[WIP] Switched to use SQLAlchemy (with Alembic for DB migrations) instead of plain psycopg2

alembic.ini

@@ -0,0 +1,116 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = 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
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python-dateutil library that can be
+# installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to dateutil.tz.gettz()
+# 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 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" below.
+# 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.ini files 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 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
+
+sqlalchemy.url = postgresql+psycopg2://chatux:postgres@localhost/postgres
+
+
+[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 exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix 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 =
+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/README

@@ -0,0 +1 @@
+Generic single-database configuration.

alembic/env.py

@@ -0,0 +1,77 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+
+# 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
+from server.src.core.scheme import Base
+target_metadata = Base.metadata
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+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()

alembic/script.py.mako

@@ -0,0 +1,26 @@
+"""${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, 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:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

alembic/versions/5c0b6ae8f9ac_initial_migration.py

@@ -0,0 +1,51 @@
+"""initial migration
+
+Revision ID: 5c0b6ae8f9ac
+Revises: 
+Create Date: 2023-10-17 23:39:41.441696
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = '5c0b6ae8f9ac'
+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:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('users',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('email', sa.String(length=250), nullable=False),
+    sa.Column('password', sa.String(length=200), nullable=False),
+    sa.Column('name', sa.String(length=50), nullable=False),
+    sa.PrimaryKeyConstraint('id'),
+    sa.UniqueConstraint('email')
+    )
+    op.create_table('chat_messages',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('user_ref', sa.Integer(), nullable=False),
+    sa.Column('chatbot_id', sa.String(length=50), nullable=False),
+    sa.Column('message', sa.Text(), nullable=False),
+    sa.Column('is_bot_reply', sa.Boolean(), nullable=False),
+    sa.Column('createdat', sa.DateTime(), server_default=sa.text('now()'), nullable=False),
+    sa.ForeignKeyConstraint(['user_ref'], ['users.id'], onupdate='CASCADE', ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('id', 'user_ref'),
+    sa.UniqueConstraint('chatbot_id')
+    )
+    op.create_index(op.f('ix_chat_messages_createdat'), 'chat_messages', ['createdat'], unique=False)
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f('ix_chat_messages_createdat'), table_name='chat_messages')
+    op.drop_table('chat_messages')
+    op.drop_table('users')
+    # ### end Alembic commands ###

requirements.txt

@@ -9,7 +9,9 @@ python-jose
 numpy
 pandas
 requests
-psycopg2-binary
+psycopg2
 python-decouple
 sseclient-py
 openai
+SQLAlchemy==2.0.22
+alembic

server/src/api/apps.py

@@ -5,8 +5,9 @@
 from fastapi.responses import JSONResponse
 
 from api.factory import apps, chat_history
-from api.user import User, get_current_user
+from api.user import get_current_user
 from core.app.app_dao import App
+from core.scheme import User
 
 apps_router = r = APIRouter()
 
@@ -92,11 +93,11 @@ def delete_app(app_key: str, current_user: User = Depends(get_current_user)):
 @r.get("/applications/{app_key}/history")
 def get_app_conversation(app_key: str, user: User = Depends(get_current_user)):
     if app_key == "chat":
-        return chat_history.get_latest_messages(user.email, app_key)
+        return chat_history.get_latest_messages(user.pk, app_key)
 
     for a in apps.get_by_user_email(user.email):
         if app_key == a.app_key:
-            return chat_history.get_latest_messages(user.email, app_key)
+            return chat_history.get_latest_messages(user.pk, app_key)
 
     raise HTTPException(status_code=404, detail="App not found")
 

server/src/api/common.py

@@ -3,7 +3,8 @@
 from fastapi import Depends, APIRouter
 from starlette.responses import JSONResponse
 
-from api.user import User, get_current_user
+from api.user import get_current_user
+from core.scheme import User
 
 common_router = r = APIRouter()
 

server/src/api/docs.py

@@ -6,11 +6,12 @@
 from fastapi.responses import JSONResponse
 
 from api.factory import doc_search_service, redis_client, llm_service, cost_service
-from api.user import get_current_user, User
+from api.user import get_current_user
 from core.docs_search.dtos import AddDocRequest
 from core.docs_search.dtos import (
     SearchRequest
 )
+from core.scheme import User
 
 docs_router = r = APIRouter()
 

server/src/api/factory.py

@@ -16,5 +16,5 @@
 chat_history = factory_chat_history(pg_conn)
 agent = agent_factory(chat_history, cost_service, llm_service)
 apps = AppDao()
-user_service = UserService(UserDao(), apps)
+user_service = UserService(UserDao(pg_conn), apps)
 current_session = {}

server/src/api/predict.py

@@ -5,12 +5,13 @@
 from fastapi.responses import StreamingResponse
 
 from api.factory import agent, apps, cost_service, llm_service
-from api.user import User, get_current_user
+from api.user import get_current_user
 from core.agent.agent_service import UserInputDto
 from core.app.app_dao import App
 from core.docs_search.dtos import (
     CompletionRequest
 )
+from core.scheme import User
 
 predict_router = r = APIRouter()
 

server/src/api/user.py

@@ -5,7 +5,7 @@
 
 from api.factory import user_service, current_session, cost_service
 from api.jwttoken import decode_access_token, create_access_token
-from core.user.user_dao import User
+from core.scheme import User
 
 user_router = r = APIRouter()