删除两个节点，统一graph视图，修改windows日志.

agent/citu_agent.py

@@ -40,146 +40,48 @@ class CituLangGraphAgent:
         self.logger.info("LangGraph Agent with Direct Tools初始化完成")
     
     def _create_workflow(self, routing_mode: str = None) -> StateGraph:
-        """根据路由模式创建不同的工作流"""
-        self.logger.info(f"🏗️ [WORKFLOW] 动态创建workflow被调用")
-        
-        # 确定使用的路由模式
-        if routing_mode:
-            QUESTION_ROUTING_MODE = routing_mode
-            self.logger.info(f"使用传入的路由模式: {QUESTION_ROUTING_MODE}")
-        else:
-            try:
-                from app_config import QUESTION_ROUTING_MODE
-                self.logger.info(f"使用配置文件路由模式: {QUESTION_ROUTING_MODE}")
-            except ImportError:
-                QUESTION_ROUTING_MODE = "hybrid"
-                self.logger.warning(f"配置导入失败，使用默认路由模式: {QUESTION_ROUTING_MODE}")
+        """创建统一的工作流，所有路由模式都通过classify_question进行分类"""
+        self.logger.info(f"🏗️ [WORKFLOW] 创建统一workflow")
         
         workflow = StateGraph(AgentState)
         
-        # 根据路由模式创建不同的工作流
-        if QUESTION_ROUTING_MODE == "database_direct":
-            # 直接数据库模式：跳过分类，直接进入数据库处理（使用新的拆分节点）
-            workflow.add_node("init_direct_database", self._init_direct_database_node)
-            workflow.add_node("agent_sql_generation", self._agent_sql_generation_node)
-            workflow.add_node("agent_sql_execution", self._agent_sql_execution_node)
-            workflow.add_node("format_response", self._format_response_node)
-            
-            workflow.set_entry_point("init_direct_database")
-            
-            # 添加条件路由
-            workflow.add_edge("init_direct_database", "agent_sql_generation")
-            workflow.add_conditional_edges(
-                "agent_sql_generation",
-                self._route_after_sql_generation,
-                {
-                    "continue_execution": "agent_sql_execution",
-                    "return_to_user": "format_response"
-                }
-            )
-            workflow.add_edge("agent_sql_execution", "format_response")
-            workflow.add_edge("format_response", END)
-            
-        elif QUESTION_ROUTING_MODE == "chat_direct":
-            # 直接聊天模式：跳过分类，直接进入聊天处理
-            workflow.add_node("init_direct_chat", self._init_direct_chat_node)
-            workflow.add_node("agent_chat", self._agent_chat_node)
-            workflow.add_node("format_response", self._format_response_node)
-            
-            workflow.set_entry_point("init_direct_chat")
-            workflow.add_edge("init_direct_chat", "agent_chat")
-            workflow.add_edge("agent_chat", "format_response")
-            workflow.add_edge("format_response", END)
-            
-        else:
-            self.logger.info(f"🧠 [WORKFLOW] 构建hybrid模式的workflow...")
-            # 其他模式(hybrid, llm_only)：使用新的拆分工作流
-            workflow.add_node("classify_question", self._classify_question_node)
-            workflow.add_node("agent_chat", self._agent_chat_node)
-            workflow.add_node("agent_sql_generation", self._agent_sql_generation_node)
-            workflow.add_node("agent_sql_execution", self._agent_sql_execution_node)
-            workflow.add_node("format_response", self._format_response_node)
-            
-            workflow.set_entry_point("classify_question")
-            
-            # 添加条件边：分类后的路由
-            workflow.add_conditional_edges(
-                "classify_question",
-                self._route_after_classification,
-                {
-                    "DATABASE": "agent_sql_generation",
-                    "CHAT": "agent_chat"
-                }
-            )
-            
-            # 添加条件边：SQL生成后的路由
-            workflow.add_conditional_edges(
-                "agent_sql_generation",
-                self._route_after_sql_generation,
-                {
-                    "continue_execution": "agent_sql_execution",
-                    "return_to_user": "format_response"
-                }
-            )
-            
-            # 普通边
-            workflow.add_edge("agent_chat", "format_response")
-            workflow.add_edge("agent_sql_execution", "format_response")
-            workflow.add_edge("format_response", END)
+        # 统一的工作流结构 - 所有模式都使用相同的节点和路由
+        workflow.add_node("classify_question", self._classify_question_node)
+        workflow.add_node("agent_chat", self._agent_chat_node) 
+        workflow.add_node("agent_sql_generation", self._agent_sql_generation_node)
+        workflow.add_node("agent_sql_execution", self._agent_sql_execution_node)
+        workflow.add_node("format_response", self._format_response_node)
+        
+        # 统一入口点
+        workflow.set_entry_point("classify_question")
+        
+        # 添加条件边：分类后的路由
+        workflow.add_conditional_edges(
+            "classify_question",
+            self._route_after_classification,
+            {
+                "DATABASE": "agent_sql_generation",
+                "CHAT": "agent_chat"
+            }
+        )
+        
+        # 添加条件边：SQL生成后的路由
+        workflow.add_conditional_edges(
+            "agent_sql_generation", 
+            self._route_after_sql_generation,
+            {
+                "continue_execution": "agent_sql_execution",
+                "return_to_user": "format_response"
+            }
+        )
+        
+        # 普通边
+        workflow.add_edge("agent_chat", "format_response")
+        workflow.add_edge("agent_sql_execution", "format_response") 
+        workflow.add_edge("format_response", END)
         
         return workflow.compile()
-    
-    def _init_direct_database_node(self, state: AgentState) -> AgentState:
-        """初始化直接数据库模式的状态"""
-        try:
-            # 从state中获取路由模式，而不是从配置文件读取
-            routing_mode = state.get("routing_mode", "database_direct")
-            
-            # 设置直接数据库模式的分类状态
-            state["question_type"] = "DATABASE"
-            state["classification_confidence"] = 1.0
-            state["classification_reason"] = "配置为直接数据库查询模式"
-            state["classification_method"] = "direct_database"
-            state["routing_mode"] = routing_mode
-            state["current_step"] = "direct_database_init"
-            state["execution_path"].append("init_direct_database")
-            
-            self.logger.info("直接数据库模式初始化完成")
-            
-            return state
-            
-        except Exception as e:
-            self.logger.error(f"直接数据库模式初始化异常: {str(e)}")
-            state["error"] = f"直接数据库模式初始化失败: {str(e)}"
-            state["error_code"] = 500
-            state["execution_path"].append("init_direct_database_error")
-            return state
 
-    def _init_direct_chat_node(self, state: AgentState) -> AgentState:
-        """初始化直接聊天模式的状态"""
-        try:
-            # 从state中获取路由模式，而不是从配置文件读取
-            routing_mode = state.get("routing_mode", "chat_direct")
-            
-            # 设置直接聊天模式的分类状态
-            state["question_type"] = "CHAT"
-            state["classification_confidence"] = 1.0
-            state["classification_reason"] = "配置为直接聊天模式"
-            state["classification_method"] = "direct_chat"
-            state["routing_mode"] = routing_mode
-            state["current_step"] = "direct_chat_init"
-            state["execution_path"].append("init_direct_chat")
-            
-            self.logger.info("直接聊天模式初始化完成")
-            
-            return state
-            
-        except Exception as e:
-            self.logger.error(f"直接聊天模式初始化异常: {str(e)}")
-            state["error"] = f"直接聊天模式初始化失败: {str(e)}"
-            state["error_code"] = 500
-            state["execution_path"].append("init_direct_chat_error")
-            return state
     
     def _classify_question_node(self, state: AgentState) -> AgentState:
         """问题分类节点 - 支持渐进式分类策略"""

config/logging_config_backup_20250725_181936.yaml

@@ -0,0 +1,110 @@
+version: 1
+
+# 全局配置
+global:
+  base_level: INFO
+  
+# 默认配置（用于app.log）
+default:
+  level: INFO
+  console:
+    enabled: true
+    level: INFO
+    format: "%(asctime)s [%(levelname)s] %(name)s: %(message)s"
+  file:
+    enabled: true
+    level: DEBUG
+    filename: "app.log"
+    format: "%(asctime)s [%(levelname)s] [%(name)s] %(filename)s:%(lineno)d - %(message)s"
+    rotation:
+      enabled: true
+      when: "midnight"
+      interval: 1
+      backup_count: 30
+
+# 模块特定配置
+modules:
+  app:
+    level: INFO
+    console:
+      enabled: true
+      level: INFO
+      format: "%(asctime)s [%(levelname)s] %(name)s: %(message)s"
+    file:
+      enabled: true
+      level: DEBUG
+      filename: "app.log"
+      format: "%(asctime)s [%(levelname)s] [%(name)s] %(filename)s:%(lineno)d - %(message)s"
+      rotation:
+        enabled: true
+        when: "midnight"
+        interval: 1
+        backup_count: 30
+  
+  data_pipeline:
+    level: DEBUG
+    console:
+      enabled: true
+      level: INFO
+      format: "%(asctime)s [%(levelname)s] Pipeline: %(message)s"
+    file:
+      enabled: true
+      level: DEBUG
+      filename: "data_pipeline.log"
+      format: "%(asctime)s [%(levelname)s] [%(name)s] %(filename)s:%(lineno)d - %(message)s"
+      rotation:
+        enabled: true
+        when: "midnight"
+        interval: 1
+        backup_count: 30
+  
+  agent:
+    level: DEBUG
+    console:
+      enabled: true
+      level: INFO
+      format: "%(asctime)s [%(levelname)s] Agent: %(message)s"
+    file:
+      enabled: true
+      level: DEBUG
+      filename: "agent.log"
+      format: "%(asctime)s [%(levelname)s] [%(name)s] %(filename)s:%(lineno)d - %(message)s"
+      rotation:
+        enabled: true
+        when: "H"
+        interval: 24
+        backup_count: 7
+  
+  vanna:
+    level: DEBUG
+    console:
+      enabled: true
+      level: INFO
+      format: "%(asctime)s [%(levelname)s] Vanna: %(message)s"
+    file:
+      enabled: true
+      level: DEBUG
+      filename: "vanna.log"
+      format: "%(asctime)s [%(levelname)s] [%(name)s] %(filename)s:%(lineno)d - %(message)s"
+      rotation:
+        enabled: true
+        when: "midnight"
+        interval: 1
+        backup_count: 30
+  
+  react_agent:
+    level: DEBUG
+    console:
+      enabled: true
+      level: INFO
+      format: "%(asctime)s [%(levelname)s] ReactAgent: %(message)s"
+    file:
+      enabled: true
+      level: DEBUG
+      filename: "react_agent.log"
+      format: "%(asctime)s [%(levelname)s] [%(name)s] %(filename)s:%(lineno)d - %(message)s"
+      rotation:
+        enabled: true
+        when: "midnight"
+        interval: 1
+        backup_count: 30 

config/logging_config_windows.yaml

@@ -0,0 +1,104 @@
+version: 1
+
+# 全局配置
+global:
+  base_level: INFO
+  
+# 默认配置（用于app.log）
+default:
+  level: INFO
+  console:
+    enabled: true
+    level: INFO
+    format: "%(asctime)s [%(levelname)s] %(name)s: %(message)s"
+  file:
+    enabled: true
+    level: DEBUG
+    filename: "app.log"
+    format: "%(asctime)s [%(levelname)s] [%(name)s] %(filename)s:%(lineno)d - %(message)s"
+    rotation:
+      enabled: true
+      max_size: "10MB"
+      backup_count: 5
+
+# 模块特定配置
+modules:
+  app:
+    level: INFO
+    console:
+      enabled: true
+      level: INFO
+      format: "%(asctime)s [%(levelname)s] %(name)s: %(message)s"
+    file:
+      enabled: true
+      level: DEBUG
+      filename: "app.log"
+      format: "%(asctime)s [%(levelname)s] [%(name)s] %(filename)s:%(lineno)d - %(message)s"
+      rotation:
+        enabled: true
+        max_size: "10MB"
+        backup_count: 5
+  
+  data_pipeline:
+    level: DEBUG
+    console:
+      enabled: true
+      level: INFO
+      format: "%(asctime)s [%(levelname)s] Pipeline: %(message)s"
+    file:
+      enabled: true
+      level: DEBUG
+      filename: "data_pipeline.log"
+      format: "%(asctime)s [%(levelname)s] [%(name)s] %(filename)s:%(lineno)d - %(message)s"
+      rotation:
+        enabled: true
+        max_size: "10MB"
+        backup_count: 5
+  
+  agent:
+    level: DEBUG
+    console:
+      enabled: true
+      level: INFO
+      format: "%(asctime)s [%(levelname)s] Agent: %(message)s"
+    file:
+      enabled: true
+      level: DEBUG
+      filename: "agent.log"
+      format: "%(asctime)s [%(levelname)s] [%(name)s] %(filename)s:%(lineno)d - %(message)s"
+      rotation:
+        enabled: true
+        max_size: "10MB"
+        backup_count: 5
+  
+  vanna:
+    level: DEBUG
+    console:
+      enabled: true
+      level: INFO
+      format: "%(asctime)s [%(levelname)s] Vanna: %(message)s"
+    file:
+      enabled: true
+      level: DEBUG
+      filename: "vanna.log"
+      format: "%(asctime)s [%(levelname)s] [%(name)s] %(filename)s:%(lineno)d - %(message)s"
+      rotation:
+        enabled: true
+        max_size: "10MB"
+        backup_count: 5
+  
+  react_agent:
+    level: DEBUG
+    console:
+      enabled: true
+      level: INFO
+      format: "%(asctime)s [%(levelname)s] ReactAgent: %(message)s"
+    file:
+      enabled: true
+      level: DEBUG
+      filename: "react_agent.log"
+      format: "%(asctime)s [%(levelname)s] [%(name)s] %(filename)s:%(lineno)d - %(message)s"
+      rotation:
+        enabled: true
+        max_size: "10MB"
+        backup_count: 5 

core/logging/__init__.py

@@ -1,11 +1,37 @@
 from .log_manager import LogManager
 import logging
+import platform
+import os
 
 # 全局日志管理器实例
 _log_manager = LogManager()
 
-def initialize_logging(config_path: str = "config/logging_config.yaml"):
-    """初始化项目日志系统"""
+def get_platform_specific_config_path() -> str:
+    """根据操作系统自动选择合适的日志配置文件"""
+    if platform.system() == "Windows":
+        config_path = "config/logging_config_windows.yaml"
+    else:
+        config_path = "config/logging_config.yaml"
+    
+    # 检查配置文件是否存在，如果不存在则回退到默认配置
+    if not os.path.exists(config_path):
+        fallback_path = "config/logging_config.yaml"
+        if os.path.exists(fallback_path):
+            return fallback_path
+        else:
+            raise FileNotFoundError(f"日志配置文件不存在: {config_path} 和 {fallback_path}")
+    
+    return config_path
+
+def initialize_logging(config_path: str = None):
+    """初始化项目日志系统
+    
+    Args:
+        config_path: 可选的配置文件路径。如果不提供，将根据操作系统自动选择
+    """
+    if config_path is None:
+        config_path = get_platform_specific_config_path()
+    
     _log_manager.initialize(config_path)
 
 def get_logger(name: str, module: str = "default") -> logging.Logger:

