This commit is contained in:
ruslangilfanov 2025-06-15 22:24:57 +03:00
commit 063da135ec
No known key found for this signature in database
34 changed files with 2537 additions and 0 deletions

161
.gitignore vendored Normal file
View File

@ -0,0 +1,161 @@
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
env/
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
*.egg-info/
.installed.cfg
*.egg
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
.hypothesis/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
target/
# Jupyter Notebook
.ipynb_checkpoints
# pyenv
.python-version
# celery beat schedule file
celerybeat-schedule
# SageMath parsed files
*.sage.py
# dotenv
.env
# virtualenv
.venv
venv/
ENV/
.vscode
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.DS_Store
*.sqlite3
media/
*.pyc
*.db
*.pid
*.sqlite
### VirtualEnv template
# Virtualenv
# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
[Bb]in
[Ii]nclude
[Ll]ib
[Ll]ib64
[Ll]ocal
pyvenv.cfg
pip-selfcheck.json
### JetBrains template
# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and Webstorm
# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
# User-specific stuff:
.idea/workspace.xml
.idea/tasks.xml
.idea/dictionaries
.idea/vcs.xml
.idea/jsLibraryMappings.xml
# Sensitive or high-churn files:
.idea/dataSources.ids
.idea/dataSources.xml
.idea/dataSources.local.xml
.idea/sqlDataSources.xml
.idea/dynamic.xml
.idea/uiDesigner.xml
# Gradle:
.idea/gradle.xml
.idea/libraries
**/.idea/
.idea/
.idea_modules/
.idea/mongoSettings.xml
## File-based project format:
*.iws
## Plugin-specific files:
# IntelliJ
/out/
*.local.json
#ansible part
ansible-etcd.cache
etcd.ini
/inventory

31
.pre-commit-config.yaml Normal file
View File

@ -0,0 +1,31 @@
repos:
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v5.0.0
hooks:
- id: check-yaml
- id: end-of-file-fixer
- id: trailing-whitespace
- repo: https://github.com/charliermarsh/ruff-pre-commit
rev: v0.11.13
hooks:
- id: ruff
name: ruff (auto-fix & format)
args: [--fix]
files: ^src/greek_lang/.*\.py$
stages: [pre-commit]
- id: ruff
name: ruff (lint only)
args: [check]
files: ^src/greek_lang/.*\.py$
stages: [pre-push]
- repo: local
hooks:
- id: mypy-all
name: mypy (strict on all libs)
entry: bash -c 'mypy --strict src/greek_lang
language: system
pass_filenames: false
always_run: true

0
README.md Normal file
View File

45
Taskfile.yml Normal file
View File

@ -0,0 +1,45 @@
version: '3'
tasks:
mypy:
desc: "Run mypy for type checking"
cmds:
- mypy --strict src/greek_lang --python-version 3.13 --strict
ruff-check:
desc: “Run ruff lint checks”
cmds:
- ruff check src/greek_lang
- ruff format --check src/greek_lang
ruff-fix:
desc: “Auto-fix issues and format code with ruff”
cmds:
- ruff check --fix src/greek_lang
- ruff format src/greek_lang
ruff-format:
desc: "Format code using ruff"
cmds:
- ruff format src/greek_lang
check:
desc: "Run mypy and ruff checks"
cmds:
- task mypy
- task ruff-check
fix:
desc: "Run auto-fixes using ruff"
cmds:
- task ruff-fix
- task ruff-format
clean:
desc: "Clean cache and temporary files"
cmds:
- rm -rf .mypy_cache
- rm -rf .ruff_cache
- rm -rf .pytest_cache
- rm -rf htmlcov
- rm -rf .coverage

