finalised backend

backend/alembic.ini

@@ -0,0 +1,115 @@
+# 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
+# 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 = 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 = 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
+

backend/alembic/env.py

@@ -0,0 +1,85 @@
+"""
+Alembic environment configuration
+"""
+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
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
+
+from src.infrastructure.database.base import Base
+from src.infrastructure.database.models import *
+from src.shared.config import settings
+
+config = context.config
+
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+config.set_main_option("sqlalchemy.url", settings.database_url.replace("postgresql://", "postgresql+asyncpg://"))
+
+target_metadata = Base.metadata
+
+
+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_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    configuration = config.get_section(config.config_ini_section)
+    configuration["sqlalchemy.url"] = settings.database_url.replace("postgresql://", "postgresql+asyncpg://")
+    connectable = async_engine_from_config(
+        configuration,
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    async with connectable.connect() as connection:
+        await connection.run_sync(do_run_migrations)
+
+    await connectable.dispose()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    import asyncio
+    asyncio.run(run_migrations_online())
+

backend/alembic/script.py.mako

@@ -0,0 +1,25 @@
+"""${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_migration.py

@@ -0,0 +1,111 @@
+"""Initial migration
+
+Revision ID: 001
+Revises: 
+Create Date: 2024-01-01 00:00:00.000000
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+revision = '001'
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        'users',
+        sa.Column('user_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('telegram_id', sa.String(), nullable=False),
+        sa.Column('role', sa.String(), nullable=False),
+        sa.Column('created_at', sa.DateTime(), nullable=False),
+        sa.PrimaryKeyConstraint('user_id'),
+        sa.UniqueConstraint('telegram_id')
+    )
+    op.create_index(op.f('ix_users_telegram_id'), 'users', ['telegram_id'], unique=True)
+    
+    op.create_table(
+        'collections',
+        sa.Column('collection_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('name', sa.String(), nullable=False),
+        sa.Column('description', sa.Text(), nullable=True),
+        sa.Column('owner_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('is_public', sa.Boolean(), nullable=False),
+        sa.Column('created_at', sa.DateTime(), nullable=False),
+        sa.ForeignKeyConstraint(['owner_id'], ['users.user_id'], ),
+        sa.PrimaryKeyConstraint('collection_id')
+    )
+    
+    op.create_table(
+        'documents',
+        sa.Column('document_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('collection_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('title', sa.String(), nullable=False),
+        sa.Column('content', sa.Text(), nullable=False),
+        sa.Column('metadata', postgresql.JSON(astext_type=sa.Text()), nullable=True),
+        sa.Column('created_at', sa.DateTime(), nullable=False),
+        sa.ForeignKeyConstraint(['collection_id'], ['collections.collection_id'], ),
+        sa.PrimaryKeyConstraint('document_id')
+    )
+    
+    op.create_table(
+        'embeddings',
+        sa.Column('embedding_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('document_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('embedding', postgresql.JSON(astext_type=sa.Text()), nullable=True),
+        sa.Column('model_version', sa.String(), nullable=True),
+        sa.Column('created_at', sa.DateTime(), nullable=False),
+        sa.ForeignKeyConstraint(['document_id'], ['documents.document_id'], ),
+        sa.PrimaryKeyConstraint('embedding_id')
+    )
+    
+    op.create_table(
+        'conversations',
+        sa.Column('conversation_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('user_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('collection_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('created_at', sa.DateTime(), nullable=False),
+        sa.Column('updated_at', sa.DateTime(), nullable=False),
+        sa.ForeignKeyConstraint(['collection_id'], ['collections.collection_id'], ),
+        sa.ForeignKeyConstraint(['user_id'], ['users.user_id'], ),
+        sa.PrimaryKeyConstraint('conversation_id')
+    )
+    
+    op.create_table(
+        'messages',
+        sa.Column('message_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('conversation_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('content', sa.Text(), nullable=False),
+        sa.Column('role', sa.String(), nullable=False),
+        sa.Column('sources', postgresql.JSON(astext_type=sa.Text()), nullable=True),
+        sa.Column('created_at', sa.DateTime(), nullable=False),
+        sa.ForeignKeyConstraint(['conversation_id'], ['conversations.conversation_id'], ),
+        sa.PrimaryKeyConstraint('message_id')
+    )
+    
+    op.create_table(
+        'collection_access',
+        sa.Column('access_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('user_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('collection_id', postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column('created_at', sa.DateTime(), nullable=False),
+        sa.ForeignKeyConstraint(['collection_id'], ['collections.collection_id'], ),
+        sa.ForeignKeyConstraint(['user_id'], ['users.user_id'], ),
+        sa.PrimaryKeyConstraint('access_id'),
+        sa.UniqueConstraint('user_id', 'collection_id', name='uq_user_collection')
+    )
+
+
+def downgrade() -> None:
+    op.drop_table('collection_access')
+    op.drop_table('messages')
+    op.drop_table('conversations')
+    op.drop_table('embeddings')
+    op.drop_table('documents')
+    op.drop_table('collections')
+    op.drop_index(op.f('ix_users_telegram_id'), table_name='users')
+    op.drop_table('users')
+