logs/app.log.2025-07-21

@@ -1,360 +0,0 @@
-2025-07-21 08:21:18 [INFO] [app.UnifiedApp] unified_api.py:2771 - 接收到信号 2，准备退出...
-2025-07-21 08:21:18 [ERROR] [app.UnifiedApp] unified_api.py:521 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-21 08:21:57 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 08:21:57 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 08:21:57 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 08:21:57 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 08:21:57 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 08:21:57 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 08:21:57 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 08:21:59 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-21 08:21:59 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 08:21:59 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 08:21:59 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 08:21:59 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 08:21:59 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 08:21:59 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 08:21:59 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 08:22:01 [INFO] [app.UnifiedApp] unified_api.py:2780 - 🚀 启动统一API服务...
-2025-07-21 08:22:01 [INFO] [app.UnifiedApp] unified_api.py:2781 - 📍 服务地址: http://localhost:8084
-2025-07-21 08:22:01 [INFO] [app.UnifiedApp] unified_api.py:2782 - 🔗 健康检查: http://localhost:8084/health
-2025-07-21 08:22:01 [INFO] [app.UnifiedApp] unified_api.py:2783 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-21 08:22:01 [INFO] [app.UnifiedApp] unified_api.py:2784 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-21 08:22:01 [INFO] [app.UnifiedApp] unified_api.py:2791 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-21 08:22:01 [INFO] [app.UnifiedApp] unified_api.py:2792 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-21 08:30:25 [INFO] [app.UnifiedApp] unified_api.py:2771 - 接收到信号 2，准备退出...
-2025-07-21 08:30:25 [ERROR] [app.UnifiedApp] unified_api.py:521 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-21 08:31:38 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 08:31:38 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 08:31:38 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 08:31:38 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 08:31:38 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 08:31:38 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 08:31:38 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 08:31:40 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-21 08:31:40 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 08:31:40 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 08:31:40 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 08:31:40 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 08:31:40 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 08:31:40 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 08:31:40 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 08:31:42 [INFO] [app.UnifiedApp] unified_api.py:2780 - 🚀 启动统一API服务...
-2025-07-21 08:31:42 [INFO] [app.UnifiedApp] unified_api.py:2781 - 📍 服务地址: http://localhost:8084
-2025-07-21 08:31:42 [INFO] [app.UnifiedApp] unified_api.py:2782 - 🔗 健康检查: http://localhost:8084/health
-2025-07-21 08:31:42 [INFO] [app.UnifiedApp] unified_api.py:2783 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-21 08:31:42 [INFO] [app.UnifiedApp] unified_api.py:2784 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-21 08:31:42 [INFO] [app.UnifiedApp] unified_api.py:2791 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-21 08:31:42 [INFO] [app.UnifiedApp] unified_api.py:2792 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-21 08:34:45 [INFO] [app.UnifiedApp] unified_api.py:2771 - 接收到信号 2，准备退出...
-2025-07-21 08:34:45 [ERROR] [app.UnifiedApp] unified_api.py:521 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-21 08:35:04 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 08:35:04 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 08:35:04 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 08:35:04 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 08:35:04 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 08:35:04 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 08:35:04 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 08:35:06 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-21 08:35:06 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 08:35:06 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 08:35:06 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 08:35:06 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 08:35:06 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 08:35:06 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 08:35:06 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 08:35:08 [INFO] [app.UnifiedApp] unified_api.py:4421 - 🚀 启动统一API服务...
-2025-07-21 08:35:08 [INFO] [app.UnifiedApp] unified_api.py:4422 - 📍 服务地址: http://localhost:8084
-2025-07-21 08:35:08 [INFO] [app.UnifiedApp] unified_api.py:4423 - 🔗 健康检查: http://localhost:8084/health
-2025-07-21 08:35:08 [INFO] [app.UnifiedApp] unified_api.py:4424 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-21 08:35:08 [INFO] [app.UnifiedApp] unified_api.py:4425 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-21 08:35:08 [INFO] [app.UnifiedApp] unified_api.py:4432 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-21 08:35:08 [INFO] [app.UnifiedApp] unified_api.py:4433 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-21 09:07:50 [INFO] [app.UnifiedApp] unified_api.py:4412 - 接收到信号 2，准备退出...
-2025-07-21 09:07:50 [ERROR] [app.UnifiedApp] unified_api.py:521 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-21 09:08:07 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 09:08:07 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 09:08:07 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 09:08:07 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 09:08:07 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 09:08:07 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 09:08:07 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 09:08:09 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-21 09:08:09 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 09:08:09 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 09:08:09 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 09:08:09 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 09:08:09 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 09:08:09 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 09:08:09 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 09:08:11 [INFO] [app.UnifiedApp] unified_api.py:4421 - 🚀 启动统一API服务...
-2025-07-21 09:08:11 [INFO] [app.UnifiedApp] unified_api.py:4422 - 📍 服务地址: http://localhost:8084
-2025-07-21 09:08:11 [INFO] [app.UnifiedApp] unified_api.py:4423 - 🔗 健康检查: http://localhost:8084/health
-2025-07-21 09:08:11 [INFO] [app.UnifiedApp] unified_api.py:4424 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-21 09:08:11 [INFO] [app.UnifiedApp] unified_api.py:4425 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-21 09:08:11 [INFO] [app.UnifiedApp] unified_api.py:4432 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-21 09:08:11 [INFO] [app.UnifiedApp] unified_api.py:4433 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-21 09:18:48 [INFO] [app.UnifiedApp] unified_api.py:3141 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_083557 --execution-mode complete
-2025-07-21 09:18:49 [INFO] [app.UnifiedApp] unified_api.py:3152 - 任务进程已启动: PID=31888, task_id=task_20250721_083557
-2025-07-21 09:49:07 [INFO] [app.UnifiedApp] unified_api.py:4412 - 接收到信号 2，准备退出...
-2025-07-21 09:49:07 [ERROR] [app.UnifiedApp] unified_api.py:521 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-21 09:49:24 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 09:49:24 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 09:49:24 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 09:49:24 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 09:49:24 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 09:49:24 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 09:49:24 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 09:49:27 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-21 09:49:27 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 09:49:27 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 09:49:27 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 09:49:27 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 09:49:27 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 09:49:27 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 09:49:27 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 09:49:28 [INFO] [app.UnifiedApp] unified_api.py:4421 - 🚀 启动统一API服务...
-2025-07-21 09:49:28 [INFO] [app.UnifiedApp] unified_api.py:4422 - 📍 服务地址: http://localhost:8084
-2025-07-21 09:49:28 [INFO] [app.UnifiedApp] unified_api.py:4423 - 🔗 健康检查: http://localhost:8084/health
-2025-07-21 09:49:28 [INFO] [app.UnifiedApp] unified_api.py:4424 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-21 09:49:28 [INFO] [app.UnifiedApp] unified_api.py:4425 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-21 09:49:28 [INFO] [app.UnifiedApp] unified_api.py:4432 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-21 09:49:28 [INFO] [app.UnifiedApp] unified_api.py:4433 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-21 11:28:18 [INFO] [app.UnifiedApp] unified_api.py:4412 - 接收到信号 2，准备退出...
-2025-07-21 11:28:18 [ERROR] [app.UnifiedApp] unified_api.py:521 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-21 11:28:44 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 11:28:44 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 11:28:44 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 11:28:44 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 11:28:44 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 11:28:44 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 11:28:44 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 11:28:47 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-21 11:28:47 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 11:28:47 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 11:28:47 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 11:28:47 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 11:28:47 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 11:28:47 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 11:28:47 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 11:28:49 [INFO] [app.UnifiedApp] unified_api.py:4421 - 🚀 启动统一API服务...
-2025-07-21 11:28:49 [INFO] [app.UnifiedApp] unified_api.py:4422 - 📍 服务地址: http://localhost:8084
-2025-07-21 11:28:49 [INFO] [app.UnifiedApp] unified_api.py:4423 - 🔗 健康检查: http://localhost:8084/health
-2025-07-21 11:28:49 [INFO] [app.UnifiedApp] unified_api.py:4424 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-21 11:28:49 [INFO] [app.UnifiedApp] unified_api.py:4425 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-21 11:28:49 [INFO] [app.UnifiedApp] unified_api.py:4432 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-21 11:28:49 [INFO] [app.UnifiedApp] unified_api.py:4433 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-21 11:36:52 [INFO] [app.UnifiedApp] unified_api.py:3141 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_113010 --execution-mode complete
-2025-07-21 11:36:52 [INFO] [app.UnifiedApp] unified_api.py:3152 - 任务进程已启动: PID=13848, task_id=task_20250721_113010
-2025-07-21 11:43:42 [INFO] [app.UnifiedApp] unified_api.py:4412 - 接收到信号 2，准备退出...
-2025-07-21 11:43:42 [ERROR] [app.UnifiedApp] unified_api.py:521 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-21 11:53:52 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 11:53:52 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 11:53:52 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 11:53:52 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 11:53:52 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 11:53:52 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 11:53:52 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 11:53:54 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-21 11:53:54 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 11:53:54 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 11:53:54 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 11:53:54 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 11:53:54 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 11:53:54 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 11:53:54 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 11:53:56 [INFO] [app.UnifiedApp] unified_api.py:4421 - 🚀 启动统一API服务...
-2025-07-21 11:53:56 [INFO] [app.UnifiedApp] unified_api.py:4422 - 📍 服务地址: http://localhost:8084
-2025-07-21 11:53:56 [INFO] [app.UnifiedApp] unified_api.py:4423 - 🔗 健康检查: http://localhost:8084/health
-2025-07-21 11:53:56 [INFO] [app.UnifiedApp] unified_api.py:4424 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-21 11:53:56 [INFO] [app.UnifiedApp] unified_api.py:4425 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-21 11:53:56 [INFO] [app.UnifiedApp] unified_api.py:4432 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-21 11:53:56 [INFO] [app.UnifiedApp] unified_api.py:4433 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-21 11:54:28 [INFO] [app.UnifiedApp] unified_api.py:3141 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_113010 --execution-mode complete
-2025-07-21 11:54:28 [INFO] [app.UnifiedApp] unified_api.py:3152 - 任务进程已启动: PID=45604, task_id=task_20250721_113010
-2025-07-21 12:01:49 [INFO] [app.UnifiedApp] unified_api.py:4412 - 接收到信号 2，准备退出...
-2025-07-21 12:01:49 [ERROR] [app.UnifiedApp] unified_api.py:521 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-21 12:02:06 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 12:02:06 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 12:02:06 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 12:02:06 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 12:02:06 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 12:02:06 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 12:02:06 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 12:02:08 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-21 12:02:08 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 12:02:08 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 12:02:08 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 12:02:08 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 12:02:08 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 12:02:08 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 12:02:08 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 12:02:10 [INFO] [app.UnifiedApp] unified_api.py:4421 - 🚀 启动统一API服务...
-2025-07-21 12:02:10 [INFO] [app.UnifiedApp] unified_api.py:4422 - 📍 服务地址: http://localhost:8084
-2025-07-21 12:02:10 [INFO] [app.UnifiedApp] unified_api.py:4423 - 🔗 健康检查: http://localhost:8084/health