39
pyproject.toml Normal file
View File

@ -0,0 +1,39 @@
[project]
name = "greek-lang"
version = "0.1.0"
description = "Add your description here"
readme = "README.md"
authors = [
{ name = "ruslangilfanov", email = "rgilfanov@walletteam.org" }
]
requires-python = ">=3.13"
dependencies = [
"aiogtts>=1.1.1",
"alembic>=1.16.1",
"asyncpg>=0.30.0",
"dependency-injector>=4.47.1",
"greenlet>=3.2.3",
"openai>=1.84.0",
"pendulum>=3.1.0",
"psycopg2-binary>=2.9.10",
"pydantic>=2.11.5",
"pydantic-settings>=2.9.1",
"sqlalchemy>=2.0.41",
]
[project.scripts]
greek-lang = "greek_lang:main"
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[dependency-groups]
dev = [
"bandit>=1.8.3",
"go-task-bin>=3.43.3",
"mypy>=1.16.0",
"pre-commit>=4.2.0",
"pyupgrade>=3.20.0",
"ruff>=0.11.13",
]

View File

View File

@ -0,0 +1,16 @@
import os.path
import pathlib
from pydantic_settings import BaseSettings, SettingsConfigDict
class EnvConfig(BaseSettings):
model_config = SettingsConfigDict(
env_file=pathlib.Path(__file__).parent
/ os.path.pardir
/ os.path.pardir
/ os.path.pardir
/ ".env",
env_file_encoding="utf-8",
extra="allow",
)

View File

@ -0,0 +1,15 @@
from dependency_injector import containers, providers
from .db_config import PostgresConfig
from .log_config import LoggerConfig
from .openai_config import OpenAiConfig
from .tg_bot_config import TgBotConfig
class ConfigContainer(containers.DeclarativeContainer):
log_config: providers.Provider[LoggerConfig] = providers.Singleton(LoggerConfig)
postgres_config: providers.Provider[PostgresConfig] = providers.Singleton(
PostgresConfig
)
tg_bot_config: providers.Provider[TgBotConfig] = providers.Singleton(TgBotConfig)
openai_config: providers.Provider[OpenAiConfig] = providers.Singleton(OpenAiConfig)

View File

@ -0,0 +1,15 @@
import pydantic
from . import EnvConfig
class PostgresConfig(EnvConfig):
db_host: str = pydantic.Field(default="127.0.0.1")
db_port: int = pydantic.Field(default=5432)
db_name: str = pydantic.Field(default="greek_lang")
db_user: str = pydantic.Field(default="greek_lang")
db_password: pydantic.SecretStr = pydantic.SecretStr("greek_lang")
db_pool_size: int = pydantic.Field(default=20)
db_pool_max_overflow: int = pydantic.Field(default=5)
db_connect_wait_timeout_seconds: int = pydantic.Field(default=5)
db_debug: bool = pydantic.Field(default=False)

View File

@ -0,0 +1,8 @@
import pydantic
from . import EnvConfig
class LoggerConfig(EnvConfig):
telegram_bot_token: pydantic.SecretStr | None = None
telegram_chat_id: int | None = None

View File

@ -0,0 +1,7 @@
import pydantic
from . import EnvConfig
class OpenAiConfig(EnvConfig):
api_key: pydantic.SecretStr

View File

@ -0,0 +1,7 @@
import pydantic
from . import EnvConfig
class TgBotConfig(EnvConfig):
token: pydantic.SecretStr

View File

@ -0,0 +1,49 @@
import contextlib
from collections.abc import AsyncIterator
from dependency_injector import containers, providers
from .configs.container import ConfigContainer
from .database.container import DatabaseContainer
from .openai_manager.container import OpenAiContainer
class MainContainer(containers.DeclarativeContainer):
config_container = providers.Container(
ConfigContainer,
)
database_container = providers.Container(
DatabaseContainer, config_container=config_container
)
openai_container = providers.Container(
OpenAiContainer, config_container=config_container
)
@contextlib.asynccontextmanager
async def init_resources(
container: MainContainer,
packages: tuple[str, ...] = ("greek_lang",),
modules: tuple[str, ...] = (),
) -> AsyncIterator[MainContainer]:
for provider in container.traverse(types=[providers.Container]):
provider.wire(packages=packages, modules=modules)
resources = container.init_resources()
if resources:
await resources
try:
yield container
finally:
shutdown_resources = container.shutdown_resources()
if shutdown_resources:
await shutdown_resources
@contextlib.asynccontextmanager
async def init_main_container(
packages: tuple[str, ...] = ("greek_lang",),
modules: tuple[str, ...] = (),
) -> AsyncIterator[MainContainer]:
container = MainContainer()
async with init_resources(container, packages=packages, modules=modules):
yield container

