20251217 #1 postgre sql 연결 및 테이블 생성

.coderabbit.yaml

@@ -0,0 +1,18 @@
+# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
+language: "ko-KR"
+early_access: false
+reviews:
+  profile: "chill"
+  request_changes_workflow: false
+  high_level_summary: true
+  poem: true
+  review_status: true
+  collapse_walkthrough: false
+  auto_review:
+    enabled: true
+    drafts: false
+    base_branches:
+      - main
+      - test
+chat:
+  auto_reply: true

.gitignore

@@ -85,6 +85,7 @@ celerybeat-schedule
 
 # Environments
 .env
+.env.*
 .venv
 env/
 venv/

app/config/database.py

@@ -1,2 +1,40 @@
-# 빈 파일 - DB 연결 설정
+from typing import AsyncGenerator
 
+from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine, AsyncEngine
+
+from app.config.settings import get_settings
+from app.utils.logger import logger
+
+_settings = get_settings()
+
+_engine = create_async_engine(
+  _settings.postgres_url,
+  pool_pre_ping=True,
+  echo=False,  # SQL 쿼리 로깅
+)
+
+_async_session_factory = async_sessionmaker(
+  bind=_engine,
+  expire_on_commit=False,
+  autoflush=False,
+)
+
+
+def get_async_engine() -> AsyncEngine:
+  return _engine
+
+
+def get_async_session_factory() -> async_sessionmaker[AsyncSession]:
+  return _async_session_factory
+
+
+async def get_async_session() -> AsyncGenerator[AsyncSession, None]:
+  async with _async_session_factory() as session:
+    try:
+      yield session
+    except Exception as e:
+      logger.error(f"Postgres DB 에러: {e}")
+      await session.rollback()
+      raise
+    finally:
+      await session.close()

app/config/settings.py

@@ -1,2 +1,47 @@
-# 빈 파일 - 환경 변수 설정
+from functools import lru_cache
 
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+
+class Settings(BaseSettings):
+  """
+  .env 에서 환경변수 로딩
+  """
+
+  model_config = SettingsConfigDict(
+    env_file=".env",
+    env_file_encoding="utf-8",
+    case_sensitive=False,
+    extra="ignore"
+  )
+
+  # GitHub API 설정
+  github_api_base_url: str
+  github_api_token: str | None = None
+
+  # Ollama 설정
+  ollama_base_url: str
+  ollama_api_key: str
+  ollama_model: str
+  ollama_timeout_seconds: int
+
+  # Qdrant 설정
+  qdrant_base_url: str
+  qdrant_collection: str
+  qdrant_api_key: str
+
+  # 텍스트 청크 설정
+  text_chunk_max_chars: int
+  text_chunk_overlap_chars: int
+  text_chunk_hard_max_chars: int
+
+  # 동시성 설정
+  concurrency_embedding_max_concurrency: int
+
+  # PostgreSQL 설정
+  postgres_url: str
+
+
+@lru_cache(maxsize=1)
+def get_settings() -> Settings:
+  return Settings()

app/db/init_db.py

@@ -0,0 +1,17 @@
+from sqlalchemy.ext.asyncio import AsyncEngine
+
+from app.models.base import Base
+from app.utils.logger import logger
+
+
+def _import_all_models() -> None:
+  from app.models.github_cursor import GithubCursorEntity
+
+
+async def create_tables_if_not_exists(engine: AsyncEngine) -> None:
+  _import_all_models()
+
+  async with engine.begin() as conn:
+    await conn.run_sync(Base.metadata.create_all)
+
+  logger.info("DB 테이블 생성완료")

app/main.py

@@ -1,8 +1,22 @@
+from contextlib import asynccontextmanager
 from typing import Dict
 
 from fastapi import FastAPI
 
-app = FastAPI()
+from app.config.database import get_async_engine
+from app.db.init_db import create_tables_if_not_exists
+from app.utils.logger import logger
+
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+  logger.info("ChatBot 애플리케이션 시작")
+  await create_tables_if_not_exists(get_async_engine())
+  yield
+  logger.info("애플리케이션 종료")
+
+
+app = FastAPI(lifespan=lifespan)
 