-2025-07-21 12:02:10 [INFO] [app.UnifiedApp] unified_api.py:4424 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-21 12:02:10 [INFO] [app.UnifiedApp] unified_api.py:4425 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-21 12:02:10 [INFO] [app.UnifiedApp] unified_api.py:4432 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-21 12:02:10 [INFO] [app.UnifiedApp] unified_api.py:4433 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-21 12:02:19 [INFO] [app.UnifiedApp] unified_api.py:3141 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_113010 --execution-mode complete
-2025-07-21 12:02:19 [INFO] [app.UnifiedApp] unified_api.py:3152 - 任务进程已启动: PID=26376, task_id=task_20250721_113010
-2025-07-21 12:20:29 [INFO] [app.UnifiedApp] unified_api.py:3141 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_113010 --execution-mode complete
-2025-07-21 12:20:29 [INFO] [app.UnifiedApp] unified_api.py:3152 - 任务进程已启动: PID=44784, task_id=task_20250721_113010
-2025-07-21 18:36:33 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 18:36:33 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 18:36:33 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 18:36:33 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 18:36:33 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 18:36:33 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 18:36:33 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 18:37:42 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 18:37:42 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 18:37:42 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 18:37:42 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 18:37:42 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 18:37:42 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 18:37:42 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 18:37:43 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-21 18:37:43 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 18:37:43 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 18:37:43 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 18:37:43 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 18:37:43 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 18:37:43 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 18:37:43 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 18:37:45 [INFO] [app.UnifiedApp] unified_api.py:4448 - 🚀 启动统一API服务...
-2025-07-21 18:37:45 [INFO] [app.UnifiedApp] unified_api.py:4449 - 📍 服务地址: http://localhost:8084
-2025-07-21 18:37:45 [INFO] [app.UnifiedApp] unified_api.py:4450 - 🔗 健康检查: http://localhost:8084/health
-2025-07-21 18:37:45 [INFO] [app.UnifiedApp] unified_api.py:4451 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-21 18:37:45 [INFO] [app.UnifiedApp] unified_api.py:4452 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-21 18:37:45 [INFO] [app.UnifiedApp] unified_api.py:4459 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-21 18:37:45 [INFO] [app.UnifiedApp] unified_api.py:4460 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-21 18:44:40 [INFO] [app.UnifiedApp] unified_api.py:3164 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_183935 --execution-mode complete --backup-vector-tables --truncate-vector-tables --skip-training
-2025-07-21 18:44:40 [INFO] [app.UnifiedApp] unified_api.py:3186 - 📋 API请求包含Vector表管理参数: backup=True, truncate=True
-2025-07-21 18:44:40 [INFO] [app.UnifiedApp] unified_api.py:3175 - 任务进程已启动: PID=10516, task_id=task_20250721_183935
-2025-07-21 19:39:39 [INFO] [app.UnifiedApp] unified_api.py:4439 - 接收到信号 2，准备退出...
-2025-07-21 19:39:39 [ERROR] [app.UnifiedApp] unified_api.py:521 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-21 19:39:54 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 19:39:54 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 19:39:54 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 19:39:54 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 19:39:54 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 19:39:54 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 19:39:54 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 19:39:56 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-21 19:39:56 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 19:39:56 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 19:39:56 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 19:39:56 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 19:39:56 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 19:39:56 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 19:39:56 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 19:39:57 [INFO] [app.UnifiedApp] unified_api.py:4448 - 🚀 启动统一API服务...
-2025-07-21 19:39:57 [INFO] [app.UnifiedApp] unified_api.py:4449 - 📍 服务地址: http://localhost:8084
-2025-07-21 19:39:57 [INFO] [app.UnifiedApp] unified_api.py:4450 - 🔗 健康检查: http://localhost:8084/health
-2025-07-21 19:39:57 [INFO] [app.UnifiedApp] unified_api.py:4451 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-21 19:39:57 [INFO] [app.UnifiedApp] unified_api.py:4452 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-21 19:39:57 [INFO] [app.UnifiedApp] unified_api.py:4459 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-21 19:39:57 [INFO] [app.UnifiedApp] unified_api.py:4460 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-21 19:40:53 [INFO] [app.UnifiedApp] unified_api.py:3164 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_183935 --execution-mode complete --backup-vector-tables --truncate-vector-tables --skip-training
-2025-07-21 19:40:53 [INFO] [app.UnifiedApp] unified_api.py:3186 - 📋 API请求包含Vector表管理参数: backup=True, truncate=True
-2025-07-21 19:40:53 [INFO] [app.UnifiedApp] unified_api.py:3175 - 任务进程已启动: PID=12948, task_id=task_20250721_183935
-2025-07-21 19:46:22 [INFO] [app.UnifiedApp] unified_api.py:3164 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_183935 --execution-mode complete --backup-vector-tables --truncate-vector-tables --skip-training
-2025-07-21 19:46:22 [INFO] [app.UnifiedApp] unified_api.py:3186 - 📋 API请求包含Vector表管理参数: backup=True, truncate=True
-2025-07-21 19:46:22 [INFO] [app.UnifiedApp] unified_api.py:3175 - 任务进程已启动: PID=21180, task_id=task_20250721_183935
-2025-07-21 20:00:03 [INFO] [app.UnifiedApp] unified_api.py:4439 - 接收到信号 2，准备退出...
-2025-07-21 20:00:03 [ERROR] [app.UnifiedApp] unified_api.py:521 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-21 20:09:09 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 20:09:09 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 20:09:09 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 20:09:09 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 20:09:09 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 20:09:09 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 20:09:09 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 20:09:11 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-21 20:09:11 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 20:09:11 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 20:09:11 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 20:09:11 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 20:09:11 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 20:09:11 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 20:09:11 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 20:09:13 [INFO] [app.UnifiedApp] unified_api.py:4448 - 🚀 启动统一API服务...
-2025-07-21 20:09:13 [INFO] [app.UnifiedApp] unified_api.py:4449 - 📍 服务地址: http://localhost:8084
-2025-07-21 20:09:13 [INFO] [app.UnifiedApp] unified_api.py:4450 - 🔗 健康检查: http://localhost:8084/health
-2025-07-21 20:09:13 [INFO] [app.UnifiedApp] unified_api.py:4451 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-21 20:09:13 [INFO] [app.UnifiedApp] unified_api.py:4452 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-21 20:09:13 [INFO] [app.UnifiedApp] unified_api.py:4459 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-21 20:09:13 [INFO] [app.UnifiedApp] unified_api.py:4460 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-21 20:09:17 [INFO] [app.UnifiedApp] unified_api.py:3164 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_183935 --execution-mode complete --backup-vector-tables --truncate-vector-tables --skip-training
-2025-07-21 20:09:17 [INFO] [app.UnifiedApp] unified_api.py:3186 - 📋 API请求包含Vector表管理参数: backup=True, truncate=True
-2025-07-21 20:09:17 [INFO] [app.UnifiedApp] unified_api.py:3175 - 任务进程已启动: PID=3772, task_id=task_20250721_183935
-2025-07-21 20:30:26 [INFO] [app.UnifiedApp] unified_api.py:3164 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_202929 --execution-mode complete --truncate-vector-tables
-2025-07-21 20:30:26 [INFO] [app.UnifiedApp] unified_api.py:3186 - 📋 API请求包含Vector表管理参数: backup=False, truncate=True
-2025-07-21 20:30:26 [INFO] [app.UnifiedApp] unified_api.py:3175 - 任务进程已启动: PID=20732, task_id=task_20250721_202929
-2025-07-21 21:37:15 [INFO] [app.UnifiedApp] unified_api.py:3164 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_213627 --execution-mode step --step-name ddl_generation
-2025-07-21 21:37:15 [INFO] [app.UnifiedApp] unified_api.py:3175 - 任务进程已启动: PID=31584, task_id=task_20250721_213627
-2025-07-21 21:40:25 [INFO] [app.UnifiedApp] unified_api.py:3164 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_213627 --execution-mode step --step-name qa_generation
-2025-07-21 21:40:25 [INFO] [app.UnifiedApp] unified_api.py:3175 - 任务进程已启动: PID=36728, task_id=task_20250721_213627
-2025-07-21 21:48:41 [INFO] [app.UnifiedApp] unified_api.py:3164 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_213627 --execution-mode step --step-name sql_validation
-2025-07-21 21:48:41 [INFO] [app.UnifiedApp] unified_api.py:3175 - 任务进程已启动: PID=39320, task_id=task_20250721_213627
-2025-07-21 21:57:42 [INFO] [app.UnifiedApp] unified_api.py:3164 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_213627 --execution-mode step --step-name training_load --truncate-vector-tables
-2025-07-21 21:57:42 [INFO] [app.UnifiedApp] unified_api.py:3186 - 📋 API请求包含Vector表管理参数: backup=False, truncate=True
-2025-07-21 21:57:42 [INFO] [app.UnifiedApp] unified_api.py:3175 - 任务进程已启动: PID=30656, task_id=task_20250721_213627
-2025-07-21 22:02:31 [INFO] [app.UnifiedApp] unified_api.py:4439 - 接收到信号 2，准备退出...
-2025-07-21 22:02:31 [ERROR] [app.UnifiedApp] unified_api.py:521 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-21 23:16:59 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 23:16:59 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 23:16:59 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 23:16:59 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 23:16:59 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 23:16:59 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 23:16:59 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 23:17:00 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-21 23:17:00 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 23:17:00 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 23:17:00 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 23:17:00 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 23:17:00 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 23:17:00 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 23:17:00 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 23:17:02 [INFO] [app.UnifiedApp] unified_api.py:4448 - 🚀 启动统一API服务...
-2025-07-21 23:17:02 [INFO] [app.UnifiedApp] unified_api.py:4449 - 📍 服务地址: http://localhost:8084
-2025-07-21 23:17:02 [INFO] [app.UnifiedApp] unified_api.py:4450 - 🔗 健康检查: http://localhost:8084/health
-2025-07-21 23:17:02 [INFO] [app.UnifiedApp] unified_api.py:4451 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-21 23:17:02 [INFO] [app.UnifiedApp] unified_api.py:4452 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-21 23:17:02 [INFO] [app.UnifiedApp] unified_api.py:4459 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-21 23:17:02 [INFO] [app.UnifiedApp] unified_api.py:4460 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-21 23:17:06 [WARNING] [app.UnifiedApp] unified_api.py:3120 - ⚠️ Vector表管理参数仅在training_load步骤有效，当前步骤: ddl_generation，忽略参数
-2025-07-21 23:17:06 [INFO] [app.UnifiedApp] unified_api.py:3164 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_213627 --execution-mode step --step-name ddl_generation
-2025-07-21 23:17:06 [INFO] [app.UnifiedApp] unified_api.py:3175 - 任务进程已启动: PID=38096, task_id=task_20250721_213627
-2025-07-21 23:20:45 [WARNING] [app.UnifiedApp] unified_api.py:3120 - ⚠️ Vector表管理参数仅在training_load步骤有效，当前步骤: qa_generation，忽略参数
-2025-07-21 23:20:45 [INFO] [app.UnifiedApp] unified_api.py:3164 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_213627 --execution-mode step --step-name qa_generation
-2025-07-21 23:20:45 [INFO] [app.UnifiedApp] unified_api.py:3175 - 任务进程已启动: PID=14012, task_id=task_20250721_213627
-2025-07-21 23:46:21 [WARNING] [app.UnifiedApp] unified_api.py:3120 - ⚠️ Vector表管理参数仅在training_load步骤有效，当前步骤: qa_generation，忽略参数
-2025-07-21 23:46:21 [INFO] [app.UnifiedApp] unified_api.py:3164 - 启动任务进程: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\.venv\Scripts\python.exe C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\data_pipeline\task_executor.py --task-id task_20250721_213627 --execution-mode step --step-name qa_generation
-2025-07-21 23:46:21 [INFO] [app.UnifiedApp] unified_api.py:3175 - 任务进程已启动: PID=26292, task_id=task_20250721_213627
-2025-07-21 23:57:49 [INFO] [app.UnifiedApp] unified_api.py:4439 - 接收到信号 2，准备退出...
-2025-07-21 23:57:49 [ERROR] [app.UnifiedApp] unified_api.py:521 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-21 23:58:03 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 23:58:03 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 23:58:03 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 23:58:03 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 23:58:03 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 23:58:03 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 23:58:03 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 23:58:05 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-21 23:58:05 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-21 23:58:05 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-21 23:58:05 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-21 23:58:05 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-21 23:58:05 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-21 23:58:05 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-21 23:58:05 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-21 23:58:06 [INFO] [app.UnifiedApp] unified_api.py:4449 - 🚀 启动统一API服务...
-2025-07-21 23:58:06 [INFO] [app.UnifiedApp] unified_api.py:4450 - 📍 服务地址: http://localhost:8084
-2025-07-21 23:58:06 [INFO] [app.UnifiedApp] unified_api.py:4451 - 🔗 健康检查: http://localhost:8084/health
-2025-07-21 23:58:06 [INFO] [app.UnifiedApp] unified_api.py:4452 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-21 23:58:06 [INFO] [app.UnifiedApp] unified_api.py:4453 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-21 23:58:06 [INFO] [app.UnifiedApp] unified_api.py:4460 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-21 23:58:06 [INFO] [app.UnifiedApp] unified_api.py:4461 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存

