feat(db): add sqlalchemy models, pgvector, and alembic migrations (#1)

* chore(db): add docker-compose and config for local postgres

* feat(db): add sqlalchemy engine and session management

* chore(db): configure alembic to read env variables

* feat(db): add initial schema migration with pgvector extension

alembic.ini

@@ -0,0 +1,149 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts.
+# this is typically a path given in POSIX (e.g. forward slashes)
+# format, relative to the token %(here)s which refers to the location of this
+# ini file
+script_location = %(here)s/alembic
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+# Or organize into date-based subdirectories (requires recursive_version_locations = true)
+# file_template = %%(year)d/%%(month).2d/%%(day).2d_%%(hour).2d%%(minute).2d_%%(second).2d_%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.  for multiple paths, the path separator
+# is defined by "path_separator" below.
+prepend_sys_path = .
+
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the tzdata library which can be installed by adding
+# `alembic[tz]` to the pip requirements.
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to <script_location>/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "path_separator"
+# below.
+# version_locations = %(here)s/bar:%(here)s/bat:%(here)s/alembic/versions
+
+# path_separator; This indicates what character is used to split lists of file
+# paths, including version_locations and prepend_sys_path within configparser
+# files such as alembic.ini.
+# The default rendered in new alembic.ini files is "os", which uses os.pathsep
+# to provide os-dependent path splitting.
+#
+# Note that in order to support legacy alembic.ini files, this default does NOT
+# take place if path_separator is not present in alembic.ini.  If this
+# option is omitted entirely, fallback logic is as follows:
+#
+# 1. Parsing of the version_locations option falls back to using the legacy
+#    "version_path_separator" key, which if absent then falls back to the legacy
+#    behavior of splitting on spaces and/or commas.
+# 2. Parsing of the prepend_sys_path option falls back to the legacy
+#    behavior of splitting on spaces, commas, or colons.
+#
+# Valid values for path_separator are:
+#
+# path_separator = :
+# path_separator = ;
+# path_separator = space
+# path_separator = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+path_separator = os
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# database URL.  This is consumed by the user-maintained env.py script only.
+# other means of configuring database URLs may be customized within the env.py
+# file.
+sqlalchemy.url = 
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the module runner, against the "ruff" module
+# hooks = ruff
+# ruff.type = module
+# ruff.module = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Alternatively, use the exec runner to execute a binary found on your PATH
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration.  This is also consumed by the user-maintained
+# env.py script only.
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

alembic/env.py

@@ -0,0 +1,46 @@
+from logging.config import fileConfig
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+from alembic import context
+from app.config import settings
+from app.db import Base
+from app import models
+
+config = context.config
+
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+target_metadata = Base.metadata
+
+def run_migrations_offline() -> None:
+    url = settings.DIRECT_DATABASE_URL or settings.DATABASE_URL
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+    with context.begin_transaction():
+        context.run_migrations()
+
+def run_migrations_online() -> None:
+    configuration = config.get_section(config.config_ini_section, {})
+    configuration["sqlalchemy.url"] = settings.DIRECT_DATABASE_URL or settings.DATABASE_URL
+    
+    connectable = engine_from_config(
+        configuration,
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata
+        )
+        with context.begin_transaction():
+            context.run_migrations()
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

alembic/versions/04b68bac8d84_initial_schema_with_pgvector.py

@@ -0,0 +1,109 @@
+"""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 ###

app/config.py

@@ -5,7 +5,8 @@ class Settings(BaseSettings):
     model_config = SettingsConfigDict(env_file=".env", extra="ignore")
 
     # Secrets — no defaults. Missing -> startup fails, naming the variable.
-    DATABASE_URL: str 
+    DATABASE_URL: str
+    DIRECT_DATABASE_URL: str | None = None
     JWT_SECRET_KEY: str
     GEMINI_API_KEY: str
 
@@ -28,5 +29,4 @@ class Settings(BaseSettings):
         return [o.strip() for o in self.CORS_ORIGINS.split(",") if o.strip()]
 
 
-settings = Settings()
-
+settings = Settings()

app/db.py

@@ -0,0 +1,22 @@
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker, declarative_base
+from app.config import settings
+
+engine = create_engine(
+    settings.DATABASE_URL,
+    pool_pre_ping=True,
+    pool_size=3,
+    max_overflow=2,
+    connect_args={"prepare_threshold": None}
+)
+
+SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
+
+Base = declarative_base()
+
+def get_db():
+    db = SessionLocal()
+    try:
+        yield db
+    finally:
+        db.close()

docker-compose.yml

@@ -0,0 +1,15 @@
+services:
+  db:
+    image: pgvector/pgvector:pg16
+    container_name: contextquery_db_final
+    environment:
+      POSTGRES_USER: cq
+      POSTGRES_PASSWORD: cq
+      POSTGRES_DB: contextquery
+    ports:
+      - "55432:5432"
+    volumes:
+      - pgdata_final:/var/lib/postgresql/data
+
+volumes:
+  pgdata_final: