267 lines
13 KiB
Python
267 lines
13 KiB
Python
"""PostgreSQL 数据库管理器 - 支持知识库和业务数据"""
|
||
|
||
import json
|
||
import os
|
||
from contextlib import asynccontextmanager
|
||
|
||
from sqlalchemy import text
|
||
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
|
||
from sqlalchemy.orm import declarative_base
|
||
from yuxi.storage.postgres.models_business import Base as BusinessBase
|
||
from yuxi.storage.postgres.models_knowledge import Base as KnowledgeBase
|
||
from yuxi.utils import logger
|
||
|
||
from server.utils.singleton import SingletonMeta
|
||
|
||
# 合并两个 Base
|
||
CombinedBase = declarative_base()
|
||
|
||
# 继承所有表
|
||
for module in [KnowledgeBase, BusinessBase]:
|
||
for table_name in dir(module):
|
||
table = getattr(module, table_name)
|
||
if isinstance(table, type) and hasattr(table, "__tablename__"):
|
||
setattr(CombinedBase, table_name, table)
|
||
|
||
|
||
class PostgresManager(metaclass=SingletonMeta):
|
||
"""PostgreSQL 数据库管理器 - 支持知识库和业务数据"""
|
||
|
||
# 知识库 PostgreSQL URL 环境变量名
|
||
KB_DATABASE_URL_ENV = "POSTGRES_URL"
|
||
|
||
def __init__(self):
|
||
self.async_engine = None
|
||
self.AsyncSession = None
|
||
self._initialized = False
|
||
|
||
def initialize(self):
|
||
"""初始化数据库连接"""
|
||
if self._initialized:
|
||
return
|
||
|
||
db_url = os.getenv(self.KB_DATABASE_URL_ENV)
|
||
if not db_url:
|
||
logger.error(
|
||
f"环境变量 {self.KB_DATABASE_URL_ENV} 未设置，"
|
||
"请在 docker-compose.yml 或 .env 中配置 PostgreSQL 连接字符串"
|
||
)
|
||
return
|
||
|
||
try:
|
||
# 创建异步 SQLAlchemy 引擎
|
||
self.async_engine = create_async_engine(
|
||
db_url,
|
||
json_serializer=lambda obj: json.dumps(obj, ensure_ascii=False),
|
||
json_deserializer=json.loads,
|
||
pool_pre_ping=True,
|
||
pool_recycle=1800,
|
||
)
|
||
|
||
# 创建异步会话工厂
|
||
self.AsyncSession = async_sessionmaker(
|
||
bind=self.async_engine,
|
||
class_=AsyncSession,
|
||
expire_on_commit=False,
|
||
)
|
||
|
||
self._initialized = True
|
||
logger.info(f"PostgreSQL manager initialized for knowledge base: {db_url.split('@')[0]}://***")
|
||
except Exception as e:
|
||
logger.error(f"Failed to initialize PostgreSQL manager: {e}")
|
||
# 不抛出异常，允许应用启动，但在使用时会报错
|
||
|
||
def _check_initialized(self):
|
||
"""检查是否已初始化"""
|
||
if not self._initialized:
|
||
raise RuntimeError("PostgreSQL manager not initialized. Please check configuration.")