logs/app.log.2025-07-22

@@ -1,270 +0,0 @@
-2025-07-22 00:28:27 [INFO] [app.UnifiedApp] unified_api.py:4440 - 接收到信号 2，准备退出...
-2025-07-22 00:28:27 [ERROR] [app.UnifiedApp] unified_api.py:521 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-22 01:03:06 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 01:03:06 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 01:03:06 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 01:03:06 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 01:03:06 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 01:03:06 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 01:03:06 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 01:03:08 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-22 01:03:08 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 01:03:08 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 01:03:08 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 01:03:08 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 01:03:08 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 01:03:08 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 01:03:08 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 01:03:09 [INFO] [app.UnifiedApp] unified_api.py:4522 - 🚀 启动统一API服务...
-2025-07-22 01:03:09 [INFO] [app.UnifiedApp] unified_api.py:4523 - 📍 服务地址: http://localhost:8084
-2025-07-22 01:03:09 [INFO] [app.UnifiedApp] unified_api.py:4524 - 🔗 健康检查: http://localhost:8084/health
-2025-07-22 01:03:09 [INFO] [app.UnifiedApp] unified_api.py:4525 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-22 01:03:09 [INFO] [app.UnifiedApp] unified_api.py:4526 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-22 01:03:09 [INFO] [app.UnifiedApp] unified_api.py:4533 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-22 01:03:09 [INFO] [app.UnifiedApp] unified_api.py:4534 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-22 01:04:57 [INFO] [app.UnifiedApp] unified_api.py:4441 - 接收到信号 2，准备退出...
-2025-07-22 01:04:57 [ERROR] [app.UnifiedApp] unified_api.py:522 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-22 11:33:44 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 11:33:44 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 11:33:44 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 11:33:44 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 11:33:44 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 11:33:44 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 11:33:44 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 11:33:46 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-22 11:33:46 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 11:33:46 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 11:33:46 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 11:33:46 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 11:33:46 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 11:33:46 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 11:33:46 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 11:33:47 [INFO] [app.UnifiedApp] unified_api.py:4642 - 🚀 启动统一API服务...
-2025-07-22 11:33:47 [INFO] [app.UnifiedApp] unified_api.py:4643 - 📍 服务地址: http://localhost:8084
-2025-07-22 11:33:47 [INFO] [app.UnifiedApp] unified_api.py:4644 - 🔗 健康检查: http://localhost:8084/health
-2025-07-22 11:33:47 [INFO] [app.UnifiedApp] unified_api.py:4645 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-22 11:33:47 [INFO] [app.UnifiedApp] unified_api.py:4646 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-22 11:33:47 [INFO] [app.UnifiedApp] unified_api.py:4647 - 💾 Vector备份API: http://localhost:8084/api/v0/data_pipeline/vector/backup
-2025-07-22 11:33:47 [INFO] [app.UnifiedApp] unified_api.py:4648 - 📥 Vector恢复API: http://localhost:8084/api/v0/data_pipeline/vector/restore
-2025-07-22 11:33:47 [INFO] [app.UnifiedApp] unified_api.py:4649 - 📋 备份列表API: http://localhost:8084/api/v0/data_pipeline/vector/restore/list
-2025-07-22 11:33:47 [INFO] [app.UnifiedApp] unified_api.py:4656 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-22 11:33:47 [INFO] [app.UnifiedApp] unified_api.py:4657 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-22 11:53:31 [INFO] [app.UnifiedApp] unified_api.py:4441 - 接收到信号 2，准备退出...
-2025-07-22 11:53:31 [ERROR] [app.UnifiedApp] unified_api.py:522 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-22 11:53:46 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 11:53:46 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 11:53:46 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 11:53:46 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 11:53:46 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 11:53:46 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 11:53:46 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 11:53:47 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-22 11:53:47 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 11:53:47 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 11:53:47 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 11:53:47 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 11:53:47 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 11:53:47 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 11:53:47 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 11:53:49 [INFO] [app.UnifiedApp] unified_api.py:4642 - 🚀 启动统一API服务...
-2025-07-22 11:53:49 [INFO] [app.UnifiedApp] unified_api.py:4643 - 📍 服务地址: http://localhost:8084
-2025-07-22 11:53:49 [INFO] [app.UnifiedApp] unified_api.py:4644 - 🔗 健康检查: http://localhost:8084/health
-2025-07-22 11:53:49 [INFO] [app.UnifiedApp] unified_api.py:4645 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-22 11:53:49 [INFO] [app.UnifiedApp] unified_api.py:4646 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-22 11:53:49 [INFO] [app.UnifiedApp] unified_api.py:4647 - 💾 Vector备份API: http://localhost:8084/api/v0/data_pipeline/vector/backup
-2025-07-22 11:53:49 [INFO] [app.UnifiedApp] unified_api.py:4648 - 📥 Vector恢复API: http://localhost:8084/api/v0/data_pipeline/vector/restore
-2025-07-22 11:53:49 [INFO] [app.UnifiedApp] unified_api.py:4649 - 📋 备份列表API: http://localhost:8084/api/v0/data_pipeline/vector/restore/list
-2025-07-22 11:53:49 [INFO] [app.UnifiedApp] unified_api.py:4656 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-22 11:53:49 [INFO] [app.UnifiedApp] unified_api.py:4657 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-22 11:56:39 [INFO] [app.UnifiedApp] unified_api.py:4441 - 接收到信号 2，准备退出...
-2025-07-22 11:56:39 [ERROR] [app.UnifiedApp] unified_api.py:522 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-22 11:56:58 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 11:56:58 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 11:56:58 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 11:56:58 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 11:56:58 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 11:56:58 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 11:56:58 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 11:57:00 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-22 11:57:00 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 11:57:00 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 11:57:00 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 11:57:00 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 11:57:00 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 11:57:00 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 11:57:00 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 11:57:02 [INFO] [app.UnifiedApp] unified_api.py:4642 - 🚀 启动统一API服务...
-2025-07-22 11:57:02 [INFO] [app.UnifiedApp] unified_api.py:4643 - 📍 服务地址: http://localhost:8084
-2025-07-22 11:57:02 [INFO] [app.UnifiedApp] unified_api.py:4644 - 🔗 健康检查: http://localhost:8084/health
-2025-07-22 11:57:02 [INFO] [app.UnifiedApp] unified_api.py:4645 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-22 11:57:02 [INFO] [app.UnifiedApp] unified_api.py:4646 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-22 11:57:02 [INFO] [app.UnifiedApp] unified_api.py:4647 - 💾 Vector备份API: http://localhost:8084/api/v0/data_pipeline/vector/backup
-2025-07-22 11:57:02 [INFO] [app.UnifiedApp] unified_api.py:4648 - 📥 Vector恢复API: http://localhost:8084/api/v0/data_pipeline/vector/restore
-2025-07-22 11:57:02 [INFO] [app.UnifiedApp] unified_api.py:4649 - 📋 备份列表API: http://localhost:8084/api/v0/data_pipeline/vector/restore/list
-2025-07-22 11:57:02 [INFO] [app.UnifiedApp] unified_api.py:4656 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-22 11:57:02 [INFO] [app.UnifiedApp] unified_api.py:4657 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-22 11:57:12 [INFO] [app.UnifiedApp] unified_api.py:4441 - 接收到信号 2，准备退出...
-2025-07-22 11:57:12 [ERROR] [app.UnifiedApp] unified_api.py:522 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-22 12:08:43 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 12:08:43 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 12:08:43 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 12:08:43 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 12:08:43 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 12:08:43 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 12:08:43 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 12:08:45 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-22 12:08:45 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 12:08:45 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 12:08:45 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 12:08:45 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 12:08:45 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 12:08:45 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 12:08:45 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 12:08:47 [INFO] [app.UnifiedApp] unified_api.py:4642 - 🚀 启动统一API服务...
-2025-07-22 12:08:47 [INFO] [app.UnifiedApp] unified_api.py:4643 - 📍 服务地址: http://localhost:8084
-2025-07-22 12:08:47 [INFO] [app.UnifiedApp] unified_api.py:4644 - 🔗 健康检查: http://localhost:8084/health
-2025-07-22 12:08:47 [INFO] [app.UnifiedApp] unified_api.py:4645 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-22 12:08:47 [INFO] [app.UnifiedApp] unified_api.py:4646 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-22 12:08:47 [INFO] [app.UnifiedApp] unified_api.py:4647 - 💾 Vector备份API: http://localhost:8084/api/v0/data_pipeline/vector/backup
-2025-07-22 12:08:47 [INFO] [app.UnifiedApp] unified_api.py:4648 - 📥 Vector恢复API: http://localhost:8084/api/v0/data_pipeline/vector/restore
-2025-07-22 12:08:47 [INFO] [app.UnifiedApp] unified_api.py:4649 - 📋 备份列表API: http://localhost:8084/api/v0/data_pipeline/vector/restore/list
-2025-07-22 12:08:47 [INFO] [app.UnifiedApp] unified_api.py:4656 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-22 12:08:47 [INFO] [app.UnifiedApp] unified_api.py:4657 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-22 12:25:31 [INFO] [app.UnifiedApp] unified_api.py:4441 - 接收到信号 2，准备退出...
-2025-07-22 12:25:31 [ERROR] [app.UnifiedApp] unified_api.py:522 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-22 12:26:17 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 12:26:17 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 12:26:17 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 12:26:17 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 12:26:17 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 12:26:17 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 12:26:17 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 12:26:18 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-22 12:26:18 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 12:26:18 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 12:26:18 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 12:26:18 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 12:26:18 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 12:26:18 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 12:26:18 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 12:26:20 [INFO] [app.UnifiedApp] unified_api.py:4642 - 🚀 启动统一API服务...
-2025-07-22 12:26:20 [INFO] [app.UnifiedApp] unified_api.py:4643 - 📍 服务地址: http://localhost:8084
-2025-07-22 12:26:20 [INFO] [app.UnifiedApp] unified_api.py:4644 - 🔗 健康检查: http://localhost:8084/health
-2025-07-22 12:26:20 [INFO] [app.UnifiedApp] unified_api.py:4645 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-22 12:26:20 [INFO] [app.UnifiedApp] unified_api.py:4646 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-22 12:26:20 [INFO] [app.UnifiedApp] unified_api.py:4647 - 💾 Vector备份API: http://localhost:8084/api/v0/data_pipeline/vector/backup
-2025-07-22 12:26:20 [INFO] [app.UnifiedApp] unified_api.py:4648 - 📥 Vector恢复API: http://localhost:8084/api/v0/data_pipeline/vector/restore
-2025-07-22 12:26:20 [INFO] [app.UnifiedApp] unified_api.py:4649 - 📋 备份列表API: http://localhost:8084/api/v0/data_pipeline/vector/restore/list
-2025-07-22 12:26:20 [INFO] [app.UnifiedApp] unified_api.py:4656 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-22 12:26:20 [INFO] [app.UnifiedApp] unified_api.py:4657 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-22 12:27:03 [INFO] [app.UnifiedApp] unified_api.py:4441 - 接收到信号 2，准备退出...
-2025-07-22 12:27:03 [ERROR] [app.UnifiedApp] unified_api.py:522 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-22 13:24:45 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 13:24:45 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 13:24:45 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 13:24:45 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 13:24:45 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 13:24:45 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 13:24:45 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 13:24:46 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-22 13:24:46 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 13:24:46 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 13:24:46 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 13:24:46 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 13:24:46 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 13:24:46 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 13:24:46 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 13:24:48 [INFO] [app.UnifiedApp] unified_api.py:4642 - 🚀 启动统一API服务...
-2025-07-22 13:24:48 [INFO] [app.UnifiedApp] unified_api.py:4643 - 📍 服务地址: http://localhost:8084
-2025-07-22 13:24:48 [INFO] [app.UnifiedApp] unified_api.py:4644 - 🔗 健康检查: http://localhost:8084/health
-2025-07-22 13:24:48 [INFO] [app.UnifiedApp] unified_api.py:4645 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-22 13:24:48 [INFO] [app.UnifiedApp] unified_api.py:4646 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-22 13:24:48 [INFO] [app.UnifiedApp] unified_api.py:4647 - 💾 Vector备份API: http://localhost:8084/api/v0/data_pipeline/vector/backup
-2025-07-22 13:24:48 [INFO] [app.UnifiedApp] unified_api.py:4648 - 📥 Vector恢复API: http://localhost:8084/api/v0/data_pipeline/vector/restore
-2025-07-22 13:24:48 [INFO] [app.UnifiedApp] unified_api.py:4649 - 📋 备份列表API: http://localhost:8084/api/v0/data_pipeline/vector/restore/list
-2025-07-22 13:24:48 [INFO] [app.UnifiedApp] unified_api.py:4656 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-22 13:24:48 [INFO] [app.UnifiedApp] unified_api.py:4657 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-22 13:32:02 [INFO] [app.UnifiedApp] unified_api.py:4441 - 接收到信号 2，准备退出...
-2025-07-22 13:32:02 [ERROR] [app.UnifiedApp] unified_api.py:522 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-22 13:32:18 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 13:32:18 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 13:32:18 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 13:32:18 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 13:32:18 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 13:32:18 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 13:32:18 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 13:32:19 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-22 13:32:19 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 13:32:19 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 13:32:19 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 13:32:19 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 13:32:19 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 13:32:19 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 13:32:19 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 13:32:21 [INFO] [app.UnifiedApp] unified_api.py:4642 - 🚀 启动统一API服务...
-2025-07-22 13:32:21 [INFO] [app.UnifiedApp] unified_api.py:4643 - 📍 服务地址: http://localhost:8084
-2025-07-22 13:32:21 [INFO] [app.UnifiedApp] unified_api.py:4644 - 🔗 健康检查: http://localhost:8084/health
-2025-07-22 13:32:21 [INFO] [app.UnifiedApp] unified_api.py:4645 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-22 13:32:21 [INFO] [app.UnifiedApp] unified_api.py:4646 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-22 13:32:21 [INFO] [app.UnifiedApp] unified_api.py:4647 - 💾 Vector备份API: http://localhost:8084/api/v0/data_pipeline/vector/backup
-2025-07-22 13:32:21 [INFO] [app.UnifiedApp] unified_api.py:4648 - 📥 Vector恢复API: http://localhost:8084/api/v0/data_pipeline/vector/restore
-2025-07-22 13:32:21 [INFO] [app.UnifiedApp] unified_api.py:4649 - 📋 备份列表API: http://localhost:8084/api/v0/data_pipeline/vector/restore/list
-2025-07-22 13:32:21 [INFO] [app.UnifiedApp] unified_api.py:4656 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-22 13:32:21 [INFO] [app.UnifiedApp] unified_api.py:4657 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-22 13:33:54 [INFO] [app.UnifiedApp] unified_api.py:4441 - 接收到信号 2，准备退出...
-2025-07-22 13:33:54 [ERROR] [app.UnifiedApp] unified_api.py:522 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-22 17:38:36 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 17:38:36 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 17:38:36 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 17:38:36 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 17:38:36 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 17:38:36 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 17:38:36 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 17:38:37 [INFO] [app.RedisConversationManager] redis_conversation_manager.py:35 - Redis连接成功: localhost:6379
-2025-07-22 17:38:37 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 17:38:37 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 17:38:37 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 17:38:37 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 17:38:37 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 17:38:37 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 17:38:37 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 17:38:39 [INFO] [app.UnifiedApp] unified_api.py:4642 - 🚀 启动统一API服务...
-2025-07-22 17:38:39 [INFO] [app.UnifiedApp] unified_api.py:4643 - 📍 服务地址: http://localhost:8084
-2025-07-22 17:38:39 [INFO] [app.UnifiedApp] unified_api.py:4644 - 🔗 健康检查: http://localhost:8084/health
-2025-07-22 17:38:39 [INFO] [app.UnifiedApp] unified_api.py:4645 - 📘 React Agent API: http://localhost:8084/api/v0/ask_react_agent
-2025-07-22 17:38:39 [INFO] [app.UnifiedApp] unified_api.py:4646 - 📘 LangGraph Agent API: http://localhost:8084/api/v0/ask_agent
-2025-07-22 17:38:39 [INFO] [app.UnifiedApp] unified_api.py:4647 - 💾 Vector备份API: http://localhost:8084/api/v0/data_pipeline/vector/backup
-2025-07-22 17:38:39 [INFO] [app.UnifiedApp] unified_api.py:4648 - 📥 Vector恢复API: http://localhost:8084/api/v0/data_pipeline/vector/restore
-2025-07-22 17:38:39 [INFO] [app.UnifiedApp] unified_api.py:4649 - 📋 备份列表API: http://localhost:8084/api/v0/data_pipeline/vector/restore/list
-2025-07-22 17:38:39 [INFO] [app.UnifiedApp] unified_api.py:4656 - 🚀 使用ASGI模式启动异步Flask应用...
-2025-07-22 17:38:39 [INFO] [app.UnifiedApp] unified_api.py:4657 -    这将解决事件循环冲突问题，支持LangGraph异步checkpoint保存
-2025-07-22 20:45:47 [INFO] [app.UnifiedApp] unified_api.py:282 - 🚀 正在异步初始化 Custom React Agent...
-2025-07-22 20:45:47 [INFO] [app.UnifiedApp] unified_api.py:290 - ✅ Redis客户端连接成功
-2025-07-22 20:45:50 [INFO] [app.UnifiedApp] unified_api.py:293 - ✅ React Agent 异步初始化完成
-2025-07-22 20:45:50 [INFO] [app.UnifiedApp] unified_api.py:592 - 📨 收到React Agent请求 - User: wang16, Question: 请问系统中哪个服务区档口最多？...
-2025-07-22 20:45:56 [INFO] [app.VannaSingleton] vanna_instance.py:29 - 创建 Vanna 实例...
-2025-07-22 20:45:56 [INFO] [app.ConfigUtils] utils.py:187 - === 当前模型配置 ===
-2025-07-22 20:45:56 [INFO] [app.ConfigUtils] utils.py:188 - LLM提供商: api
-2025-07-22 20:45:56 [INFO] [app.ConfigUtils] utils.py:189 - LLM模型: qianwen
-2025-07-22 20:45:56 [INFO] [app.ConfigUtils] utils.py:190 - Embedding提供商: api
-2025-07-22 20:45:56 [INFO] [app.ConfigUtils] utils.py:191 - Embedding模型: text-embedding-v4
-2025-07-22 20:45:56 [INFO] [app.ConfigUtils] utils.py:192 - 向量数据库: pgvector
-2025-07-22 20:45:56 [INFO] [app.ConfigUtils] utils.py:193 - ==================
-2025-07-22 20:45:57 [INFO] [app.VannaSingleton] vanna_instance.py:34 - Vanna 实例创建成功
-2025-07-22 20:54:00 [INFO] [app.UnifiedApp] unified_api.py:245 - 👤 未提供user_id，从 thread_id 'wang16:20250722204550155' 中推断出: 'wang16'
-2025-07-22 20:54:00 [INFO] [app.UnifiedApp] unified_api.py:592 - 📨 收到React Agent请求 - User: wang16, Question: 请问这个服务区有几个餐饮档口？...
-2025-07-22 20:55:54 [INFO] [app.UnifiedApp] unified_api.py:2502 - 📋 获取用户 wang16 的对话列表（直接Redis方式）
-2025-07-22 20:55:54 [INFO] [app.UnifiedApp] unified_api.py:329 - 🔍 扫描模式: checkpoint:wang16:*
-2025-07-22 20:55:54 [INFO] [app.UnifiedApp] unified_api.py:339 - 📋 找到 36 个keys
-2025-07-22 20:55:54 [INFO] [app.UnifiedApp] unified_api.py:361 - 📊 找到 1 个thread
-2025-07-22 20:55:54 [INFO] [app.UnifiedApp] unified_api.py:381 - 🔍 Key checkpoint:wang16:20250722204550155:__empty__:1f066fb2-052e-667e-8021-9fd6bcb08135 的类型: ReJSON-RL
-2025-07-22 20:55:54 [INFO] [app.UnifiedApp] unified_api.py:403 - 🔍 使用JSON.GET获取RedisJSON数据
-2025-07-22 20:55:54 [INFO] [app.UnifiedApp] unified_api.py:409 - 🔍 JSON数据长度: 24914 字符
-2025-07-22 20:55:54 [INFO] [app.UnifiedApp] unified_api.py:425 - 🔍 JSON顶级keys: ['thread_id', 'checkpoint_ns', 'checkpoint_id', 'parent_checkpoint_id', 'checkpoint', 'metadata', 'source', 'step']
-2025-07-22 20:55:54 [INFO] [app.UnifiedApp] unified_api.py:437 - 🔍 找到messages: 19 条消息
-2025-07-22 20:55:57 [INFO] [app.UnifiedApp] unified_api.py:499 - ✅ 返回 1 个对话
-2025-07-22 20:56:25 [INFO] [app.UnifiedApp] unified_api.py:2559 - 📖 获取对话详情 - Thread: wang16:20250722204550155, Include Tools: False
-2025-07-22 20:56:25 [INFO] [app.UnifiedApp] unified_api.py:2588 - ✅ 成功获取对话详情 - Messages: 4, Mode: 简化模式
-2025-07-22 23:13:30 [INFO] [app.UnifiedApp] unified_api.py:4441 - 接收到信号 2，准备退出...
-2025-07-22 23:13:30 [ERROR] [app.UnifiedApp] unified_api.py:522 - 清理资源失败: asyncio.run() cannot be called from a running event loop
-2025-07-22 23:13:30 [ERROR] [app.UnifiedApp] unified_api.py:522 - 清理资源失败: Event loop is closed