View File

View File

@ -0,0 +1,120 @@
# A generic, single database configuration.
[alembic]
# path to migration scripts
# Use forward slashes (/) also on windows to provide an os agnostic path
script_location = migrations
file_template = %%(year)d%%(month).2d%%(day).2d_%%(hour).2d%%(minute).2d_%%(rev)s_%%(slug)s
# 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>=3.9 or backports.zoneinfo library and tzdata library.
# Any required deps can 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 migrations/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:migrations/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 = newline
#
# Use os.pathsep. Default configuration used for new projects.
version_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
sqlalchemy.url = driver://user:pass@localhost/dbname
[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 = 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

View File

@ -0,0 +1,11 @@
import types
def get_app_models_modules() -> list[types.ModuleType]:
from greek_lang.glossaries import models as glossaries_models
from greek_lang.openai_manager import models as openai_manager_models
return [
glossaries_models,
openai_manager_models,
]

View File

@ -0,0 +1,17 @@
from sqlalchemy import MetaData
from sqlalchemy.orm import DeclarativeBase
metadata_obj = MetaData(
naming_convention={
"ix": "ix_%(column_0_label)s",
"uq": "uq_%(table_name)s_%(column_0_name)s",
"ck": "ck_%(table_name)s_%(constraint_name)s",
"fk": "fk_%(table_name)s_%(column_0_name)s_%(referred_table_name)s",
"pk": "pk_%(table_name)s",
},
)
class Base(DeclarativeBase):
metadata = metadata_obj

View File

@ -0,0 +1,42 @@
from collections.abc import AsyncIterator
from dependency_injector import containers, providers
from sqlalchemy import URL
from sqlalchemy.ext.asyncio import AsyncEngine, AsyncSession, async_sessionmaker
from ..configs.db_config import PostgresConfig
from .sessions import (
DRIVERNAME_SYNC,
create_async_engine,
create_url_dsn,
get_session_maker_async,
)
async def create_engine_rw_resource(
postgres_config: PostgresConfig,
) -> AsyncIterator[AsyncEngine]:
engine = create_async_engine(postgres_config)
try:
yield engine
finally:
await engine.dispose()
class DatabaseContainer(containers.DeclarativeContainer):
config_container = providers.DependenciesContainer() # ConfigContainer
async_engine: providers.Resource[AsyncEngine] = providers.Resource(
create_engine_rw_resource,
postgres_config=config_container.postgres_config,
)
async_session_maker: providers.Factory[async_sessionmaker[AsyncSession]] = (
providers.Factory(
get_session_maker_async,
engine=async_engine,
)
)
db_url: providers.Provider[URL] = providers.Factory(
create_url_dsn,
DRIVERNAME_SYNC,
config_container.postgres_config,
)