backend/src/presentation/main.py

@@ -0,0 +1,83 @@
+"""
+Главный файл FastAPI приложения
+"""
+import sys
+import os
+
+if '/app' not in sys.path:
+    sys.path.insert(0, '/app')
+
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from contextlib import asynccontextmanager
+from dishka.integrations.fastapi import setup_dishka
+from dishka import Container
+from src.shared.config import settings
+from src.shared.exceptions import LawyerAIException
+from src.shared.di_container import create_container
+from src.presentation.middleware.error_handler import exception_handler
+from src.presentation.api.v1 import users, collections, documents, conversations, messages
+from src.infrastructure.database.base import engine, Base
+
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    """Управление жизненным циклом приложения"""
+    container = create_container()
+    setup_dishka(container, app)
+    try:
+        async with engine.begin() as conn:
+            await conn.run_sync(Base.metadata.create_all)
+    except Exception as e:
+        print(f"Примечание при создании таблиц: {e}")
+    yield
+    await container.close()
+    await engine.dispose()
+
+
+app = FastAPI(
+    title=settings.APP_NAME,
+    description="API для системы ИИ-юриста",
+    version="1.0.0",
+    lifespan=lifespan
+)
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=settings.CORS_ORIGINS,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+app.add_exception_handler(LawyerAIException, exception_handler)
+
+app.include_router(users.router, prefix="/api/v1")
+app.include_router(collections.router, prefix="/api/v1")
+app.include_router(documents.router, prefix="/api/v1")
+app.include_router(conversations.router, prefix="/api/v1")
+app.include_router(messages.router, prefix="/api/v1")
+
+try:
+    from src.presentation.api.v1 import admin
+    app.include_router(admin.router, prefix="/api/v1")
+except (ImportError, AttributeError) as e:
+    print(f"Админ-панель не загружена: {e}")
+    pass
+
+
+@app.get("/")
+async def root():
+    """Корневой эндпоинт"""
+    return {
+        "message": "Добро пожаловать в API ИИ-юриста",
+        "version": "1.0.0",
+        "docs": "/docs"
+    }
+
+
+@app.get("/health")
+async def health_check():
+    """Проверка здоровья приложения"""
+    return {"status": "ok"}
+