logs/vanna.log.2025-07-20

@@ -1,1460 +0,0 @@
-2025-07-20 00:49:17 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-20 00:49:17 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-20 00:49:17 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-20 00:49:17 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-20 00:49:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-20 00:49:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-20 00:49:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-20 00:49:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-20 00:49:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-20 00:49:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-20 00:49:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-20 00:49:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-20 00:49:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-20 00:49:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-20 00:49:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-20 00:49:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001CA2C180F80>
-2025-07-20 00:49:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-20 00:49:17 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-20 00:49:17 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-20 00:49:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-20 00:49:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-20 00:49:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-20 00:49:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-20 00:49:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-20 00:49:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-20 00:49:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-20 00:49:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-20 00:49:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-20 00:49:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-20 00:49:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-20 00:49:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-20 00:49:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-20 00:49:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-20 00:49:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-20 00:49:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001CA2DB41EB0>
-2025-07-20 00:49:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-20 00:49:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-20 00:49:19 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-20 00:49:20 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-20 00:49:55 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-20 00:49:55 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-20 00:49:55 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-20 00:49:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-20 00:49:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-20 00:49:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-20 00:49:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-20 00:49:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-20 00:49:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-20 00:49:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-20 00:49:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-20 00:49:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-20 00:49:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-20 00:49:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-20 00:49:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001CA2FEEF650>
-2025-07-20 00:49:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-20 00:49:56 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-20 00:49:56 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-20 00:49:58 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:270 - 尝试为问题生成SQL: 请问哪个服务区的档口数量最多？
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 分析每个服务区关联的路线数量并找出覆盖路线最多的服务区 | similarity: 0.7464
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 哪些服务区只有单一方向的档口？ | similarity: 0.7459
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 分析各服务区关联的路段路线数量TOP10 | similarity: 0.7405
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 每个服务区的营业档口数量（曾经有交易的）？ | similarity: 0.7326
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 最近30天中车流量最高的服务区？ | similarity: 0.7325
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 各分公司管辖服务区的档口总数对比如何？ | similarity: 0.7275
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - SQL 阈值过滤: 总数=6, 阈值=0.65, 最少保留=3
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - SQL 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 1: similarity=0.7464 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 2: similarity=0.7459 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 3: similarity=0.7405 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 4: similarity=0.7326 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 5: similarity=0.7325 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 6: similarity=0.7275 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 档口基础信息表
--- 描述: 存储服务区内的档口（商铺）基础信息，如名称、编码、所属... | similarity: 0.649
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路段路线与服务区关联表
--- 描述: 路段路线与服务区关联表，维护路线与服务区之间的... | similarity: 0.6368
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路线与服务区关联表
--- 描述: 路线与服务区关联表，记录路线经过的服务区信息
-cr... | similarity: 0.6357
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路线分段与服务区关联表
--- 描述: 路线分段与服务区关联表，记录路线与服务区的对应... | similarity: 0.6313
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路线与服务区关联表
--- 描述: 路线与服务区关联表，记录路线ID与服务区ID的对应... | similarity: 0.626
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 存储路线段与服务区关联关系
--- 描述: 存储路线段与服务区关联关系，管理高速线路与... | similarity: 0.6199
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DDL 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DDL 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 1: similarity=0.649 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 2: similarity=0.6368 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 3: similarity=0.6357 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 4: similarity=0.6313 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 5: similarity=0.626 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 6: similarity=0.6199 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_branch（档口基础信息表）
-bss_branch 表存储服务区内的档口（商铺）基础... | similarity: 0.6543
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（存储高速公路服务区基础信息及版本变更记录）
-bss_serv... | similarity: 0.6345
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（存储高速公路服务区基础信息（名称、编码）及操作记录）
-bss... | similarity: 0.6339
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route_area_link（路线与服务区关联表）
-bss_sect... | similarity: 0.6287
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（服务区基础信息表）
-bss_service_area 表记录... | similarity: 0.627
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route_area_link（记录高速公路路段路线与服务区的关联关系... | similarity: 0.6263
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DOC 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DOC 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 1: similarity=0.6543 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 2: similarity=0.6345 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 3: similarity=0.6339 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 4: similarity=0.6287 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 5: similarity=0.627 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 6: similarity=0.6263 ✓
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:104 - 开始生成SQL提示词，问题: 请问哪个服务区的档口数量最多？
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:654 - Error SQL Match: 查询所有部门信息 | similarity: 0.2713
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:392 - Error SQL 阈值过滤: 总数=1, 阈值=0.8
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] pgvector.py:410 - Error SQL 过滤结果: 所有 1 条结果都低于阈值 0.8，返回空列表
-2025-07-20 00:49:58 [WARNING] [vanna.BaseLLMChat] pgvector.py:673 - 向量查询找到了 1 条错误SQL示例，但全部被阈值过滤掉.
-2025-07-20 00:49:58 [WARNING] [vanna.BaseLLMChat] pgvector.py:674 - 问题: 请问哪个服务区的档口数量最多？
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:159 - 未找到相关的错误SQL示例
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:87 - system_content: You are a PostgreSQL expert. 
-Please help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the response guidelines and format instructions.
-
-===Tables 
--- 中文名: 档口基础信息表
--- 描述: 存储服务区内的档口（商铺）基础信息，如名称、编码、所属服务区、所属公司、品类、品牌等，是商业数据分析的基础实体表。
-create table bss_branch (
-  id varchar(32) not null,              -- 主键ID
-  version integer not null,             -- 数据版本号
-  create_ts timestamp(3),               -- 创建时间
-  created_by varchar(50),               -- 创建人
-  update_ts timestamp(3),               -- 更新时间
-  updated_by varchar(50),               -- 更新人
-  delete_ts timestamp(3),               -- 删除时间
-  deleted_by varchar(50),               -- 删除人
-  branch_name varchar(255),             -- 档口名称
-  branch_no varchar(255),               -- 档口编码
-  service_area_id varchar(32),          -- 服务区ID,外键(关联bss_service_area.id)
-  company_id varchar(32),               -- 公司ID,外键(关联bss_company.ID)
-  classify varchar(256),                -- 品类
-  product_brand varchar(256),           -- 品牌
-  category varchar(256),                -- 类别
-  section_route_id varchar(32),         -- 所属路线ID,外键(关联bss_section_route.id)
-  direction varchar(256),               -- 所在方向
-  is_manual_entry integer default 0,    -- 是否手工录入
-  co_company varchar(256)               -- 合作公司名称
-)
-
--- 中文名: 路段路线与服务区关联表
--- 描述: 路段路线与服务区关联表，维护路线与服务区之间的归属关系。
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线ID，主键,
-  service_area_id varchar(32) not null -- 服务区ID，主键,
-  primary key (section_route_id, service_area_id)
-)
-
--- 中文名: 路线与服务区关联表
--- 描述: 路线与服务区关联表，记录路线经过的服务区信息
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线ID，主键,
-  service_area_id varchar(32) not null -- 服务区ID，主键,
-  primary key (section_route_id, service_area_id)
-)
-
--- 中文名: 路线分段与服务区关联表
--- 描述: 路线分段与服务区关联表，记录路线与服务区的对应关系
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线ID，主键,
-  service_area_id varchar(32) not null -- 服务区ID，主键,
-  primary key (section_route_id, service_area_id)
-)
-
--- 中文名: 路线与服务区关联表
--- 描述: 路线与服务区关联表，记录路线ID与服务区ID的对应关系，支持路径规划和资源分配。
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线ID，主键,
-  service_area_id varchar(32) not null -- 服务区ID，主键,
-  primary key (section_route_id, service_area_id)
-)
-
--- 中文名: 存储路线段与服务区关联关系
--- 描述: 存储路线段与服务区关联关系，管理高速线路与服务区归属
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线ID，主键,
-  service_area_id varchar(32) not null -- 服务区编码，主键,
-  primary key (section_route_id, service_area_id)
-)
-
-
-===Additional Context 
-
-## bss_branch（档口基础信息表）
-bss_branch 表存储服务区内的档口（商铺）基础信息，如名称、编码、所属服务区、所属公司、品类、品牌等，是商业数据分析的基础实体表。
-字段列表：
-- id (varchar(32)) - 主键ID [示例: 00904903cae681aab7a494c3e88e5acd]
-- version (integer) - 数据版本号 [示例: 1]
-- create_ts (timestamp(3)) - 创建时间 [示例: 2021-10-15 09:46:45.010]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp(3)) - 更新时间 [示例: 2021-10-15 09:46:45.010]
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp(3)) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- branch_name (varchar(255)) - 档口名称 [示例: 于都驿美餐饮南区]
-- branch_no (varchar(255)) - 档口编码（唯一业务标识）[示例: 003585]
-- service_area_id (varchar(32)) - 服务区ID（外键关联bss_service_area.id）[示例: c7e2f26df373e9cb75bd24ddba57f27f]
-- company_id (varchar(32)) - 公司ID（外键关联bss_company.id）[示例: ce5e6f553513dad393694e1fa663aaf4]
-- classify (varchar(256)) - 经营品类，枚举型：餐饮、小吃、便利店、整体租赁、其他 [示例: 餐饮]
-- product_brand (varchar(256)) - 品牌名称 [示例: 驿美餐饮]
-- category (varchar(256)) - 经营类别 [示例: 混沌]
-- section_route_id (varchar(32)) - 所属路线ID（外键关联bss_section_route.id）[示例: lvkcuu94d4487c42z7qltsvxcyz0iqu5]
-- direction (varchar(256)) - 所在方向（枚举：北区/南区/西区/东区/两区）[示例: 南区]
-- is_manual_entry (integer) - 是否手工录入（0=系统自动，1=手工录入）[示例: 0]
-- co_company (varchar(256)) - 合作公司名称 [示例: 江西驿美餐饮管理有限责任公司]
-字段补充说明：
-- service_area_id 外键关联服务区基础信息表(bss_service_area)
-- company_id 外键关联服务区管理公司表(bss_company)
-- section_route_id 外键关联高速线路信息表(bss_section_route)
-- direction 表示档口在服务区内的物理位置分区,为枚举型：北区、南区、西区、东区、两区。
-- is_manual_entry 标识数据来源（系统采集或人工录入）
-- classify 表示经营品类，为枚举型：餐饮、小吃、便利店、整体租赁、其他。
-
-## bss_service_area（存储高速公路服务区基础信息及版本变更记录）
-bss_service_area 表存储高速公路服务区基础信息及版本变更记录，支持服务区全生命周期管理。
-字段列表：
-- id (varchar(32)) - 主键标识符 [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
-- version (integer) - 版本号 [非空] [示例: 3, 6]
-- create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人 [示例: ]
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
-- service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
-- company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
-- service_position (varchar(255)) - 地理坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
-- service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
-- service_state (varchar(50)) - 运营状态 [示例: 开放, 关闭]
-字段补充说明：
-- id 为主键
-- service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
-- service_state 为枚举字段，包含取值：开放、关闭、上传数据
-
-## bss_service_area（存储高速公路服务区基础信息（名称、编码）及操作记录）
-bss_service_area 表存储高速公路服务区基础信息（名称、编码）及操作记录，支撑BSS系统服务区全生命周期管理
-字段列表：
-- id (varchar(32)) - 主键标识符 [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
-- version (integer) - 版本号 [非空] [示例: 3, 6]
-- create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人 [示例: ]
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
-- service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
-- company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
-- service_position (varchar(255)) - 地理位置坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
-- service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
-- service_state (varchar(50)) - 服务区状态 [示例: 开放, 关闭]
-字段补充说明：
-- id 为主键
-- service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
-- service_state 为枚举字段，包含取值：开放、关闭、上传数据
-
-## bss_section_route_area_link（路线与服务区关联表）
-bss_section_route_area_link 表路线与服务区关联表，记录路线ID与服务区ID的对应关系，支持路径规划和资源分配。
-字段列表：
-- section_route_id (varchar(32)) - 路段路线ID [主键, 非空] [示例: v8elrsfs5f7lt7jl8a6p87smfzesn3rz, hxzi2iim238e3s1eajjt1enmh9o4h3wp]
-- service_area_id (varchar(32)) - 服务区ID [主键, 非空] [示例: 08e01d7402abd1d6a4d9fdd5df855ef8, 091662311d2c737029445442ff198c4c]
-字段补充说明：
-- 复合主键：section_route_id, service_area_id
-
-## bss_service_area（服务区基础信息表）
-bss_service_area 表记录高速公路服务区的基础属性，包括服务区编码、名称、方向、公司归属、地理位置、服务类型和状态，是业务分析与服务区定位的核心表。
-字段列表：
-- id (varchar(32)) - 服务区唯一标识（主键，UUID) [示例: 0271d68ef93de9684b7ad8c7aae600b6]
-- version (integer) - 版本号 [示例: 3]
-- create_ts (timestamp(3)) - 创建时间 [示例: 2021-05-21 13:26:40.589]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp(3)) - 更新时间 [示例: 2021-07-10 15:41:28.795]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp(3)) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区]
-- service_area_no (varchar(255)) - 服务区编码（业务唯一标识）[示例: H0814]
-- company_id (varchar(32)) - 公司ID（外键关联bss_company.id）[示例: b1629f07c8d9ac81494fbc1de61f1ea5]
-- service_position (varchar(255)) - 经纬度坐标 [示例: 114.574721,26.825584]
-- service_area_type (varchar(50)) - 服务区类型（枚举：信息化服务区、智能化服务区）[示例: 信息化服务区]
-- service_state (varchar(50)) - 服务区状态（枚举：开放/关闭/上传数据）[示例: 开放]
-字段补充说明：
-- id 为主键，使用 UUID 编码，唯一标识每个服务区。
-- company_id 外键,关联服务区管理公司表(bss_company.id)
-- service_position 经纬度格式为"经度,纬度"
-- service_area_type 为枚举字段，包含两个取值：信息化服务区、智能化服务区。
-- 是多个表(bss_branch, bss_car_day_count等)的核心关联实体
-
-## bss_section_route_area_link（记录高速公路路段路线与服务区的关联关系）
-bss_section_route_area_link 表记录高速公路路段路线与服务区的关联关系，支撑路线规划与服务区运营管理。
-字段列表：
-- section_route_id (varchar(32)) - 路段路线ID [主键, 非空] [示例: v8elrsfs5f7lt7jl8a6p87smfzesn3rz, hxzi2iim238e3s1eajjt1enmh9o4h3wp]
-- service_area_id (varchar(32)) - 服务区ID [主键, 非空] [示例: 08e01d7402abd1d6a4d9fdd5df855ef8, 091662311d2c737029445442ff198c4c]
-字段补充说明：
-- 复合主键：section_route_id, service_area_id
-
-===Response Guidelines 
-**IMPORTANT**: All SQL queries MUST use Chinese aliases for ALL columns in SELECT clause.
-
-1. If the provided context is sufficient, please generate a valid SQL query without any explanations for the question. 
-2. If the provided context is almost sufficient but requires knowledge of a specific string in a particular column, please generate an intermediate SQL query to find the distinct strings in that column. Prepend the query with a comment saying intermediate_sql 
-3. If the provided context is insufficient, please explain why it can't be generated. 
-4. **Context Understanding**: If the question follows [CONTEXT]...[CURRENT] format, replace pronouns in [CURRENT] with specific entities from [CONTEXT].
-   - Example: If context mentions 'Nancheng Service Area has the most stalls', and current question is 'How many dining stalls does this service area have?', 
-     interpret it as 'How many dining stalls does Nancheng Service Area have?'
-5. Please use the most relevant table(s). 
-6. If the question has been asked and answered before, please repeat the answer exactly as it was given before. 
-7. Ensure that the output SQL is PostgreSQL-compliant and executable, and free of syntax errors. 
-8. Always add NULLS LAST to ORDER BY clauses to handle NULL values properly (e.g., ORDER BY total DESC NULLS LAST).
-9. **MANDATORY**: ALL columns in SELECT must have Chinese aliases. This is non-negotiable:
-   - Every column MUST use AS with a Chinese alias
-   - Raw column names without aliases are NOT acceptable
-   - Examples: 
-     * CORRECT: SELECT service_name AS 服务区名称, SUM(pay_sum) AS 总收入
-     * WRONG: SELECT service_name, SUM(pay_sum) AS total_revenue
-     * WRONG: SELECT service_name AS service_area, SUM(pay_sum) AS 总收入
-   - Common aliases: COUNT(*) AS 数量, SUM(...) AS 总计, AVG(...) AS 平均值, MAX(...) AS 最大值, MIN(...) AS 最小值
-
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 分析每个服务区关联的路线数量并找出覆盖路线最多的服务区
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT service_area_id AS 服务区ID, COUNT(section_route_id) AS 关联路线数 FROM bss_section_route_area_link GROUP BY service_area_id ORDER BY 关联路线数 DESC LIMIT 1;
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 哪些服务区只有单一方向的档口？
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT sa.service_area_name, COUNT(DISTINCT b.direction) AS direction_count, STRING_AGG(DISTINCT b.direction, ', ') AS directions FROM bss_service_area sa JOIN bss_branch b ON sa.id = b.service_area_id WHERE sa.delete_ts IS NULL AND b.delete_ts IS NULL GROUP BY sa.service_area_name HAVING COUNT(DISTINCT b.direction) = 1 ORDER BY sa.service_area_name;
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 分析各服务区关联的路段路线数量TOP10
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT sa.service_area_name AS 服务区名称, COUNT(sr.id) AS 关联路段数 FROM bss_section_route_area_link link JOIN bss_service_area sa ON link.service_area_id = sa.id JOIN bss_section_route sr ON link.section_route_id = sr.id WHERE sa.delete_ts IS NULL GROUP BY sa.service_area_name ORDER BY 关联路段数 DESC LIMIT 10;