 
 @app.get("/health")

app/models/base.py

@@ -0,0 +1,43 @@
+import uuid
+from datetime import datetime
+
+from sqlalchemy import DateTime, func
+from sqlalchemy.dialects.postgresql.base import UUID
+from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column
+
+
+class Base(DeclarativeBase):
+  """
+  SQLAlchemy Declarative Base
+  - 모든 엔티티는 Base 상속
+  """
+  pass
+
+
+class TimestampMixin:
+  """
+  created_at, updated_at 자동 관리 Mixin
+  - created_at: DB 레벨 자동 설정
+  - updated_at: 애플리케이션 레벨에서 명시적 관리
+  """
+  created_at: Mapped[datetime] = mapped_column(
+    DateTime(timezone=True),
+    nullable=False,
+    server_default=func.now(),  # DB 레벨 - INSERT 시 자동
+  )
+
+  updated_at: Mapped[datetime] = mapped_column(
+    DateTime(timezone=True),
+    nullable=False,
+    server_default=func.now(),  # DB 레벨 - INSERT 시 자동
+  )
+
+class PrimaryKeyMixin:
+  """
+  UUID Primary Key Mixin
+  """
+  id: Mapped[uuid.UUID] = mapped_column(
+    UUID(as_uuid=True),
+    primary_key=True,
+    default=uuid.uuid4,
+  )

app/models/enums/source_type.py

@@ -0,0 +1,17 @@
+from enum import Enum
+
+
+class SourceType(str, Enum):
+  """
+  깃허브 임베딩 대상 SourceType
+  - Repository: 레포 파일/문서 (README 등)
+  - ISSUE: 이슈
+  - PULL_REQUEST: PR
+  - COMMIT: 커밋
+  - RELEASE: 릴리즈
+  """
+  REPOSITORY = "REPOSITORY"
+  ISSUE = "ISSUE"
+  PULL_REQUEST = "PULL_REQUEST"
+  COMMIT = "COMMIT"
+  RELEASE = "RELEASE"

app/models/github_cursor.py

@@ -0,0 +1,20 @@
+from sqlalchemy import Enum as SqlEnum
+from sqlalchemy import UniqueConstraint, Index, String
+from sqlalchemy.orm import Mapped, mapped_column
+
+from app.models.base import Base, PrimaryKeyMixin, TimestampMixin
+from app.models.enums.source_type import SourceType
+
+
+class GithubCursorEntity(Base, PrimaryKeyMixin, TimestampMixin):
+  __tablename__ = "github_cursor"
+  __table_args__ = (
+    UniqueConstraint("repository_name", "source_type", name="uq_github_cursor"),
+    Index("idx_github_cursor_repo_type", "repository_name", "source_type")
+  )
+
+  repository_name: Mapped[str] = mapped_column(String(200), nullable=False)
+
+  source_type: Mapped[SourceType] = mapped_column(SqlEnum(SourceType, native_enum=False), nullable=False)
+
+  cursor_value: Mapped[str] = mapped_column(String(500), nullable=False)

app/repositories/github_cursor_repository.py

@@ -0,0 +1,53 @@
+import uuid
+from typing import Optional
+
+from sqlalchemy import select, func
+from sqlalchemy.dialects.postgresql import insert
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.models.enums.source_type import SourceType
+from app.models.github_cursor import GithubCursorEntity
+
+
+class GithubCursorRepository:
+  async def find_by_repository_name_and_source_type(
+    self,
+    session: AsyncSession,
+    repository_name: str,
+    source_type: SourceType,
+  ) -> Optional[GithubCursorEntity]:
+    """
+    특정 repository + source_type 커서 조회
+    """
+    query = select(GithubCursorEntity).where(
+      GithubCursorEntity.repository_name == repository_name,
+      GithubCursorEntity.source_type == source_type,
+    )
+    result = await session.execute(query)
+    return result.scalar_one_or_none()
+
+  async def upsert(
+    self,
+    session: AsyncSession,
+    repository_name: str,
+    source_type: SourceType,
+    cursor_value: str,
+  ) -> GithubCursorEntity:
+    """
+    커서 upsert (없으면 생성, 있으면 업데이트)
+    """
+    query = insert(GithubCursorEntity).values(
+      id=uuid.uuid4(),
+      repository_name=repository_name,
+      source_type=source_type,
+      cursor_value=cursor_value,
+    ).on_conflict_do_update(
+      index_elements=["repository_name", "source_type"],
+      set_={
+        "cursor_value": cursor_value,
+        "updated_at": func.now(),
+      },
+    ).returning(GithubCursorEntity)
+
+    result = await session.execute(query)
+    return result.scalar_one()