|
||
|
||
async def create_tables(self):
|
||
"""创建所有表（知识库和业务表）"""
|
||
self._check_initialized()
|
||
async with self.async_engine.begin() as conn:
|
||
await conn.run_sync(KnowledgeBase.metadata.create_all)
|
||
await conn.run_sync(BusinessBase.metadata.create_all)
|
||
logger.info("PostgreSQL tables created/checked (knowledge + business)")
|
||
|
||
async def create_business_tables(self):
|
||
"""创建所有业务数据表"""
|
||
self._check_initialized()
|
||
async with self.async_engine.begin() as conn:
|
||
await conn.run_sync(BusinessBase.metadata.create_all)
|
||
logger.info("PostgreSQL business tables created/checked")
|
||
|
||
async def drop_tables(self):
|
||
"""删除所有表（慎用！）"""
|
||
self._check_initialized()
|
||
async with self.async_engine.begin() as conn:
|
||
await conn.run_sync(BusinessBase.metadata.drop_all)
|
||
await conn.run_sync(KnowledgeBase.metadata.drop_all)
|
||
logger.info("PostgreSQL tables dropped")
|
||
|
||
async def ensure_knowledge_schema(self):
|
||
"""确保知识库 schema 包含所有必要字段"""
|
||
self._check_initialized()
|
||
stmts = [
|
||
"ALTER TABLE IF EXISTS knowledge_bases ADD COLUMN IF NOT EXISTS embed_info JSONB",
|
||
"ALTER TABLE IF EXISTS knowledge_bases ADD COLUMN IF NOT EXISTS llm_info JSONB",
|
||
"ALTER TABLE IF EXISTS knowledge_bases ADD COLUMN IF NOT EXISTS query_params JSONB",
|
||
"ALTER TABLE IF EXISTS knowledge_bases ADD COLUMN IF NOT EXISTS additional_params JSONB",
|
||
"ALTER TABLE IF EXISTS knowledge_bases ADD COLUMN IF NOT EXISTS share_config JSONB",
|
||
"ALTER TABLE IF EXISTS knowledge_bases ADD COLUMN IF NOT EXISTS mindmap JSONB",
|
||
"ALTER TABLE IF EXISTS knowledge_bases ADD COLUMN IF NOT EXISTS sample_questions JSONB",
|
||
"ALTER TABLE IF EXISTS knowledge_bases ADD COLUMN IF NOT EXISTS updated_at TIMESTAMPTZ",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS parent_id VARCHAR(64)",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS original_filename VARCHAR(512)",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS file_type VARCHAR(64)",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS path VARCHAR(1024)",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS minio_url VARCHAR(1024)",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS markdown_file VARCHAR(1024)",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS status VARCHAR(32)",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS content_hash VARCHAR(128)",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS file_size BIGINT",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS content_type VARCHAR(64)",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS processing_params JSONB",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS is_folder BOOLEAN",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS error_message TEXT",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS created_by VARCHAR(64)",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS updated_by VARCHAR(64)",
|
||
"ALTER TABLE IF EXISTS knowledge_files ADD COLUMN IF NOT EXISTS updated_at TIMESTAMPTZ",
|
||
"ALTER TABLE IF EXISTS evaluation_benchmarks ADD COLUMN IF NOT EXISTS data_file_path VARCHAR(1024)",
|
||
