Add PostgreSQL models, Alembic migrations, and Celery tasks

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Author: medevs

backend/alembic.ini

@@ -0,0 +1,100 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Use absolute path relative to this file location
+script_location = %(here)s/alembic
+
+# template used to generate migration file
+# file_template = %%(rev)s_%%(slug)s
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If string_type is specified, this will be used as the format string.
+# timezone = UTC
+
+# 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 alembic/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 "version_path_separator"
+# version_locations = %(here)s/bar:%(here)s/bat:alembic/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# set to 'true' to search inside of source files recursively
+# for revisions
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+sqlalchemy.url = postgresql://portfolio:portfolio_secret@postgres:5432/portfolio
+
+
+[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
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers = console
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers = console
+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

backend/alembic/env.py

@@ -0,0 +1,91 @@
+# A generic env.py for Alembic migrations
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+import os
+import sys
+
+# Add parent directory to path so we can import app modules
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+# Import your models here so Alembic can see them
+from app.db.database import Base
+from app.db.models import Conversation, Message, Document, UploadedFile
+
+# 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)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+target_metadata = Base.metadata
+
+# Database URL from env or fallback
+db_url = os.getenv(
+    "DATABASE_URL", 
+    "postgresql://portfolio:portfolio_secret@postgres:5432/portfolio"
+)
+# Convert asyncpg URL to psycopg2 for Alembic
+if "asyncpg" in db_url:
+    db_url = db_url.replace("+asyncpg", "")
+
+config.set_main_option("sqlalchemy.url", db_url)
+
+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 run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        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()

backend/alembic/script.py.mako

@@ -0,0 +1,24 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision = ${repr(up_revision)}
+down_revision = ${repr(down_revision)}
+branch_labels = ${repr(branch_labels)}
+depends_on = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

backend/alembic/versions/001_initial_schema.py

@@ -0,0 +1,77 @@
+"""Initial schema with all tables
+
+Revision ID: 001_initial
+Revises:
+Create Date: 2024-12-13
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = '001_initial'
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Create conversations table
+    op.create_table('conversations',
+        sa.Column('id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('title', sa.String(255), nullable=True),
+        sa.Column('session_id', sa.String(255), nullable=True),
+        sa.Column('created_at', sa.DateTime(), nullable=True),
+        sa.Column('updated_at', sa.DateTime(), nullable=True),
+        sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index('ix_conversations_session_id', 'conversations', ['session_id'], unique=False)
+
+    # Create messages table
+    op.create_table('messages',
+        sa.Column('id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('conversation_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('role', sa.String(20), nullable=False),
+        sa.Column('content', sa.Text(), nullable=False),
+        sa.Column('tokens_used', sa.Integer(), nullable=True),
+        sa.Column('latency_ms', sa.Integer(), nullable=True),
+        sa.Column('created_at', sa.DateTime(), nullable=True),
+        sa.ForeignKeyConstraint(['conversation_id'], ['conversations.id'], ),
+        sa.PrimaryKeyConstraint('id')
+    )
+
+    # Create documents table (for RAG chunks)
+    op.create_table('documents',
+        sa.Column('id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('title', sa.String(255), nullable=True),
+        sa.Column('source', sa.String(255), nullable=True),
+        sa.Column('created_at', sa.DateTime(), nullable=True),
+        sa.Column('content', sa.Text(), nullable=True),
+        sa.Column('tsv', postgresql.TSVECTOR(), nullable=True),
+        sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index('idx_docs_tsv', 'documents', ['tsv'], unique=False, postgresql_using='gin')
+
+    # Create uploaded_files table
+    op.create_table('uploaded_files',
+        sa.Column('id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('filename', sa.String(255), nullable=False),
+        sa.Column('file_type', sa.String(50), nullable=False),
+        sa.Column('file_size', sa.Integer(), nullable=True),
+        sa.Column('chunk_count', sa.Integer(), nullable=True),
+        sa.Column('status', sa.String(20), nullable=True),
+        sa.Column('error_message', sa.Text(), nullable=True),
+        sa.Column('created_at', sa.DateTime(), nullable=True),
+        sa.Column('processed_at', sa.DateTime(), nullable=True),
+        sa.PrimaryKeyConstraint('id')
+    )
+
+
+def downgrade() -> None:
+    op.drop_table('uploaded_files')
+    op.drop_index('idx_docs_tsv', table_name='documents', postgresql_using='gin')
+    op.drop_table('documents')
+    op.drop_table('messages')
+    op.drop_index('ix_conversations_session_id', table_name='conversations')
+    op.drop_table('conversations')

backend/app/db/__init__.py

@@ -0,0 +1,14 @@
+"""Database models and utilities."""
+from .database import Base, get_db, AsyncSessionLocal, engine
+from .models import Conversation, Message, Document, UploadedFile
+
+__all__ = [
+    "Base",
+    "get_db",
+    "AsyncSessionLocal",
+    "engine",
+    "Conversation",
+    "Message",
+    "Document",
+    "UploadedFile"
+]

backend/app/db/database.py

@@ -0,0 +1,28 @@
+from sqlalchemy.ext.asyncio import create_async_engine, AsyncSession
+from sqlalchemy.orm import sessionmaker, declarative_base
+import os
+
+# Database URL from environment variable
+DATABASE_URL = os.getenv(
+    "DATABASE_URL", 
+    "postgresql+asyncpg://portfolio:portfolio_secret@postgres:5432/portfolio"
+)
+
+# Create async engine
+engine = create_async_engine(DATABASE_URL, echo=False)
+
+# Create async session factory
+AsyncSessionLocal = sessionmaker(
+    engine, class_=AsyncSession, expire_on_commit=False
+)
+
+# Declarative base for models
+Base = declarative_base()
+
+async def get_db():
+    """Dependency for getting async database session."""
+    async with AsyncSessionLocal() as session:
+        try:
+            yield session
+        finally:
+            await session.close()