View File

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

View File

@ -0,0 +1,114 @@
import asyncio
import os
from collections.abc import MutableMapping
from logging.config import fileConfig
from typing import Literal
from alembic import context
from sqlalchemy import URL, create_engine, make_url, pool
from sqlalchemy.orm import DeclarativeBase
from greek_lang.configs.container import ConfigContainer
from greek_lang.database.app_models import get_app_models_modules
from greek_lang.database.base import Base
from greek_lang.database.container import DatabaseContainer
_ = get_app_models_modules()
# 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)
def include_name_filter(
name: str | None,
type_: Literal[
"schema",
"table",
"column",
"index",
"unique_constraint",
"foreign_key_constraint",
],
parent_names: MutableMapping[
Literal["schema_name", "table_name", "schema_qualified_table_name"], str | None
],
) -> bool:
match type_:
case "table":
return name not in {
"apscheduler_jobs",
"apy_changes_logs", # deprecated model, just for history
}
case _:
return True
def run_migrations_offline(base_model: type[DeclarativeBase], url: URL) -> 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.
"""
context.configure(
url=str(url),
target_metadata=base_model.metadata,
literal_binds=True,
dialect_opts={"paramstyle": "named"},
include_schemas=True,
include_name=include_name_filter,
)
if hasattr(base_model, "discover") and callable(base_model.discover):
base_model.discover()
with context.begin_transaction():
context.run_migrations()
def run_migrations_online(base_model: type[DeclarativeBase], url: URL) -> None:
connectable = create_engine(
url,
poolclass=pool.NullPool,
)
if hasattr(base_model, "discover") and callable(base_model.discover):
base_model.discover()
with connectable.connect() as connection:
context.configure(
connection=connection,
target_metadata=base_model.metadata,
include_schemas=True,
include_name=include_name_filter,
)
with context.begin_transaction():
context.run_migrations()
async def get_db_url() -> URL:
database_container = DatabaseContainer(config_container=ConfigContainer())
database_container.wire(packages=["greek_lang.database"])
db_url = database_container.db_url()
return db_url
alembic_db_url = os.environ.get("ALEMBIC_DB_URL")
if alembic_db_url is None:
alembic_db_url = asyncio.run(get_db_url()).render_as_string(hide_password=False)
if alembic_db_url is None:
raise RuntimeError("alembic_db_url not set")
if context.is_offline_mode():
run_migrations_offline(Base, make_url(alembic_db_url))
else:
run_migrations_online(Base, make_url(alembic_db_url))

View 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, 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"}

View File

@ -0,0 +1,30 @@
"""zero_state
Revision ID: 8c97f743c3c7
Revises:
Create Date: 2025-06-15 16:36:01.523616
"""
from typing import Sequence, Union
# revision identifiers, used by Alembic.
revision: str = "8c97f743c3c7"
down_revision: Union[str, None] = None
branch_labels: Union[str, Sequence[str], None] = ("zero",)
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
"""Upgrade schema."""
# ### commands auto generated by Alembic - please adjust! ###
pass
# ### end Alembic commands ###
def downgrade() -> None:
"""Downgrade schema."""
# ### commands auto generated by Alembic - please adjust! ###
pass
# ### end Alembic commands ###

View File

@ -0,0 +1,95 @@
"""glossaries
Revision ID: c66487d803bf
Revises: 8c97f743c3c7
Create Date: 2025-06-15 16:51:41.279417
"""
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 = "c66487d803bf"
down_revision: Union[str, None] = "8c97f743c3c7"
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(
"glossary_word",
sa.Column("id", sa.BigInteger(), autoincrement=True, nullable=False),
sa.Column("term", sa.Text(), nullable=False),
sa.Column(
"language",
sa.Enum("ru", "en", "el", name="languageenum", native_enum=False),
nullable=False,
),
sa.Column("transcription", sa.Text(), nullable=True),
sa.Column("translation", sa.Text(), nullable=False),
sa.Column("description", sa.Text(), nullable=True),
sa.Column(
"lexical_category",
sa.Enum(
"noun",
"verb",
"adjective",
"adverb",
"pronoun",
"preposition",
"conjunction",
"interjection",
"numeral",
"determiner",
"particle",
"other",
name="lexicalcategoryenum",
native_enum=False,
),
nullable=False,
),
sa.Column("meaning_category", sa.Text(), nullable=True),
sa.Column("example", sa.Text(), nullable=True),
sa.Column("etymology", sa.Text(), nullable=True),
sa.Column("audio_file", sa.Text(), 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("note", sa.Text(), nullable=True),
sa.Column("tags", postgresql.ARRAY(sa.Text()), nullable=True),
sa.PrimaryKeyConstraint("id", name=op.f("pk_glossary_word")),
)
op.create_index(
op.f("ix_glossary_word_language"), "glossary_word", ["language"], unique=False
)
op.create_index(
op.f("ix_glossary_word_lexical_category"),
"glossary_word",
["lexical_category"],
unique=False,
)
# ### end Alembic commands ###
def downgrade() -> None:
"""Downgrade schema."""
# ### commands auto generated by Alembic - please adjust! ###
op.drop_index(op.f("ix_glossary_word_lexical_category"), table_name="glossary_word")
op.drop_index(op.f("ix_glossary_word_language"), table_name="glossary_word")
op.drop_table("glossary_word")
# ### end Alembic commands ###