"ALTER TABLE IF EXISTS evaluation_benchmarks ADD COLUMN IF NOT EXISTS created_by VARCHAR(64)",
|
||
"ALTER TABLE IF EXISTS evaluation_benchmarks ADD COLUMN IF NOT EXISTS updated_at TIMESTAMPTZ",
|
||
"ALTER TABLE IF EXISTS evaluation_results ADD COLUMN IF NOT EXISTS metrics JSONB",
|
||
"ALTER TABLE IF EXISTS evaluation_results ADD COLUMN IF NOT EXISTS overall_score DOUBLE PRECISION",
|
||
"ALTER TABLE IF EXISTS evaluation_results ADD COLUMN IF NOT EXISTS total_questions INTEGER",
|
||
"ALTER TABLE IF EXISTS evaluation_results ADD COLUMN IF NOT EXISTS completed_questions INTEGER",
|
||
"ALTER TABLE IF EXISTS evaluation_results ADD COLUMN IF NOT EXISTS started_at TIMESTAMPTZ",
|
||
"ALTER TABLE IF EXISTS evaluation_results ADD COLUMN IF NOT EXISTS completed_at TIMESTAMPTZ",
|
||
"ALTER TABLE IF EXISTS evaluation_results ADD COLUMN IF NOT EXISTS created_by VARCHAR(64)",
|
||
"ALTER TABLE IF EXISTS evaluation_result_details ADD COLUMN IF NOT EXISTS gold_chunk_ids JSONB",
|
||
"ALTER TABLE IF EXISTS evaluation_result_details ADD COLUMN IF NOT EXISTS gold_answer TEXT",
|
||
"ALTER TABLE IF EXISTS evaluation_result_details ADD COLUMN IF NOT EXISTS generated_answer TEXT",
|
||
"ALTER TABLE IF EXISTS evaluation_result_details ADD COLUMN IF NOT EXISTS retrieved_chunks JSONB",
|
||
"ALTER TABLE IF EXISTS evaluation_result_details ADD COLUMN IF NOT EXISTS metrics JSONB",
|
||
# 扩展 db_id 字段长度以支持最长 75 字符的 ID（kb_private_ + 64字符hash）
|
||
"ALTER TABLE IF EXISTS knowledge_bases ALTER COLUMN db_id TYPE VARCHAR(80)",
|
||
"ALTER TABLE IF EXISTS knowledge_files ALTER COLUMN db_id TYPE VARCHAR(80)",
|
||
"ALTER TABLE IF EXISTS evaluation_benchmarks ALTER COLUMN db_id TYPE VARCHAR(80)",
|
||
"ALTER TABLE IF EXISTS evaluation_results ALTER COLUMN db_id TYPE VARCHAR(80)",
|
||
"CREATE INDEX IF NOT EXISTS idx_kb_type ON knowledge_bases(kb_type)",
|
||
"CREATE INDEX IF NOT EXISTS idx_kb_name ON knowledge_bases(name)",
|
||
"CREATE INDEX IF NOT EXISTS idx_kf_db_id ON knowledge_files(db_id)",
|
||
"CREATE INDEX IF NOT EXISTS idx_kf_parent ON knowledge_files(parent_id)",
|
||
"CREATE INDEX IF NOT EXISTS idx_kf_status ON knowledge_files(status)",
|
||
"CREATE INDEX IF NOT EXISTS idx_kf_hash ON knowledge_files(content_hash)",
|
||
"CREATE INDEX IF NOT EXISTS idx_eb_db_id ON evaluation_benchmarks(db_id)",
|
||
"CREATE INDEX IF NOT EXISTS idx_er_db_id ON evaluation_results(db_id)",
|
||
"CREATE INDEX IF NOT EXISTS idx_er_status ON evaluation_results(status)",
|
||
"CREATE INDEX IF NOT EXISTS idx_er_started ON evaluation_results(started_at DESC)",
|
||
"CREATE INDEX IF NOT EXISTS idx_erd_task ON evaluation_result_details(task_id)",
|
||
]
|
||
|
||
async with self.async_engine.begin() as conn:
|
||
for stmt in stmts:
|
||
await conn.execute(text(stmt))
|
||
|
||
async def ensure_business_schema(self):
|
||
"""确保业务 schema 包含后续新增字段（兼容已存在表）。"""
|
||
self._check_initialized()
|
||
stmts = [
|
||
"ALTER TABLE IF EXISTS skills ADD COLUMN IF NOT EXISTS tool_dependencies JSONB DEFAULT '[]'::jsonb",
|
||
"ALTER TABLE IF EXISTS skills ADD COLUMN IF NOT EXISTS mcp_dependencies JSONB DEFAULT '[]'::jsonb",
|
||
"ALTER TABLE IF EXISTS skills ADD COLUMN IF NOT EXISTS skill_dependencies JSONB DEFAULT '[]'::jsonb",
|
||