backend/src/presentation/middleware/__init__.py

@@ -0,0 +1,4 @@
+"""
+Middleware
+"""
+

backend/src/presentation/middleware/auth_middleware.py

@@ -0,0 +1,50 @@
+"""
+Middleware для авторизации через Telegram бота
+
+Для Telegram бота авторизация простая:
+1. Бот получает user_id от Telegram в каждом сообщении
+2. Бот передает user_id на бэкенд в заголовке X-Telegram-ID
+3. Бэкенд идентифицирует пользователя по telegram_id
+"""
+from fastapi import HTTPException, Request
+from src.domain.entities.user import User
+from src.domain.repositories.user_repository import IUserRepository
+from src.domain.entities.user import UserRole
+
+
+async def get_current_user(
+    request: Request,
+    user_repo: IUserRepository
+) -> User:
+    """
+    Получить текущего пользователя по Telegram ID
+    
+    Telegram бот передает user_id в заголовке X-Telegram-ID.
+    Бэкенд идентифицирует пользователя по этому ID.
+    
+    Args:
+        request: FastAPI Request объект
+        user_repo: Репозиторий пользователей
+        
+    Returns:
+        Пользователь
+        
+    Raises:
+        HTTPException: Если не указан X-Telegram-ID
+    """
+    x_telegram_id = request.headers.get("X-Telegram-ID")
+    
+    if not x_telegram_id:
+        raise HTTPException(
+            status_code=401, 
+            detail="Не указан X-Telegram-ID. Бот должен передавать user_id в заголовке."
+        )
+    
+    user = await user_repo.get_by_telegram_id(x_telegram_id)
+    
+    if not user:
+        user = User(telegram_id=x_telegram_id, role=UserRole.USER)
+        user = await user_repo.create(user)
+    
+    return user
+

backend/src/presentation/middleware/error_handler.py

@@ -0,0 +1,36 @@
+"""
+Обработчик ошибок для FastAPI
+"""
+from fastapi import Request, status
+from fastapi.responses import JSONResponse
+from src.shared.exceptions import (
+    LawyerAIException,
+    NotFoundError,
+    UnauthorizedError,
+    ForbiddenError,
+    ValidationError,
+    DatabaseError
+)
+
+
+async def exception_handler(request: Request, exc: LawyerAIException) -> JSONResponse:
+    """Обработчик кастомных исключений"""
+    status_code = status.HTTP_500_INTERNAL_SERVER_ERROR
+    detail = str(exc)
+    
+    if isinstance(exc, NotFoundError):
+        status_code = status.HTTP_404_NOT_FOUND
+    elif isinstance(exc, UnauthorizedError):
+        status_code = status.HTTP_401_UNAUTHORIZED
+    elif isinstance(exc, ForbiddenError):
+        status_code = status.HTTP_403_FORBIDDEN
+    elif isinstance(exc, ValidationError):
+        status_code = status.HTTP_400_BAD_REQUEST
+    elif isinstance(exc, DatabaseError):
+        status_code = status.HTTP_500_INTERNAL_SERVER_ERROR
+    
+    return JSONResponse(
+        status_code=status_code,
+        content={"detail": detail, "type": exc.__class__.__name__}
+    )
+