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 每个服务区的营业档口数量（曾经有交易的）？
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT service_name, COUNT(DISTINCT branch_no) AS branch_count FROM bss_business_day_data WHERE delete_ts IS NULL GROUP BY service_name;
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 最近30天中车流量最高的服务区？
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT s.service_area_name, SUM(c.customer_count) AS total_cars FROM bss_car_day_count c JOIN bss_service_area s ON c.service_area_id = s.id WHERE c.count_date >= CURRENT_DATE - INTERVAL '30 day' GROUP BY s.service_area_name ORDER BY total_cars DESC NULLS LAST LIMIT 10;
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 各分公司管辖服务区的档口总数对比如何？
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT c.company_name, COUNT(DISTINCT b.id) AS total_branches FROM bss_company c JOIN bss_service_area sa ON c.id = sa.company_id JOIN bss_branch b ON sa.id = b.service_area_id WHERE c.delete_ts IS NULL AND sa.delete_ts IS NULL AND b.delete_ts IS NULL GROUP BY c.company_name ORDER BY total_branches DESC NULLS LAST;
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 请问哪个服务区的档口数量最多？
-2025-07-20 00:49:58 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:70 - [Vanna] SQL Prompt: [{'role': 'system', 'content': 'You are a PostgreSQL expert. \nPlease help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the respon...
-2025-07-20 00:49:58 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:115 - 
-Using model qwen-plus-latest for 2977.0 tokens (approx)
-2025-07-20 00:49:58 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:116 - Enable thinking: False, Stream mode: False
-2025-07-20 00:49:58 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:158 - 使用非流式处理模式
-2025-07-20 00:50:01 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:77 - [Vanna] LLM Response: SELECT sa.service_area_name AS 服务区名称, COUNT(b.id) AS 档口数量 FROM bss_service_area sa JOIN bss_branch b ON sa.id = b.service_area_id WHERE sa.delete_ts IS NULL AND b.delete_ts IS NULL GROUP BY sa.service...
-2025-07-20 00:50:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:80 - [Vanna] Extracted SQL: SELECT sa.service_area_name AS 服务区名称, COUNT(b.id) AS 档口数量 FROM bss_service_area sa JOIN bss_branch b ON sa.id = b.service_area_id WHERE sa.delete_ts IS NULL AND b.delete_ts IS NULL GROUP BY sa.service_area_name ORDER BY 档口数量 DESC LIMIT 1;
-2025-07-20 00:50:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:320 - 成功生成SQL:
- SELECT sa.service_area_name AS 服务区名称, COUNT(b.id) AS 档口数量 FROM bss_service_area sa JOIN bss_branch b ON sa.id = b.service_area_id WHERE sa.delete_ts IS NULL AND b.delete_ts IS NULL GROUP BY sa.service_area_name ORDER BY 档口数量 DESC LIMIT 1;
-2025-07-20 00:50:01 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:476 - 生成摘要 - 问题: 请问哪个服务区的档口数量最多？
-2025-07-20 00:50:01 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:477 - DataFrame 形状: (1, 2)
-2025-07-20 00:50:01 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:87 - system_content: You are a professional data analysis assistant. The user asked: '请问哪个服务区的档口数量最多？'
-
-Here is the pandas DataFrame data from the query results:|    | 服务区名称   |   档口数量 |
-|---:|:-------------|-----------:|
-|  0 | 南城服务区   |         39 |
-
-Please think and analyze in the context provided and respond accordingly.
-
-2025-07-20 00:50:01 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: Based on the user's question, please briefly summarize this data. Requirements:
-1. Provide only a brief summary without adding extra explanations
-2. If there are numbers in the data, maintain appropriate precision
-Please respond in Chinese. 
-2025-07-20 00:50:01 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:115 - 
-Using model qwen-plus-latest for 136.75 tokens (approx)
-2025-07-20 00:50:01 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:116 - Enable thinking: False, Stream mode: False
-2025-07-20 00:50:01 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:158 - 使用非流式处理模式
-2025-07-20 00:50:02 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:502 - 隐藏thinking内容 - 原始长度: 19, 处理后长度: 19
-2025-07-20 00:50:02 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:504 - 生成的摘要: 南城服务区的档口数量最多，共有39个。...
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:270 - 尝试为问题生成SQL: 
-[CONTEXT]
-User: 请问哪个服务区的档口数量最多？
-Assistant: 南城服务区的档口数量最多，共有39个。
-
-[CURRENT]
-请问这个服务区有几个餐饮档口？
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 每个服务区的营业档口数量（曾经有交易的）？ | similarity: 0.722
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 各分公司管辖服务区的档口总数对比如何？ | similarity: 0.7118
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 哪些服务区只有单一方向的档口？ | similarity: 0.7021
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 分析各服务区关联的路段路线数量TOP10 | similarity: 0.6933
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 当前各运营状态下的服务区数量分布情况？ | similarity: 0.6761
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 各服务区不同类型车辆数量分布 | similarity: 0.6755
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - SQL 阈值过滤: 总数=6, 阈值=0.65, 最少保留=3
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - SQL 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 1: similarity=0.722 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 2: similarity=0.7118 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 3: similarity=0.7021 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 4: similarity=0.6933 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 5: similarity=0.6761 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 6: similarity=0.6755 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 档口基础信息表
--- 描述: 存储服务区内的档口（商铺）基础信息，如名称、编码、所属... | similarity: 0.6139
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路段路线与服务区关联表
--- 描述: 路段路线与服务区关联表，维护路线与服务区之间的... | similarity: 0.5757
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路线与服务区关联表
--- 描述: 路线与服务区关联表，记录路线经过的服务区信息
-cr... | similarity: 0.5731
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路线分段与服务区关联表
--- 描述: 路线分段与服务区关联表，记录路线与服务区的对应... | similarity: 0.5698
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 服务区基础信息表
--- 描述: 记录服务区的基础信息，如编码、名称、公司、经纬度、状... | similarity: 0.568
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路线与服务区关联表
--- 描述: 路线与服务区关联表，记录路线ID与服务区ID的对应... | similarity: 0.5665
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DDL 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DDL 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 1: similarity=0.6139 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 2: similarity=0.5757 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 3: similarity=0.5731 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 4: similarity=0.5698 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 5: similarity=0.568 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 6: similarity=0.5665 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_branch（档口基础信息表）
-bss_branch 表存储服务区内的档口（商铺）基础... | similarity: 0.6332
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（存储高速公路服务区基础信息及版本变更记录）
-bss_serv... | similarity: 0.5755
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（存储高速公路服务区基础信息（名称、编码）及操作记录）
-bss... | similarity: 0.5722
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（服务区基础信息表）
-bss_service_area 表服务... | similarity: 0.5708
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（服务区基础信息表）
-bss_service_area 表记录... | similarity: 0.5675
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（存储高速公路服务区基本信息（名称、编码等））
-bss_ser... | similarity: 0.5625
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DOC 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DOC 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 1: similarity=0.6332 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 2: similarity=0.5755 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 3: similarity=0.5722 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 4: similarity=0.5708 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 5: similarity=0.5675 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 6: similarity=0.5625 ✓
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:104 - 开始生成SQL提示词，问题: 
-[CONTEXT]
-User: 请问哪个服务区的档口数量最多？
-Assistant: 南城服务区的档口数量最多，共有39个。
-
-[CURRENT]
-请问这个服务区有几个餐饮档口？
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:654 - Error SQL Match: 查询所有部门信息 | similarity: 0.2673
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:392 - Error SQL 阈值过滤: 总数=1, 阈值=0.8
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] pgvector.py:410 - Error SQL 过滤结果: 所有 1 条结果都低于阈值 0.8，返回空列表
-2025-07-20 00:51:35 [WARNING] [vanna.BaseLLMChat] pgvector.py:673 - 向量查询找到了 1 条错误SQL示例，但全部被阈值过滤掉.
-2025-07-20 00:51:35 [WARNING] [vanna.BaseLLMChat] pgvector.py:674 - 问题: 
-[CONTEXT]
-User: 请问哪个服务区的档口数量最多？
-Assistant: 南城服务区的档口数量最多，共有39个。
-
-[CURRENT]
-请问这个服务区有几个餐饮档口？
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:159 - 未找到相关的错误SQL示例
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:87 - system_content: You are a PostgreSQL expert. 
-Please help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the response guidelines and format instructions.
-
-===Tables 
--- 中文名: 档口基础信息表
--- 描述: 存储服务区内的档口（商铺）基础信息，如名称、编码、所属服务区、所属公司、品类、品牌等，是商业数据分析的基础实体表。
-create table bss_branch (
-  id varchar(32) not null,              -- 主键ID
-  version integer not null,             -- 数据版本号
-  create_ts timestamp(3),               -- 创建时间
-  created_by varchar(50),               -- 创建人
-  update_ts timestamp(3),               -- 更新时间
-  updated_by varchar(50),               -- 更新人
-  delete_ts timestamp(3),               -- 删除时间
-  deleted_by varchar(50),               -- 删除人
-  branch_name varchar(255),             -- 档口名称
-  branch_no varchar(255),               -- 档口编码
-  service_area_id varchar(32),          -- 服务区ID,外键(关联bss_service_area.id)
-  company_id varchar(32),               -- 公司ID,外键(关联bss_company.ID)
-  classify varchar(256),                -- 品类
-  product_brand varchar(256),           -- 品牌
-  category varchar(256),                -- 类别
-  section_route_id varchar(32),         -- 所属路线ID,外键(关联bss_section_route.id)
-  direction varchar(256),               -- 所在方向
-  is_manual_entry integer default 0,    -- 是否手工录入
-  co_company varchar(256)               -- 合作公司名称
-)
-
--- 中文名: 路段路线与服务区关联表
--- 描述: 路段路线与服务区关联表，维护路线与服务区之间的归属关系。
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线ID，主键,
-  service_area_id varchar(32) not null -- 服务区ID，主键,
-  primary key (section_route_id, service_area_id)
-)
-
--- 中文名: 路线与服务区关联表
--- 描述: 路线与服务区关联表，记录路线经过的服务区信息
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线ID，主键,
-  service_area_id varchar(32) not null -- 服务区ID，主键,
-  primary key (section_route_id, service_area_id)
-)
-
--- 中文名: 路线分段与服务区关联表
--- 描述: 路线分段与服务区关联表，记录路线与服务区的对应关系
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线ID，主键,
-  service_area_id varchar(32) not null -- 服务区ID，主键,
-  primary key (section_route_id, service_area_id)
-)
-
--- 中文名: 服务区基础信息表
--- 描述: 记录服务区的基础信息，如编码、名称、公司、经纬度、状态等，是业务活动的空间节点中心。
-create table bss_service_area (
-  id varchar(32) not null,             -- 主键ID
-  version integer not null,            -- 版本号
-  create_ts timestamp(3),              -- 创建时间
-  created_by varchar(50),              -- 创建人
-  update_ts timestamp(3),              -- 更新时间
-  updated_by varchar(50),              -- 更新人
-  delete_ts timestamp(3),              -- 删除时间
-  deleted_by varchar(50),              -- 删除人
-  service_area_name varchar(255),      -- 服务区名称
-  service_area_no varchar(255),        -- 服务区编码
-  company_id varchar(32),              -- 公司ID,外键(关联bss_company.id)
-  service_position varchar(255),       -- 经纬度
-  service_area_type varchar(50),       -- 服务区类型
-  service_state varchar(50),           -- 服务区状态
-  primary key (id)
-)
-
--- 中文名: 路线与服务区关联表
--- 描述: 路线与服务区关联表，记录路线ID与服务区ID的对应关系，支持路径规划和资源分配。
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线ID，主键,
-  service_area_id varchar(32) not null -- 服务区ID，主键,
-  primary key (section_route_id, service_area_id)
-)
-
-
-===Additional Context 
-
-## bss_branch（档口基础信息表）
-bss_branch 表存储服务区内的档口（商铺）基础信息，如名称、编码、所属服务区、所属公司、品类、品牌等，是商业数据分析的基础实体表。
-字段列表：
-- id (varchar(32)) - 主键ID [示例: 00904903cae681aab7a494c3e88e5acd]
-- version (integer) - 数据版本号 [示例: 1]
-- create_ts (timestamp(3)) - 创建时间 [示例: 2021-10-15 09:46:45.010]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp(3)) - 更新时间 [示例: 2021-10-15 09:46:45.010]
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp(3)) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- branch_name (varchar(255)) - 档口名称 [示例: 于都驿美餐饮南区]
-- branch_no (varchar(255)) - 档口编码（唯一业务标识）[示例: 003585]
-- service_area_id (varchar(32)) - 服务区ID（外键关联bss_service_area.id）[示例: c7e2f26df373e9cb75bd24ddba57f27f]
-- company_id (varchar(32)) - 公司ID（外键关联bss_company.id）[示例: ce5e6f553513dad393694e1fa663aaf4]
-- classify (varchar(256)) - 经营品类，枚举型：餐饮、小吃、便利店、整体租赁、其他 [示例: 餐饮]
-- product_brand (varchar(256)) - 品牌名称 [示例: 驿美餐饮]
-- category (varchar(256)) - 经营类别 [示例: 混沌]
-- section_route_id (varchar(32)) - 所属路线ID（外键关联bss_section_route.id）[示例: lvkcuu94d4487c42z7qltsvxcyz0iqu5]
-- direction (varchar(256)) - 所在方向（枚举：北区/南区/西区/东区/两区）[示例: 南区]
-- is_manual_entry (integer) - 是否手工录入（0=系统自动，1=手工录入）[示例: 0]
-- co_company (varchar(256)) - 合作公司名称 [示例: 江西驿美餐饮管理有限责任公司]
-字段补充说明：
-- service_area_id 外键关联服务区基础信息表(bss_service_area)
-- company_id 外键关联服务区管理公司表(bss_company)
-- section_route_id 外键关联高速线路信息表(bss_section_route)
-- direction 表示档口在服务区内的物理位置分区,为枚举型：北区、南区、西区、东区、两区。
-- is_manual_entry 标识数据来源（系统采集或人工录入）
-- classify 表示经营品类，为枚举型：餐饮、小吃、便利店、整体租赁、其他。
-
-## bss_service_area（存储高速公路服务区基础信息及版本变更记录）
-bss_service_area 表存储高速公路服务区基础信息及版本变更记录，支持服务区全生命周期管理。
-字段列表：
-- id (varchar(32)) - 主键标识符 [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
-- version (integer) - 版本号 [非空] [示例: 3, 6]
-- create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人 [示例: ]
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
-- service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
-- company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
-- service_position (varchar(255)) - 地理坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
-- service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
-- service_state (varchar(50)) - 运营状态 [示例: 开放, 关闭]
-字段补充说明：
-- id 为主键
-- service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
-- service_state 为枚举字段，包含取值：开放、关闭、上传数据
-
-## bss_service_area（存储高速公路服务区基础信息（名称、编码）及操作记录）
-bss_service_area 表存储高速公路服务区基础信息（名称、编码）及操作记录，支撑BSS系统服务区全生命周期管理
-字段列表：
-- id (varchar(32)) - 主键标识符 [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
-- version (integer) - 版本号 [非空] [示例: 3, 6]
-- create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人 [示例: ]
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
-- service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
-- company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
-- service_position (varchar(255)) - 地理位置坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
-- service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
-- service_state (varchar(50)) - 服务区状态 [示例: 开放, 关闭]
-字段补充说明：
-- id 为主键
-- service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
-- service_state 为枚举字段，包含取值：开放、关闭、上传数据
-
-## bss_service_area（服务区基础信息表）
-bss_service_area 表服务区基础信息表，记录服务区名称、编码及操作审计信息
-字段列表：
-- id (varchar(32)) - 主键ID [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
-- version (integer) - 版本号 [非空] [示例: 3, 6]
-- create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人 [示例: ]
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
-- service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
-- company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
-- service_position (varchar(255)) - 地理坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
-- service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
-- service_state (varchar(50)) - 服务区状态 [示例: 开放, 关闭]
-字段补充说明：
-- id 为主键
-- service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
-- service_state 为枚举字段，包含取值：开放、关闭、上传数据
-
-## bss_service_area（服务区基础信息表）
-bss_service_area 表记录高速公路服务区的基础属性，包括服务区编码、名称、方向、公司归属、地理位置、服务类型和状态，是业务分析与服务区定位的核心表。
-字段列表：
-- id (varchar(32)) - 服务区唯一标识（主键，UUID) [示例: 0271d68ef93de9684b7ad8c7aae600b6]
-- version (integer) - 版本号 [示例: 3]
-- create_ts (timestamp(3)) - 创建时间 [示例: 2021-05-21 13:26:40.589]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp(3)) - 更新时间 [示例: 2021-07-10 15:41:28.795]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp(3)) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区]
-- service_area_no (varchar(255)) - 服务区编码（业务唯一标识）[示例: H0814]
-- company_id (varchar(32)) - 公司ID（外键关联bss_company.id）[示例: b1629f07c8d9ac81494fbc1de61f1ea5]
-- service_position (varchar(255)) - 经纬度坐标 [示例: 114.574721,26.825584]
-- service_area_type (varchar(50)) - 服务区类型（枚举：信息化服务区、智能化服务区）[示例: 信息化服务区]
-- service_state (varchar(50)) - 服务区状态（枚举：开放/关闭/上传数据）[示例: 开放]
-字段补充说明：
-- id 为主键，使用 UUID 编码，唯一标识每个服务区。
-- company_id 外键,关联服务区管理公司表(bss_company.id)
-- service_position 经纬度格式为"经度,纬度"
-- service_area_type 为枚举字段，包含两个取值：信息化服务区、智能化服务区。
-- 是多个表(bss_branch, bss_car_day_count等)的核心关联实体
-
-## bss_service_area（存储高速公路服务区基本信息（名称、编码等））
-bss_service_area 表存储高速公路服务区基本信息（名称、编码等），支持服务区运营管理。
-字段列表：
-- id (varchar(32)) - 主键ID [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
-- version (integer) - 版本号 [非空] [示例: 3, 6]
-- create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 最后更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
-- updated_by (varchar(50)) - 最后更新人 [示例: admin]
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除操作人 [示例: ]
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
-- service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
-- company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
-- service_position (varchar(255)) - 地理位置坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
-- service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
-- service_state (varchar(50)) - 服务区状态 [示例: 开放, 关闭]
-字段补充说明：
-- id 为主键
-- service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
-- service_state 为枚举字段，包含取值：开放、关闭、上传数据
-
-===Response Guidelines 
-**IMPORTANT**: All SQL queries MUST use Chinese aliases for ALL columns in SELECT clause.
-
-1. If the provided context is sufficient, please generate a valid SQL query without any explanations for the question. 
-2. If the provided context is almost sufficient but requires knowledge of a specific string in a particular column, please generate an intermediate SQL query to find the distinct strings in that column. Prepend the query with a comment saying intermediate_sql 
-3. If the provided context is insufficient, please explain why it can't be generated. 
-4. **Context Understanding**: If the question follows [CONTEXT]...[CURRENT] format, replace pronouns in [CURRENT] with specific entities from [CONTEXT].
-   - Example: If context mentions 'Nancheng Service Area has the most stalls', and current question is 'How many dining stalls does this service area have?', 