View File

@ -0,0 +1,91 @@
"""openai_token_usage
Revision ID: 19fc4bee7a9f
Revises: c66487d803bf
Create Date: 2025-06-15 17:16:53.259466
"""
from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision: str = "19fc4bee7a9f"
down_revision: Union[str, None] = "c66487d803bf"
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(
"openai_token_usage",
sa.Column("id", sa.BigInteger(), autoincrement=True, nullable=False),
sa.Column("response_id", sa.Text(), nullable=False),
sa.Column("gpt_model", sa.Text(), nullable=False),
sa.Column("open_ai_created", sa.DateTime(timezone=True), nullable=False),
sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
sa.Column("response_fingerprint", sa.Text(), nullable=False),
sa.Column("completion_tokens", sa.Integer(), nullable=False),
sa.Column("prompt_tokens", sa.Integer(), nullable=False),
sa.Column("total_tokens", sa.Integer(), nullable=False),
sa.PrimaryKeyConstraint("id", name=op.f("pk_openai_token_usage")),
)
op.create_index(
op.f("ix_openai_token_usage_created_at"),
"openai_token_usage",
["created_at"],
unique=False,
)
op.create_index(
op.f("ix_openai_token_usage_gpt_model"),
"openai_token_usage",
["gpt_model"],
unique=False,
)
op.create_index(
op.f("ix_openai_token_usage_open_ai_created"),
"openai_token_usage",
["open_ai_created"],
unique=False,
)
op.create_index(
op.f("ix_openai_token_usage_response_fingerprint"),
"openai_token_usage",
["response_fingerprint"],
unique=False,
)
op.create_index(
op.f("ix_openai_token_usage_response_id"),
"openai_token_usage",
["response_id"],
unique=True,
)
# ### end Alembic commands ###
def downgrade() -> None:
"""Downgrade schema."""
# ### commands auto generated by Alembic - please adjust! ###
op.drop_index(
op.f("ix_openai_token_usage_response_id"), table_name="openai_token_usage"
)
op.drop_index(
op.f("ix_openai_token_usage_response_fingerprint"),
table_name="openai_token_usage",
)
op.drop_index(
op.f("ix_openai_token_usage_open_ai_created"), table_name="openai_token_usage"
)
op.drop_index(
op.f("ix_openai_token_usage_gpt_model"), table_name="openai_token_usage"
)
op.drop_index(
op.f("ix_openai_token_usage_created_at"), table_name="openai_token_usage"
)
op.drop_table("openai_token_usage")
# ### end Alembic commands ###