"ALTER TABLE IF EXISTS conversations ADD COLUMN IF NOT EXISTS is_pinned BOOLEAN NOT NULL DEFAULT FALSE",
|
||
"ALTER TABLE IF EXISTS mcp_servers ADD COLUMN IF NOT EXISTS env JSONB",
|
||
"""
|
||
CREATE TABLE IF NOT EXISTS agent_runs (
|
||
id VARCHAR(64) PRIMARY KEY,
|
||
thread_id VARCHAR(64) NOT NULL,
|
||
agent_id VARCHAR(64) NOT NULL,
|
||
user_id VARCHAR(64) NOT NULL,
|
||
status VARCHAR(32) NOT NULL DEFAULT 'pending',
|
||
request_id VARCHAR(64) NOT NULL UNIQUE,
|
||
input_payload JSONB NOT NULL DEFAULT '{}'::jsonb,
|
||
error_type VARCHAR(64),
|
||
error_message TEXT,
|
||
started_at TIMESTAMPTZ,
|
||
finished_at TIMESTAMPTZ,
|
||
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
|
||
updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
|
||
)
|
||
""",
|
||
"CREATE INDEX IF NOT EXISTS idx_agent_runs_user_created ON agent_runs(user_id, created_at DESC)",
|
||
"CREATE INDEX IF NOT EXISTS idx_agent_runs_thread_created ON agent_runs(thread_id, created_at DESC)",
|
||
"CREATE INDEX IF NOT EXISTS idx_agent_runs_status_updated ON agent_runs(status, updated_at)",
|
||
"CREATE INDEX IF NOT EXISTS ix_conversations_is_pinned ON conversations(is_pinned)",
|
||
]
|
||
async with self.async_engine.begin() as conn:
|
||
for stmt in stmts:
|
||
await conn.execute(text(stmt))
|
||
|
||
@property
|
||
def is_postgresql(self) -> bool:
|
||
"""检查是否是 PostgreSQL 数据库"""
|
||
if not self._initialized:
|
||
return False
|
||
return self.async_engine.dialect.name == "postgresql"
|
||
|
||
async def get_async_session(self) -> AsyncSession:
|
||
"""获取异步数据库会话"""
|
||
self._check_initialized()
|
||
return self.AsyncSession()
|
||
|
||
@asynccontextmanager
|
||
async def get_async_session_context(self):
|
||
"""获取异步数据库会话的上下文管理器"""
|
||
self._check_initialized()
|
||
session = self.AsyncSession()
|
||
try:
|
||
yield session
|
||
await session.commit()
|
||
except Exception as e:
|
||
await session.rollback()
|
||
logger.error(f"PostgreSQL async operation failed: {e}")
|
||
raise
|
||
finally:
|
||
await session.close()
|
||
|
||
async def close(self):
|
||
"""关闭引擎"""
|
||
if self.async_engine:
|
||
await self.async_engine.dispose()
|
||
|
||
async def async_check_first_run(self):
|
||
"""检查是否首次运行（异步版本）- 检查用户表是否有数据"""
|
||
from sqlalchemy import func, select
|
||
|
||
self._check_initialized()
|
||
async with self.get_async_session_context() as session:
|
||
from yuxi.storage.postgres.models_business import User
|
||
|
||
result = await session.execute(select(func.count(User.id)))
|
||
count = result.scalar()
|
||
return count == 0
|
||
|
||
async def execute(self, statement):
|
||
"""直接执行 SQL 语句（用于迁移脚本）"""
|
||
self._check_initialized()
|
||
async with self.get_async_session_context() as session:
|
||
return await session.execute(statement)
|
||
|
||
async def add(self, instance):
|
||
"""添加实例到会话（用于迁移脚本）"""
|
||
self._check_initialized()
|
||
async with self.get_async_session_context() as session:
|
||
session.add(instance)
|
||
|
||
async def commit(self):
|
||
"""提交当前会话"""
|
||
self._check_initialized()
|
||
async with self.get_async_session_context():
|
||
pass # commit is automatic in context manager
|
||
|
||
|
||
# 创建全局 PostgreSQL 管理器实例
|
||
pg_manager = PostgresManager()
|