-     interpret it as 'How many dining stalls does Nancheng Service Area have?'
-5. Please use the most relevant table(s). 
-6. If the question has been asked and answered before, please repeat the answer exactly as it was given before. 
-7. Ensure that the output SQL is PostgreSQL-compliant and executable, and free of syntax errors. 
-8. Always add NULLS LAST to ORDER BY clauses to handle NULL values properly (e.g., ORDER BY total DESC NULLS LAST).
-9. **MANDATORY**: ALL columns in SELECT must have Chinese aliases. This is non-negotiable:
-   - Every column MUST use AS with a Chinese alias
-   - Raw column names without aliases are NOT acceptable
-   - Examples: 
-     * CORRECT: SELECT service_name AS 服务区名称, SUM(pay_sum) AS 总收入
-     * WRONG: SELECT service_name, SUM(pay_sum) AS total_revenue
-     * WRONG: SELECT service_name AS service_area, SUM(pay_sum) AS 总收入
-   - Common aliases: COUNT(*) AS 数量, SUM(...) AS 总计, AVG(...) AS 平均值, MAX(...) AS 最大值, MIN(...) AS 最小值
-
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 每个服务区的营业档口数量（曾经有交易的）？
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT service_name, COUNT(DISTINCT branch_no) AS branch_count FROM bss_business_day_data WHERE delete_ts IS NULL GROUP BY service_name;
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 各分公司管辖服务区的档口总数对比如何？
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT c.company_name, COUNT(DISTINCT b.id) AS total_branches FROM bss_company c JOIN bss_service_area sa ON c.id = sa.company_id JOIN bss_branch b ON sa.id = b.service_area_id WHERE c.delete_ts IS NULL AND sa.delete_ts IS NULL AND b.delete_ts IS NULL GROUP BY c.company_name ORDER BY total_branches DESC NULLS LAST;
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 哪些服务区只有单一方向的档口？
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT sa.service_area_name, COUNT(DISTINCT b.direction) AS direction_count, STRING_AGG(DISTINCT b.direction, ', ') AS directions FROM bss_service_area sa JOIN bss_branch b ON sa.id = b.service_area_id WHERE sa.delete_ts IS NULL AND b.delete_ts IS NULL GROUP BY sa.service_area_name HAVING COUNT(DISTINCT b.direction) = 1 ORDER BY sa.service_area_name;
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 分析各服务区关联的路段路线数量TOP10
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT sa.service_area_name AS 服务区名称, COUNT(sr.id) AS 关联路段数 FROM bss_section_route_area_link link JOIN bss_service_area sa ON link.service_area_id = sa.id JOIN bss_section_route sr ON link.section_route_id = sr.id WHERE sa.delete_ts IS NULL GROUP BY sa.service_area_name ORDER BY 关联路段数 DESC LIMIT 10;
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 当前各运营状态下的服务区数量分布情况？
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT service_state AS 运营状态, COUNT(*) AS 数量 FROM bss_service_area WHERE delete_ts IS NULL GROUP BY service_state ORDER BY 数量 DESC;
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 各服务区不同类型车辆数量分布
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT b.service_area_name AS 服务区名称, a.car_type AS 车辆类型, SUM(a.customer_count) AS 车辆总数 FROM bss_car_day_count a JOIN bss_service_area b ON a.service_area_id = b.id AND b.delete_ts IS NULL GROUP BY b.service_area_name, a.car_type ORDER BY 服务区名称, 车辆总数 DESC;
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 
-[CONTEXT]
-User: 请问哪个服务区的档口数量最多？
-Assistant: 南城服务区的档口数量最多，共有39个。
-
-[CURRENT]
-请问这个服务区有几个餐饮档口？
-2025-07-20 00:51:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:70 - [Vanna] SQL Prompt: [{'role': 'system', 'content': 'You are a PostgreSQL expert. \nPlease help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the respon...
-2025-07-20 00:51:35 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:115 - 
-Using model qwen-plus-latest for 3469.25 tokens (approx)
-2025-07-20 00:51:35 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:116 - Enable thinking: False, Stream mode: False
-2025-07-20 00:51:35 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:158 - 使用非流式处理模式
-2025-07-20 00:51:39 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:77 - [Vanna] LLM Response: SELECT COUNT(*) AS 餐饮档口数量 FROM bss_branch WHERE service_area_id = (SELECT id FROM bss_service_area WHERE service_area_name = '南城服务区') AND classify = '餐饮' AND delete_ts IS NULL;
-2025-07-20 00:51:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:80 - [Vanna] Extracted SQL: SELECT COUNT(*) AS 餐饮档口数量 FROM bss_branch WHERE service_area_id = (SELECT id FROM bss_service_area WHERE service_area_name = '南城服务区') AND classify = '餐饮' AND delete_ts IS NULL;
-2025-07-20 00:51:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:320 - 成功生成SQL:
- SELECT COUNT(*) AS 餐饮档口数量 FROM bss_branch WHERE service_area_id = (SELECT id FROM bss_service_area WHERE service_area_name = '南城服务区') AND classify = '餐饮' AND delete_ts IS NULL;
-2025-07-20 00:51:39 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:476 - 生成摘要 - 问题: 请问这个服务区有几个餐饮档口？
-2025-07-20 00:51:39 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:477 - DataFrame 形状: (1, 1)
-2025-07-20 00:51:39 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:87 - system_content: You are a professional data analysis assistant. The user asked: '请问这个服务区有几个餐饮档口？'
-
-Here is the pandas DataFrame data from the query results:|    |   餐饮档口数量 |
-|---:|---------------:|
-|  0 |              6 |
-
-Please think and analyze in the context provided and respond accordingly.
-
-2025-07-20 00:51:39 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: Based on the user's question, please briefly summarize this data. Requirements:
-1. Provide only a brief summary without adding extra explanations
-2. If there are numbers in the data, maintain appropriate precision
-Please respond in Chinese. 
-2025-07-20 00:51:39 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:115 - 
-Using model qwen-plus-latest for 130.5 tokens (approx)
-2025-07-20 00:51:39 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:116 - Enable thinking: False, Stream mode: False
-2025-07-20 00:51:39 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:158 - 使用非流式处理模式
-2025-07-20 00:51:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:502 - 隐藏thinking内容 - 原始长度: 14, 处理后长度: 14
-2025-07-20 00:51:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:504 - 生成的摘要: 这个服务区共有6个餐饮档口。...
-2025-07-20 00:53:21 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:87 - system_content: 
-你是Citu智能数据问答平台的AI助手，为用户提供全面的帮助和支持。
-
-你的职责包括：
-1. 回答关于平台功能和使用方法的问题
-2. 解释数据分析相关的概念和术语
-3. 提供操作指导和建议
-4. 进行友好的日常对话
-5. 回答用户的各类知识问题和常识咨询
-
-回答原则：
-- 保持友好、专业、热情的语调
-- 提供准确、有用的信息
-- 对于通用知识问题，尽量给出准确回答
-- 如果不确定某个问题，诚实地表达不确定性
-- 适时鼓励用户尝试数据查询功能
-- 回答要简洁明了，避免过于冗长
-- 保持中文回答，语言自然流畅
-- 以帮助用户为目标，不要过度限制回答范围
-
-2025-07-20 00:53:21 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 
-[CONTEXT]
-User: 请问哪个服务区的档口数量最多？
-Assistant: 南城服务区的档口数量最多，共有39个。
-User: 请问这个服务区有几个餐饮档口？
-Assistant: 这个服务区共有6个餐饮档口。
-
-[CURRENT]
-请问中国的CBA联赛赛季在哪几个月？
-2025-07-20 00:53:21 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:115 - 
-Using model qwen-plus-latest for 105.0 tokens (approx)
-2025-07-20 00:53:21 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:116 - Enable thinking: False, Stream mode: False
-2025-07-20 00:53:21 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:158 - 使用非流式处理模式
-2025-07-20 00:53:25 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:399 - chat_with_llm隐藏thinking内容 - 原始长度: 90, 处理后长度: 90
-2025-07-20 01:12:13 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:270 - 尝试为问题生成SQL: 
-[CONTEXT]
-User: 请问这个服务区有几个餐饮档口？
-Assistant: 这个服务区共有6个餐饮档口。
-User: 请问中国的CBA联赛赛季在哪几个月？
-Assistant: CBA（中国男子篮球职业联赛）通常从每年的10月开始，持续到次年的4月或5月。常规赛一般在10月至次年1月进行，随后是季后赛，可能延续到4月或5月，具体时间会根据赛季安排略有调整。
-
-[CURRENT]
-请问荔枝通常是几月份上市
-2025-07-20 01:12:14 [DEBUG] [vanna.EmbeddingFunction] embedding_function.py:169 - 成功生成embedding向量，维度: 1024
-2025-07-20 01:12:15 [DEBUG] [vanna.EmbeddingFunction] embedding_function.py:169 - 成功生成embedding向量，维度: 1024
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 每个服务区的营业档口数量（曾经有交易的）？ | similarity: 0.5485
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 计算各服务区行吧支付方式的月均交易次数 | similarity: 0.5436
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 哪些服务区受季节性影响最大？ | similarity: 0.5435
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 统计2023年春节期间各服务区节假日营收占Q1季度总营收比例 | similarity: 0.5363
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 查询2023年6月1日庐山服务区各档口订单数排名 | similarity: 0.5361
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 分析服务区关联路段的创建时间分布情况 | similarity: 0.5287
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - SQL 阈值过滤: 总数=6, 阈值=0.65, 最少保留=3
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:348 - SQL 过滤结果: 保留 3 条, 过滤掉 3 条 (满足阈值: 0, 强制保留: 3)
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 1: similarity=0.5485 ✗
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 2: similarity=0.5436 ✗
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 3: similarity=0.5435 ✗
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 档口基础信息表
--- 描述: 存储服务区内的档口（商铺）基础信息，如名称、编码、所属... | similarity: 0.4857
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 档口日营业数据表
--- 描述: 记录每天每个档口的营业情况，包含微信、支付宝、现金、... | similarity: 0.472
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 服务区基础信息表
--- 描述: 记录服务区的基础信息，如编码、名称、公司、经纬度、状... | similarity: 0.4642
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路线与服务区关联表
--- 描述: 路线与服务区关联表，记录路线经过的服务区信息
-cr... | similarity: 0.4573
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路段路线与服务区关联表
--- 描述: 路段路线与服务区关联表，维护路线与服务区之间的... | similarity: 0.4566
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 记录各服务区每日营业统计数据
--- 描述: 记录各服务区每日营业统计数据，支持运营分... | similarity: 0.4547
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DDL 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:348 - DDL 过滤结果: 保留 3 条, 过滤掉 3 条 (满足阈值: 0, 强制保留: 3)
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 1: similarity=0.4857 ✗
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 2: similarity=0.472 ✗
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 3: similarity=0.4642 ✗
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_branch（档口基础信息表）
-bss_branch 表存储服务区内的档口（商铺）基础... | similarity: 0.506
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（服务区基础信息表）
-bss_service_area 表服务... | similarity: 0.4792
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（存储高速公路服务区基础信息及版本变更记录）
-bss_serv... | similarity: 0.479
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（服务区基础信息表）
-bss_service_area 表记录... | similarity: 0.4752
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（存储高速公路服务区基础信息（名称、编码）及操作记录）
-bss... | similarity: 0.4732
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（存储高速公路服务区基本信息（名称、编码等））
-bss_ser... | similarity: 0.4689
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DOC 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:348 - DOC 过滤结果: 保留 3 条, 过滤掉 3 条 (满足阈值: 1, 强制保留: 2)
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 1: similarity=0.506 ✓
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 2: similarity=0.4792 ✗
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 3: similarity=0.479 ✗
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:104 - 开始生成SQL提示词，问题: 
-[CONTEXT]
-User: 请问这个服务区有几个餐饮档口？
-Assistant: 这个服务区共有6个餐饮档口。
-User: 请问中国的CBA联赛赛季在哪几个月？
-Assistant: CBA（中国男子篮球职业联赛）通常从每年的10月开始，持续到次年的4月或5月。常规赛一般在10月至次年1月进行，随后是季后赛，可能延续到4月或5月，具体时间会根据赛季安排略有调整。
-
-[CURRENT]
-请问荔枝通常是几月份上市
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:654 - Error SQL Match: 查询所有部门信息 | similarity: 0.2301
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:392 - Error SQL 阈值过滤: 总数=1, 阈值=0.8
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] pgvector.py:410 - Error SQL 过滤结果: 所有 1 条结果都低于阈值 0.8，返回空列表
-2025-07-20 01:12:15 [WARNING] [vanna.BaseLLMChat] pgvector.py:673 - 向量查询找到了 1 条错误SQL示例，但全部被阈值过滤掉.
-2025-07-20 01:12:15 [WARNING] [vanna.BaseLLMChat] pgvector.py:674 - 问题: 
-[CONTEXT]
-User: 请问这个服务区有几个餐饮档口？
-Assistant: 这个服务区共有6个餐饮档口。
-User: 请问中国的CBA联赛赛季在哪几个月？
-Assistant: CBA（中国男子篮球职业联赛）通常从每年的10月开始，持续到次年的4月或5月。常规赛一般在10月至次年1月进行，随后是季后赛，可能延续到4月或5月，具体时间会根据赛季安排略有调整。
-
-[CURRENT]
-请问荔枝通常是几月份上市
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:159 - 未找到相关的错误SQL示例
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:87 - system_content: You are a PostgreSQL expert. 
-Please help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the response guidelines and format instructions.
-
-===Tables 
--- 中文名: 档口基础信息表
--- 描述: 存储服务区内的档口（商铺）基础信息，如名称、编码、所属服务区、所属公司、品类、品牌等，是商业数据分析的基础实体表。
-create table bss_branch (
-  id varchar(32) not null,              -- 主键ID
-  version integer not null,             -- 数据版本号
-  create_ts timestamp(3),               -- 创建时间
-  created_by varchar(50),               -- 创建人
-  update_ts timestamp(3),               -- 更新时间
-  updated_by varchar(50),               -- 更新人
-  delete_ts timestamp(3),               -- 删除时间
-  deleted_by varchar(50),               -- 删除人
-  branch_name varchar(255),             -- 档口名称
-  branch_no varchar(255),               -- 档口编码
-  service_area_id varchar(32),          -- 服务区ID,外键(关联bss_service_area.id)
-  company_id varchar(32),               -- 公司ID,外键(关联bss_company.ID)
-  classify varchar(256),                -- 品类
-  product_brand varchar(256),           -- 品牌
-  category varchar(256),                -- 类别
-  section_route_id varchar(32),         -- 所属路线ID,外键(关联bss_section_route.id)
-  direction varchar(256),               -- 所在方向
-  is_manual_entry integer default 0,    -- 是否手工录入
-  co_company varchar(256)               -- 合作公司名称
-)
-
--- 中文名: 档口日营业数据表
--- 描述: 记录每天每个档口的营业情况，包含微信、支付宝、现金、金豆等支付方式的金额与订单数，是核心交易数据表。
-create table bss_business_day_data (
-  id varchar(32) not null,        -- 主键ID
-  version integer not null,       -- 数据版本号
-  create_ts timestamp(3),         -- 创建时间
-  created_by varchar(50),         -- 创建人
-  update_ts timestamp(3),         -- 更新时间
-  updated_by varchar(50),         -- 更新人
-  delete_ts timestamp(3),         -- 删除时间
-  deleted_by varchar(50),         -- 删除人
-  oper_date date,                 -- 统计日期
-  service_no varchar(255),        -- 服务区编码
-  service_name varchar(255),      -- 服务区名称
-  branch_no varchar(255),         -- 档口编码
-  branch_name varchar(255),       -- 档口名称
-  wx numeric(19,4),               -- 微信支付金额
-  wx_order integer,               -- 微信支付订单数量
-  zfb numeric(19,4),              -- 支付宝支付金额
-  zf_order integer,               -- 支付宝支付订单数量
-  rmb numeric(19,4),              -- 现金支付金额
-  rmb_order integer,              -- 现金支付订单数量
-  xs numeric(19,4),               -- 行吧支付金额
-  xs_order integer,               -- 行吧支付订单数量
-  jd numeric(19,4),               -- 金豆支付金额
-  jd_order integer,               -- 金豆支付订单数量
-  order_sum integer,              -- 订单总数
-  pay_sum numeric(19,4),          -- 支付总金额
-  source_type integer,            -- 数据来源类型ID
-  primary key (id)
-)
-
--- 中文名: 服务区基础信息表
--- 描述: 记录服务区的基础信息，如编码、名称、公司、经纬度、状态等，是业务活动的空间节点中心。
-create table bss_service_area (
-  id varchar(32) not null,             -- 主键ID
-  version integer not null,            -- 版本号
-  create_ts timestamp(3),              -- 创建时间
-  created_by varchar(50),              -- 创建人
-  update_ts timestamp(3),              -- 更新时间
-  updated_by varchar(50),              -- 更新人
-  delete_ts timestamp(3),              -- 删除时间
-  deleted_by varchar(50),              -- 删除人
-  service_area_name varchar(255),      -- 服务区名称
-  service_area_no varchar(255),        -- 服务区编码
-  company_id varchar(32),              -- 公司ID,外键(关联bss_company.id)
-  service_position varchar(255),       -- 经纬度
-  service_area_type varchar(50),       -- 服务区类型
-  service_state varchar(50),           -- 服务区状态
-  primary key (id)
-)
-
-
-===Additional Context 
-
-## bss_branch（档口基础信息表）
-bss_branch 表存储服务区内的档口（商铺）基础信息，如名称、编码、所属服务区、所属公司、品类、品牌等，是商业数据分析的基础实体表。
-字段列表：
-- id (varchar(32)) - 主键ID [示例: 00904903cae681aab7a494c3e88e5acd]
-- version (integer) - 数据版本号 [示例: 1]
-- create_ts (timestamp(3)) - 创建时间 [示例: 2021-10-15 09:46:45.010]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp(3)) - 更新时间 [示例: 2021-10-15 09:46:45.010]
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp(3)) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- branch_name (varchar(255)) - 档口名称 [示例: 于都驿美餐饮南区]
-- branch_no (varchar(255)) - 档口编码（唯一业务标识）[示例: 003585]
-- service_area_id (varchar(32)) - 服务区ID（外键关联bss_service_area.id）[示例: c7e2f26df373e9cb75bd24ddba57f27f]
-- company_id (varchar(32)) - 公司ID（外键关联bss_company.id）[示例: ce5e6f553513dad393694e1fa663aaf4]
-- classify (varchar(256)) - 经营品类，枚举型：餐饮、小吃、便利店、整体租赁、其他 [示例: 餐饮]
-- product_brand (varchar(256)) - 品牌名称 [示例: 驿美餐饮]
-- category (varchar(256)) - 经营类别 [示例: 混沌]
-- section_route_id (varchar(32)) - 所属路线ID（外键关联bss_section_route.id）[示例: lvkcuu94d4487c42z7qltsvxcyz0iqu5]
-- direction (varchar(256)) - 所在方向（枚举：北区/南区/西区/东区/两区）[示例: 南区]
-- is_manual_entry (integer) - 是否手工录入（0=系统自动，1=手工录入）[示例: 0]
-- co_company (varchar(256)) - 合作公司名称 [示例: 江西驿美餐饮管理有限责任公司]
-字段补充说明：
-- service_area_id 外键关联服务区基础信息表(bss_service_area)
-- company_id 外键关联服务区管理公司表(bss_company)
-- section_route_id 外键关联高速线路信息表(bss_section_route)
-- direction 表示档口在服务区内的物理位置分区,为枚举型：北区、南区、西区、东区、两区。
-- is_manual_entry 标识数据来源（系统采集或人工录入）
-- classify 表示经营品类，为枚举型：餐饮、小吃、便利店、整体租赁、其他。
-
-## bss_service_area（服务区基础信息表）
-bss_service_area 表服务区基础信息表，记录服务区名称、编码及操作审计信息
-字段列表：
-- id (varchar(32)) - 主键ID [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
-- version (integer) - 版本号 [非空] [示例: 3, 6]
-- create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人 [示例: ]
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
-- service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
-- company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
-- service_position (varchar(255)) - 地理坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
-- service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
-- service_state (varchar(50)) - 服务区状态 [示例: 开放, 关闭]
-字段补充说明：
-- id 为主键
-- service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
-- service_state 为枚举字段，包含取值：开放、关闭、上传数据
-
-## bss_service_area（存储高速公路服务区基础信息及版本变更记录）
-bss_service_area 表存储高速公路服务区基础信息及版本变更记录，支持服务区全生命周期管理。
-字段列表：
-- id (varchar(32)) - 主键标识符 [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
-- version (integer) - 版本号 [非空] [示例: 3, 6]
-- create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人 [示例: ]
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
-- service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
-- company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
-- service_position (varchar(255)) - 地理坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
-- service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
-- service_state (varchar(50)) - 运营状态 [示例: 开放, 关闭]
-字段补充说明：
-- id 为主键
-- service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
-- service_state 为枚举字段，包含取值：开放、关闭、上传数据
-
-===Response Guidelines 
-**IMPORTANT**: All SQL queries MUST use Chinese aliases for ALL columns in SELECT clause.