View File

@ -0,0 +1,190 @@
import dataclasses
import functools
from collections.abc import AsyncIterator
from contextlib import asynccontextmanager
from typing import Any
from sqlalchemy import (
URL,
Connection,
Engine,
create_engine,
event,
text,
)
from sqlalchemy.ext.asyncio import (
AsyncEngine,
AsyncSession,
AsyncSessionTransaction,
async_sessionmaker,
)
from sqlalchemy.orm import Session, sessionmaker
from ..configs.db_config import PostgresConfig
DRIVERNAME_SYNC = "postgresql"
DRIVERNAME_ASYNC = "postgresql+asyncpg"
def create_url_dsn(
driver_name: str,
config: PostgresConfig,
) -> URL:
url = URL.create(
drivername=driver_name,
username=config.db_user,
password=config.db_password.get_secret_value(),
host=config.db_host,
port=config.db_port,
database=config.db_name,
)
return url
create_sync_dsn = functools.partial(
create_url_dsn,
driver_name=DRIVERNAME_SYNC,
)
@dataclasses.dataclass(frozen=True)
class EngineOptions:
read_only: bool
is_async: bool
username: str
password: str
host: str
port: int
database: str
# **kwargs for create_engine_async / create_engine
pool_size: int
max_overflow: int
pool_timeout: float
echo: bool
echo_pool: bool
pool_pre_ping: bool = dataclasses.field(default=True)
connect_args: dict[str, Any] = dataclasses.field(default_factory=lambda: {})
@property
def url(self) -> URL:
query: dict[str, Any] = {}
return URL.create(
drivername=DRIVERNAME_ASYNC if self.is_async else DRIVERNAME_SYNC,
username=self.username,
password=self.password,
host=self.host,
port=self.port,
database=self.database,
query=query,
)
@property
def params(self) -> dict[str, Any]:
params = dataclasses.asdict(self)
is_async = params.pop("is_async")
for name in ("read_only", "username", "password", "host", "port", "database"):
params.pop(name)
if is_async:
params["connect_args"].update(
{
"prepared_statement_name_func": lambda: "",
"statement_cache_size": 0,
"prepared_statement_cache_size": 0,
}
)
else:
# TODO: implement disable prepared statement for sync
raise NotImplementedError(
"TODO: implement disable prepared statement for sync"
)
return params
def make_engine(self) -> Engine | AsyncEngine:
from sqlalchemy.ext.asyncio import create_async_engine
engine: Engine | AsyncEngine
if self.is_async:
engine = create_async_engine(self.url, **self.params)
if self.read_only:
@event.listens_for(engine.sync_engine, "begin")
def set_transaction_read_only(conn: Connection) -> None:
conn.execute(text("SET TRANSACTION READ ONLY;"))
return engine
else:
engine = create_engine(self.url, **self.params)
if self.read_only:
@event.listens_for(engine, "begin")
def set_transaction_read_only(conn: Connection) -> None:
conn.execute(text("SET TRANSACTION READ ONLY;"))
return engine
AUTOFLUSH = False
EXPIRE_ON_COMMIT = False
def get_session_maker_async(
engine: AsyncEngine,
) -> async_sessionmaker[AsyncSession]:
return async_sessionmaker(
bind=engine,
autoflush=AUTOFLUSH,
expire_on_commit=EXPIRE_ON_COMMIT,
)
def get_session_maker_sync(engine: Engine) -> sessionmaker[Session]:
maker = sessionmaker(
bind=engine,
autoflush=AUTOFLUSH,
expire_on_commit=EXPIRE_ON_COMMIT,
)
return maker
def create_async_engine(postgres_config: PostgresConfig) -> AsyncEngine:
engine = EngineOptions(
read_only=False,
is_async=True,
username=postgres_config.db_user,
password=postgres_config.db_password.get_secret_value(),
host=postgres_config.db_host,
port=postgres_config.db_port,
database=postgres_config.db_name,
pool_size=postgres_config.db_pool_size,
max_overflow=postgres_config.db_pool_max_overflow,
pool_timeout=postgres_config.db_connect_wait_timeout_seconds,
echo=postgres_config.db_debug,
echo_pool=postgres_config.db_debug,
).make_engine()
if not isinstance(engine, AsyncEngine):
raise RuntimeError("engine must be an AsyncEngine")
return engine
def use_db_session(session: AsyncSession) -> async_sessionmaker[AsyncSession]:
@asynccontextmanager
async def _maker() -> AsyncIterator[AsyncSession]:
yield session
return _maker # type: ignore[return-value]
@asynccontextmanager
async def begin_maybe_nested(
session: AsyncSession,
) -> AsyncIterator[AsyncSessionTransaction]:
tx: AsyncSessionTransaction
if session.in_transaction():
tx = session.begin_nested()
else:
tx = session.begin()
async with tx:
yield tx

