], unique=False)
|
||||
op.create_index('ix_ingestion_job_events_ingestion_job_id_created_at', 'ingestion_job_events', ['ingestion_job_id', 'created_at'], unique=False)
|
||||
op.create_index(op.f('ix_ingestion_job_events_tenant_id'), 'ingestion_job_events', ['tenant_id'], unique=False)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade schema."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_index(op.f('ix_ingestion_job_events_tenant_id'), table_name='ingestion_job_events')
|
||||
op.drop_index('ix_ingestion_job_events_ingestion_job_id_created_at', table_name='ingestion_job_events')
|
||||
op.drop_index(op.f('ix_ingestion_job_events_ingestion_job_id'), table_name='ingestion_job_events')
|
||||
op.drop_table('ingestion_job_events')
|
||||
op.drop_index('ix_ingestion_jobs_tenant_id_status_created_at', table_name='ingestion_jobs')
|
||||
op.drop_index(op.f('ix_ingestion_jobs_tenant_id'), table_name='ingestion_jobs')
|
||||
op.drop_index('ix_ingestion_jobs_source_file_id_created_at', table_name='ingestion_jobs')
|
||||
op.drop_index(op.f('ix_ingestion_jobs_source_file_id'), table_name='ingestion_jobs')
|
||||
op.drop_table('ingestion_jobs')
|
||||
op.drop_index('ix_source_files_tenant_id_domain_created_at', table_name='source_files')
|
||||
op.drop_index('ix_source_files_tenant_id_content_sha256', table_name='source_files')
|
||||
op.drop_index(op.f('ix_source_files_tenant_id'), table_name='source_files')
|
||||
op.drop_table('source_files')
|
||||
op.drop_index('ix_api_keys_tenant_id_status', table_name='api_keys')
|
||||
op.drop_index(op.f('ix_api_keys_tenant_id'), table_name='api_keys')
|
||||
op.drop_index(op.f('ix_api_keys_key_prefix'), table_name='api_keys')
|
||||
op.drop_table('api_keys')
|
||||
op.drop_index(op.f('ix_tenants_slug'), table_name='tenants')
|
||||
op.drop_table('tenants')
|
||||
# ### end Alembic commands ###
|
||||
Reference in New Issue
Block a user