backend/src/shared/di_container.py

@@ -0,0 +1,143 @@
+"""
+DI контейнер на основе dishka
+"""
+from dishka import Container, Provider, Scope, provide
+from fastapi import Request
+from sqlalchemy.ext.asyncio import AsyncSession
+from contextlib import asynccontextmanager
+
+from src.infrastructure.database.base import AsyncSessionLocal
+from src.infrastructure.repositories.postgresql.user_repository import PostgreSQLUserRepository
+from src.infrastructure.repositories.postgresql.collection_repository import PostgreSQLCollectionRepository
+from src.infrastructure.repositories.postgresql.document_repository import PostgreSQLDocumentRepository
+from src.infrastructure.repositories.postgresql.conversation_repository import PostgreSQLConversationRepository
+from src.infrastructure.repositories.postgresql.message_repository import PostgreSQLMessageRepository
+from src.infrastructure.repositories.postgresql.collection_access_repository import PostgreSQLCollectionAccessRepository
+from src.domain.repositories.user_repository import IUserRepository
+from src.domain.repositories.collection_repository import ICollectionRepository
+from src.domain.repositories.document_repository import IDocumentRepository
+from src.domain.repositories.conversation_repository import IConversationRepository
+from src.domain.repositories.message_repository import IMessageRepository
+from src.domain.repositories.collection_access_repository import ICollectionAccessRepository
+from src.infrastructure.external.yandex_ocr import YandexOCRService
+from src.infrastructure.external.deepseek_client import DeepSeekClient
+from src.application.services.document_parser_service import DocumentParserService
+from src.application.use_cases.user_use_cases import UserUseCases
+from src.application.use_cases.collection_use_cases import CollectionUseCases
+from src.application.use_cases.document_use_cases import DocumentUseCases
+from src.application.use_cases.conversation_use_cases import ConversationUseCases
+from src.application.use_cases.message_use_cases import MessageUseCases
+from src.domain.entities.user import User
+
+
+class DatabaseProvider(Provider):
+    @provide(scope=Scope.REQUEST)
+    @asynccontextmanager
+    async def get_db(self) -> AsyncSession:
+        async with AsyncSessionLocal() as session:
+            try:
+                yield session
+            finally:
+                await session.close()
+
+
+class RepositoryProvider(Provider):
+    @provide(scope=Scope.REQUEST)
+    def get_user_repository(self, session: AsyncSession) -> IUserRepository:
+        return PostgreSQLUserRepository(session)
+
+    @provide(scope=Scope.REQUEST)
+    def get_collection_repository(self, session: AsyncSession) -> ICollectionRepository:
+        return PostgreSQLCollectionRepository(session)
+
+    @provide(scope=Scope.REQUEST)
+    def get_document_repository(self, session: AsyncSession) -> IDocumentRepository:
+        return PostgreSQLDocumentRepository(session)
+
+    @provide(scope=Scope.REQUEST)
+    def get_conversation_repository(self, session: AsyncSession) -> IConversationRepository:
+        return PostgreSQLConversationRepository(session)
+
+    @provide(scope=Scope.REQUEST)
+    def get_message_repository(self, session: AsyncSession) -> IMessageRepository:
+        return PostgreSQLMessageRepository(session)
+
+    @provide(scope=Scope.REQUEST)
+    def get_collection_access_repository(self, session: AsyncSession) -> ICollectionAccessRepository:
+        return PostgreSQLCollectionAccessRepository(session)
+
+
+class ServiceProvider(Provider):
+    @provide(scope=Scope.APP)
+    def get_ocr_service(self) -> YandexOCRService:
+        return YandexOCRService()
+
+    @provide(scope=Scope.APP)
+    def get_deepseek_client(self) -> DeepSeekClient:
+        return DeepSeekClient()
+
+    @provide(scope=Scope.APP)
+    def get_parser_service(self, ocr_service: YandexOCRService) -> DocumentParserService:
+        return DocumentParserService(ocr_service)
+
+
+class AuthProvider(Provider):
+    @provide(scope=Scope.REQUEST)
+    async def get_current_user(self, request: Request, user_repo: IUserRepository) -> User:
+        from src.presentation.middleware.auth_middleware import get_current_user
+        return await get_current_user(request, user_repo)
+
+
+class UseCaseProvider(Provider):
+    @provide(scope=Scope.REQUEST)
+    def get_user_use_cases(
+        self,
+        user_repo: IUserRepository
+    ) -> UserUseCases:
+        return UserUseCases(user_repo)
+
+    @provide(scope=Scope.REQUEST)
+    def get_collection_use_cases(
+        self,
+        collection_repo: ICollectionRepository,
+        access_repo: ICollectionAccessRepository,
+        user_repo: IUserRepository
+    ) -> CollectionUseCases:
+        return CollectionUseCases(collection_repo, access_repo, user_repo)
+
+    @provide(scope=Scope.REQUEST)
+    def get_document_use_cases(
+        self,
+        document_repo: IDocumentRepository,
+        collection_repo: ICollectionRepository,
+        parser_service: DocumentParserService
+    ) -> DocumentUseCases:
+        return DocumentUseCases(document_repo, collection_repo, parser_service)
+
+    @provide(scope=Scope.REQUEST)
+    def get_conversation_use_cases(
+        self,
+        conversation_repo: IConversationRepository,
+        collection_repo: ICollectionRepository,
+        access_repo: ICollectionAccessRepository
+    ) -> ConversationUseCases:
+        return ConversationUseCases(conversation_repo, collection_repo, access_repo)
+
+    @provide(scope=Scope.REQUEST)
+    def get_message_use_cases(
+        self,
+        message_repo: IMessageRepository,
+        conversation_repo: IConversationRepository
+    ) -> MessageUseCases:
+        return MessageUseCases(message_repo, conversation_repo)
+
+
+def create_container() -> Container:
+    container = Container()
+    container.add_provider(DatabaseProvider())
+    container.add_provider(RepositoryProvider())
+    container.add_provider(ServiceProvider())
+    container.add_provider(AuthProvider())
+    container.add_provider(UseCaseProvider())
+    return container
+