View File

View File

@ -0,0 +1,103 @@
from __future__ import annotations
import datetime
import enum
from sqlalchemy import BigInteger, Text, DateTime, Enum, func
from sqlalchemy.dialects.postgresql import ARRAY
from sqlalchemy.orm import Mapped, mapped_column
from ..database.base import Base
from ..languages import LanguageEnum
class LexicalCategoryEnum(str, enum.Enum):
noun = "noun"
verb = "verb"
adjective = "adjective"
adverb = "adverb"
pronoun = "pronoun"
preposition = "preposition"
conjunction = "conjunction"
interjection = "interjection"
numeral = "numeral"
determiner = "determiner"
particle = "particle"
other = "other"
class GlossaryWord(Base):
__tablename__ = "glossary_word"
id: Mapped[int] = mapped_column(
BigInteger(),
primary_key=True,
autoincrement=True,
)
term: Mapped[str] = mapped_column(
Text(),
nullable=False,
)
language: Mapped[LanguageEnum] = mapped_column(
Enum(LanguageEnum, native_enum=False),
nullable=False,
index=True,
)
transcription: Mapped[str | None] = mapped_column(
Text(),
nullable=True,
)
translation: Mapped[str] = mapped_column(
Text(),
nullable=False,
)
description: Mapped[str | None] = mapped_column(
Text(),
nullable=True,
)
lexical_category: Mapped[LexicalCategoryEnum] = mapped_column(
Enum(
LexicalCategoryEnum,
native_enum=False,
),
nullable=False,
index=True,
)
meaning_category: Mapped[str | None] = mapped_column(
Text(),
nullable=True,
)
example: Mapped[str | None] = mapped_column(
Text(),
nullable=True,
)
etymology: Mapped[str | None] = mapped_column(
Text(),
nullable=True,
)
audio_file: Mapped[str | None] = mapped_column(
Text(),
nullable=True,
)
created_at: Mapped[datetime.datetime] = mapped_column(
DateTime(timezone=True), server_default=func.now()
)
updated_at: Mapped[datetime.datetime] = mapped_column(
DateTime(timezone=True),
server_default=func.now(),
)
note: Mapped[str | None] = mapped_column(
Text(),
nullable=True,
)
tags: Mapped[list[str]] = mapped_column(
ARRAY(Text),
nullable=True,
)
def __repr__(self) -> str:
return (
f"<GlossaryWord(id={self.id}, term='{self.term}', language='{self.language.value}', "
f"translation='{self.translation}', transcription='{self.transcription}', "
f"lexical_category='{self.lexical_category}', meaning_category='{self.meaning_category}')>"
)

View File

@ -0,0 +1,8 @@
import enum
@enum.unique
class LanguageEnum(str, enum.Enum):
ru = "ru"
en = "en"
el = "el"

View File

@ -0,0 +1,41 @@
import pendulum
from dependency_injector.wiring import inject, Provide
from openai import AsyncOpenAI
from openai._types import ResponseT
from sqlalchemy.ext.asyncio import async_sessionmaker, AsyncSession
from ..database.container import DatabaseContainer
from .models import OpenAiTokenUsage
class AsyncOpenAICustom(AsyncOpenAI):
async def _process_response( # type: ignore
self,
*args,
**kwargs,
) -> ResponseT:
response: ResponseT = await super()._process_response(*args, **kwargs)
await self.save_token_usage(response)
return response
@inject
async def save_token_usage(
self,
response: ResponseT,
async_session_maker: async_sessionmaker[AsyncSession] = Provide[
DatabaseContainer.async_session_maker
],
) -> None:
async with async_session_maker.begin() as db_session:
db_session.add(
OpenAiTokenUsage(
response_id=response.id, # type: ignore[union-attr]
gpt_model=response.model, # type: ignore[union-attr]
open_ai_created=pendulum.from_timestamp(response.created, tz="UTC"), # type: ignore[union-attr]
response_fingerprint=response.system_fingerprint, # type: ignore[union-attr]
completion_tokens=response.usage.completion_tokens, # type: ignore[union-attr]
prompt_tokens=response.usage.prompt_tokens, # type: ignore[union-attr]
total_tokens=response.usage.total_tokens, # type: ignore[union-attr]
)
)

View File

@ -0,0 +1,25 @@
from typing import AsyncIterator
from dependency_injector import containers, providers
from openai import AsyncOpenAI
from pydantic import SecretStr
from .client import AsyncOpenAICustom
from .manager import OpenAiManager
async def create_async_openai_client(api_key: SecretStr) -> AsyncIterator[AsyncOpenAI]:
async with AsyncOpenAICustom(api_key=api_key.get_secret_value()) as client:
yield client
class OpenAiContainer(containers.DeclarativeContainer):
config_container = providers.DependenciesContainer()
ai_client: providers.Resource[AsyncOpenAI] = providers.Resource(
create_async_openai_client,
api_key=config_container.openai_config.provided.api_key,
)
ai_manager: providers.Factory[OpenAiManager] = providers.Factory(
OpenAiManager,
client=ai_client,
)

View File

@ -0,0 +1,79 @@
from __future__ import annotations
import dataclasses
import pydantic
from openai import AsyncOpenAI
class WordInfo(pydantic.BaseModel):
transcription: str = pydantic.Field(
...,
description="phonetic transcription in IPA",
)
translation: str = pydantic.Field(
...,
description="translation in {target_language}",
)
description: str = pydantic.Field(
...,
description="description in {target_language}",
)
part_of_speech: str = pydantic.Field(
...,
description="part of speech in {target_language}",
)
example: str = pydantic.Field(
...,
description="example",
)
example_transcription: str = pydantic.Field(
...,
description="phonetic transcription in IPA of an example",
)
example_translation: str = pydantic.Field(
...,
description="translation of the example in {target_language}",
)
category: str = pydantic.Field(
...,
description="semantic category in {target_language}",
)
etymology: str = pydantic.Field(
...,
description="short etymology of the word described in {target_language}",
)
@dataclasses.dataclass(frozen=True)
class OpenAiManager:
client: AsyncOpenAI
async def get_gpt_response(
self,
*,
word: str,
source_lang: str,
target_lang: str,
model: str = "gpt-4o",
) -> WordInfo:
system_message = {
"role": "system",
"content": "You are a helpful assistant that provides detailed word information.",
}
user_message = {
"role": "user",
"content": f'Provide detailed information about the word "{word}" in language {source_lang}, set {{target_language}} = {target_lang}.',
}
response = await self.client.beta.chat.completions.parse(
model=model,
messages=( # type: ignore
system_message,
user_message,
),
response_format=WordInfo,
)
word_info: WordInfo | None = response.choices[0].message.parsed
if word_info is None:
raise RuntimeError("No word_info")
return word_info

View File

@ -0,0 +1,65 @@
from __future__ import annotations
import datetime
from sqlalchemy import BigInteger, Text, DateTime, Integer
from sqlalchemy.orm import Mapped, mapped_column
from ..database.base import Base
class OpenAiTokenUsage(Base):
__tablename__ = "openai_token_usage"
id: Mapped[int] = mapped_column(
BigInteger(),
primary_key=True,
autoincrement=True,
)
response_id: Mapped[str] = mapped_column(
Text(),
nullable=False,
index=True,
unique=True,
)
gpt_model: Mapped[str] = mapped_column(
Text(),
nullable=False,
index=True,
)
open_ai_created: Mapped[datetime.datetime] = mapped_column(
DateTime(timezone=True),
nullable=False,
index=True,
)
created_at: Mapped[datetime.datetime] = mapped_column(
DateTime(timezone=True),
default=datetime.datetime.now(datetime.UTC),
nullable=False,
index=True,
)
response_fingerprint: Mapped[str] = mapped_column(
Text(),
nullable=False,
index=True,
)
completion_tokens: Mapped[int] = mapped_column(
Integer(),
nullable=False,
)
prompt_tokens: Mapped[int] = mapped_column(
Integer(),
nullable=False,
)
total_tokens: Mapped[int] = mapped_column(
Integer(),
nullable=False,
)
def __repr__(self) -> str:
return (
f"<OpenAiTokenUsage(id={self.id}, response_id='{self.response_id}', gpt_model='{self.gpt_model}', "
f"open_ai_created={self.open_ai_created}, created_at={self.created_at}, "
f"response_fingerprint='{self.response_fingerprint}', completion_tokens={self.completion_tokens} "
f"prompt_tokens={self.prompt_tokens} total_tokens={self.total_tokens})>"
)

1084
uv.lock Normal file

File diff suppressed because it is too large Load Diff