-
-1. If the provided context is sufficient, please generate a valid SQL query without any explanations for the question. 
-2. If the provided context is almost sufficient but requires knowledge of a specific string in a particular column, please generate an intermediate SQL query to find the distinct strings in that column. Prepend the query with a comment saying intermediate_sql 
-3. If the provided context is insufficient, please explain why it can't be generated. 
-4. **Context Understanding**: If the question follows [CONTEXT]...[CURRENT] format, replace pronouns in [CURRENT] with specific entities from [CONTEXT].
-   - Example: If context mentions 'Nancheng Service Area has the most stalls', and current question is 'How many dining stalls does this service area have?', 
-     interpret it as 'How many dining stalls does Nancheng Service Area have?'
-5. Please use the most relevant table(s). 
-6. If the question has been asked and answered before, please repeat the answer exactly as it was given before. 
-7. Ensure that the output SQL is PostgreSQL-compliant and executable, and free of syntax errors. 
-8. Always add NULLS LAST to ORDER BY clauses to handle NULL values properly (e.g., ORDER BY total DESC NULLS LAST).
-9. **MANDATORY**: ALL columns in SELECT must have Chinese aliases. This is non-negotiable:
-   - Every column MUST use AS with a Chinese alias
-   - Raw column names without aliases are NOT acceptable
-   - Examples: 
-     * CORRECT: SELECT service_name AS 服务区名称, SUM(pay_sum) AS 总收入
-     * WRONG: SELECT service_name, SUM(pay_sum) AS total_revenue
-     * WRONG: SELECT service_name AS service_area, SUM(pay_sum) AS 总收入
-   - Common aliases: COUNT(*) AS 数量, SUM(...) AS 总计, AVG(...) AS 平均值, MAX(...) AS 最大值, MIN(...) AS 最小值
-
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 每个服务区的营业档口数量（曾经有交易的）？
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT service_name, COUNT(DISTINCT branch_no) AS branch_count FROM bss_business_day_data WHERE delete_ts IS NULL GROUP BY service_name;
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 计算各服务区行吧支付方式的月均交易次数
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT service_name AS 服务区名称, EXTRACT(MONTH FROM oper_date) AS 月份, AVG(xs_order) AS 月均交易次数 FROM bss_business_day_data WHERE delete_ts IS NULL GROUP BY 服务区名称, 月份 ORDER BY 服务区名称, 月份;
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 哪些服务区受季节性影响最大？
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: WITH monthly_service_revenue AS (SELECT service_name, EXTRACT(MONTH FROM oper_date) AS month, SUM(pay_sum) AS monthly_revenue FROM bss_business_day_data WHERE delete_ts IS NULL GROUP BY service_name, EXTRACT(MONTH FROM oper_date)), service_seasonality AS (SELECT service_name, MAX(monthly_revenue) AS max_monthly, MIN(monthly_revenue) AS min_monthly, ROUND((MAX(monthly_revenue) - MIN(monthly_revenue)) * 100.0 / MIN(monthly_revenue), 2) AS seasonality_index FROM monthly_service_revenue GROUP BY service_name HAVING MIN(monthly_revenue) > 0) SELECT service_name, max_monthly, min_monthly, seasonality_index FROM service_seasonality ORDER BY seasonality_index DESC NULLS LAST LIMIT 10;
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 
-[CONTEXT]
-User: 请问这个服务区有几个餐饮档口？
-Assistant: 这个服务区共有6个餐饮档口。
-User: 请问中国的CBA联赛赛季在哪几个月？
-Assistant: CBA（中国男子篮球职业联赛）通常从每年的10月开始，持续到次年的4月或5月。常规赛一般在10月至次年1月进行，随后是季后赛，可能延续到4月或5月，具体时间会根据赛季安排略有调整。
-
-[CURRENT]
-请问荔枝通常是几月份上市
-2025-07-20 01:12:15 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:70 - [Vanna] SQL Prompt: [{'role': 'system', 'content': "You are a PostgreSQL expert. \nPlease help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the respon...
-2025-07-20 01:12:15 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:115 - 
-Using model qwen-plus-latest for 2561.75 tokens (approx)
-2025-07-20 01:12:15 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:116 - Enable thinking: False, Stream mode: False
-2025-07-20 01:12:15 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:158 - 使用非流式处理模式
-2025-07-20 01:12:17 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:77 - [Vanna] LLM Response: 荔枝通常在每年的5月至7月期间上市，具体时间取决于产地和当年的气候条件。例如，广东、广西等主要产区的荔枝一般在6月达到上市高峰。
-2025-07-20 01:12:17 [WARNING] [vanna.BaseLLMChat] base_llm_chat.py:311 - 返回内容不像有效SQL: 荔枝通常在每年的5月至7月期间上市，具体时间取决于产地和当年的气候条件。例如，广东、广西等主要产区的荔枝一般在6月达到上市高峰。
-2025-07-20 01:12:17 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:316 - 隐藏thinking内容 - SQL生成非有效SQL内容
-2025-07-20 01:57:09 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-20 01:57:09 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-20 01:57:09 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-20 01:57:09 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-20 01:57:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-20 01:57:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-20 01:57:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-20 01:57:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-20 01:57:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-20 01:57:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-20 01:57:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-20 01:57:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-20 01:57:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-20 01:57:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-20 01:57:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-20 01:57:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x00000160F224B950>
-2025-07-20 01:57:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-20 01:57:09 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-20 01:57:09 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-20 01:57:10 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-20 01:57:10 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-20 01:57:10 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-20 01:57:10 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-20 01:57:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-20 01:57:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-20 01:57:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-20 01:57:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-20 01:57:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-20 01:57:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-20 01:57:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-20 01:57:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-20 01:57:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-20 01:57:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-20 01:57:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-20 01:57:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x00000160F242E090>
-2025-07-20 01:57:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-20 01:57:10 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-20 01:57:10 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-20 01:57:12 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-20 01:57:35 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-20 01:57:35 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-20 01:57:35 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-20 01:57:35 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-20 01:57:35 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-20 01:57:35 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-20 01:57:35 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-20 01:57:35 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-20 01:57:35 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-20 01:57:35 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-20 01:57:35 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-20 01:57:35 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-20 01:57:35 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-20 01:57:35 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-20 01:57:35 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x00000160F4774D40>
-2025-07-20 01:57:35 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-20 01:57:35 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-20 01:57:35 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-20 01:57:37 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:270 - 尝试为问题生成SQL: 请问哪个服务区的档口数量最多？
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 分析每个服务区关联的路线数量并找出覆盖路线最多的服务区 | similarity: 0.7464
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 哪些服务区只有单一方向的档口？ | similarity: 0.7459
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 分析各服务区关联的路段路线数量TOP10 | similarity: 0.7405
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 每个服务区的营业档口数量（曾经有交易的）？ | similarity: 0.7326
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 最近30天中车流量最高的服务区？ | similarity: 0.7325
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 各分公司管辖服务区的档口总数对比如何？ | similarity: 0.7275
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - SQL 阈值过滤: 总数=6, 阈值=0.65, 最少保留=3
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - SQL 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 1: similarity=0.7464 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 2: similarity=0.7459 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 3: similarity=0.7405 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 4: similarity=0.7326 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 5: similarity=0.7325 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 6: similarity=0.7275 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 档口基础信息表
--- 描述: 存储服务区内的档口（商铺）基础信息，如名称、编码、所属... | similarity: 0.649
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路段路线与服务区关联表
--- 描述: 路段路线与服务区关联表，维护路线与服务区之间的... | similarity: 0.6368
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路线与服务区关联表
--- 描述: 路线与服务区关联表，记录路线经过的服务区信息
-cr... | similarity: 0.6357
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路线分段与服务区关联表
--- 描述: 路线分段与服务区关联表，记录路线与服务区的对应... | similarity: 0.6313
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路线与服务区关联表
--- 描述: 路线与服务区关联表，记录路线ID与服务区ID的对应... | similarity: 0.626
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 存储路线段与服务区关联关系
--- 描述: 存储路线段与服务区关联关系，管理高速线路与... | similarity: 0.6199
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DDL 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DDL 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 1: similarity=0.649 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 2: similarity=0.6368 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 3: similarity=0.6357 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 4: similarity=0.6313 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 5: similarity=0.626 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 6: similarity=0.6199 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_branch（档口基础信息表）
-bss_branch 表存储服务区内的档口（商铺）基础... | similarity: 0.6543
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（存储高速公路服务区基础信息及版本变更记录）
-bss_serv... | similarity: 0.6345
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（存储高速公路服务区基础信息（名称、编码）及操作记录）
-bss... | similarity: 0.6339
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route_area_link（路线与服务区关联表）
-bss_sect... | similarity: 0.6287
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（服务区基础信息表）
-bss_service_area 表记录... | similarity: 0.627
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route_area_link（记录高速公路路段路线与服务区的关联关系... | similarity: 0.6263
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DOC 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DOC 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 1: similarity=0.6543 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 2: similarity=0.6345 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 3: similarity=0.6339 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 4: similarity=0.6287 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 5: similarity=0.627 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 6: similarity=0.6263 ✓
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:104 - 开始生成SQL提示词，问题: 请问哪个服务区的档口数量最多？
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:654 - Error SQL Match: 查询所有部门信息 | similarity: 0.2713
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:392 - Error SQL 阈值过滤: 总数=1, 阈值=0.8
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] pgvector.py:410 - Error SQL 过滤结果: 所有 1 条结果都低于阈值 0.8，返回空列表
-2025-07-20 01:57:37 [WARNING] [vanna.BaseLLMChat] pgvector.py:673 - 向量查询找到了 1 条错误SQL示例，但全部被阈值过滤掉.
-2025-07-20 01:57:37 [WARNING] [vanna.BaseLLMChat] pgvector.py:674 - 问题: 请问哪个服务区的档口数量最多？
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:159 - 未找到相关的错误SQL示例
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:87 - system_content: You are a PostgreSQL expert. 
-Please help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the response guidelines and format instructions.
-
-===Tables 
--- 中文名: 档口基础信息表
--- 描述: 存储服务区内的档口（商铺）基础信息，如名称、编码、所属服务区、所属公司、品类、品牌等，是商业数据分析的基础实体表。
-create table bss_branch (
-  id varchar(32) not null,              -- 主键ID
-  version integer not null,             -- 数据版本号
-  create_ts timestamp(3),               -- 创建时间
-  created_by varchar(50),               -- 创建人
-  update_ts timestamp(3),               -- 更新时间
-  updated_by varchar(50),               -- 更新人
-  delete_ts timestamp(3),               -- 删除时间
-  deleted_by varchar(50),               -- 删除人
-  branch_name varchar(255),             -- 档口名称
-  branch_no varchar(255),               -- 档口编码
-  service_area_id varchar(32),          -- 服务区ID,外键(关联bss_service_area.id)
-  company_id varchar(32),               -- 公司ID,外键(关联bss_company.ID)
-  classify varchar(256),                -- 品类
-  product_brand varchar(256),           -- 品牌
-  category varchar(256),                -- 类别
-  section_route_id varchar(32),         -- 所属路线ID,外键(关联bss_section_route.id)
-  direction varchar(256),               -- 所在方向
-  is_manual_entry integer default 0,    -- 是否手工录入
-  co_company varchar(256)               -- 合作公司名称
-)
-
--- 中文名: 路段路线与服务区关联表
--- 描述: 路段路线与服务区关联表，维护路线与服务区之间的归属关系。
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线ID，主键,
-  service_area_id varchar(32) not null -- 服务区ID，主键,
-  primary key (section_route_id, service_area_id)
-)
-
--- 中文名: 路线与服务区关联表
--- 描述: 路线与服务区关联表，记录路线经过的服务区信息
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线ID，主键,
-  service_area_id varchar(32) not null -- 服务区ID，主键,
-  primary key (section_route_id, service_area_id)
-)
-
--- 中文名: 路线分段与服务区关联表
--- 描述: 路线分段与服务区关联表，记录路线与服务区的对应关系
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线ID，主键,
-  service_area_id varchar(32) not null -- 服务区ID，主键,
-  primary key (section_route_id, service_area_id)
-)
-
--- 中文名: 路线与服务区关联表
--- 描述: 路线与服务区关联表，记录路线ID与服务区ID的对应关系，支持路径规划和资源分配。
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线ID，主键,
-  service_area_id varchar(32) not null -- 服务区ID，主键,
-  primary key (section_route_id, service_area_id)
-)
-
--- 中文名: 存储路线段与服务区关联关系
--- 描述: 存储路线段与服务区关联关系，管理高速线路与服务区归属
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线ID，主键,
-  service_area_id varchar(32) not null -- 服务区编码，主键,
-  primary key (section_route_id, service_area_id)
-)
-
-
-===Additional Context 
-
-## bss_branch（档口基础信息表）
-bss_branch 表存储服务区内的档口（商铺）基础信息，如名称、编码、所属服务区、所属公司、品类、品牌等，是商业数据分析的基础实体表。
-字段列表：
-- id (varchar(32)) - 主键ID [示例: 00904903cae681aab7a494c3e88e5acd]
-- version (integer) - 数据版本号 [示例: 1]
-- create_ts (timestamp(3)) - 创建时间 [示例: 2021-10-15 09:46:45.010]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp(3)) - 更新时间 [示例: 2021-10-15 09:46:45.010]
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp(3)) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- branch_name (varchar(255)) - 档口名称 [示例: 于都驿美餐饮南区]
-- branch_no (varchar(255)) - 档口编码（唯一业务标识）[示例: 003585]
-- service_area_id (varchar(32)) - 服务区ID（外键关联bss_service_area.id）[示例: c7e2f26df373e9cb75bd24ddba57f27f]
-- company_id (varchar(32)) - 公司ID（外键关联bss_company.id）[示例: ce5e6f553513dad393694e1fa663aaf4]
-- classify (varchar(256)) - 经营品类，枚举型：餐饮、小吃、便利店、整体租赁、其他 [示例: 餐饮]
-- product_brand (varchar(256)) - 品牌名称 [示例: 驿美餐饮]
-- category (varchar(256)) - 经营类别 [示例: 混沌]
-- section_route_id (varchar(32)) - 所属路线ID（外键关联bss_section_route.id）[示例: lvkcuu94d4487c42z7qltsvxcyz0iqu5]
-- direction (varchar(256)) - 所在方向（枚举：北区/南区/西区/东区/两区）[示例: 南区]
-- is_manual_entry (integer) - 是否手工录入（0=系统自动，1=手工录入）[示例: 0]
-- co_company (varchar(256)) - 合作公司名称 [示例: 江西驿美餐饮管理有限责任公司]
-字段补充说明：
-- service_area_id 外键关联服务区基础信息表(bss_service_area)
-- company_id 外键关联服务区管理公司表(bss_company)
-- section_route_id 外键关联高速线路信息表(bss_section_route)
-- direction 表示档口在服务区内的物理位置分区,为枚举型：北区、南区、西区、东区、两区。
-- is_manual_entry 标识数据来源（系统采集或人工录入）
-- classify 表示经营品类，为枚举型：餐饮、小吃、便利店、整体租赁、其他。
-
-## bss_service_area（存储高速公路服务区基础信息及版本变更记录）
-bss_service_area 表存储高速公路服务区基础信息及版本变更记录，支持服务区全生命周期管理。
-字段列表：
-- id (varchar(32)) - 主键标识符 [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
-- version (integer) - 版本号 [非空] [示例: 3, 6]
-- create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人 [示例: ]
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
-- service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
-- company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
-- service_position (varchar(255)) - 地理坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
-- service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
-- service_state (varchar(50)) - 运营状态 [示例: 开放, 关闭]
-字段补充说明：
-- id 为主键
-- service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
-- service_state 为枚举字段，包含取值：开放、关闭、上传数据
-
-## bss_service_area（存储高速公路服务区基础信息（名称、编码）及操作记录）
-bss_service_area 表存储高速公路服务区基础信息（名称、编码）及操作记录，支撑BSS系统服务区全生命周期管理
-字段列表：
-- id (varchar(32)) - 主键标识符 [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
-- version (integer) - 版本号 [非空] [示例: 3, 6]
-- create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人 [示例: ]
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
-- service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
-- company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
-- service_position (varchar(255)) - 地理位置坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
-- service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
-- service_state (varchar(50)) - 服务区状态 [示例: 开放, 关闭]
-字段补充说明：
-- id 为主键
-- service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
-- service_state 为枚举字段，包含取值：开放、关闭、上传数据
-
-## bss_section_route_area_link（路线与服务区关联表）
-bss_section_route_area_link 表路线与服务区关联表，记录路线ID与服务区ID的对应关系，支持路径规划和资源分配。
-字段列表：
-- section_route_id (varchar(32)) - 路段路线ID [主键, 非空] [示例: v8elrsfs5f7lt7jl8a6p87smfzesn3rz, hxzi2iim238e3s1eajjt1enmh9o4h3wp]
-- service_area_id (varchar(32)) - 服务区ID [主键, 非空] [示例: 08e01d7402abd1d6a4d9fdd5df855ef8, 091662311d2c737029445442ff198c4c]
-字段补充说明：
-- 复合主键：section_route_id, service_area_id
-
-## bss_service_area（服务区基础信息表）
-bss_service_area 表记录高速公路服务区的基础属性，包括服务区编码、名称、方向、公司归属、地理位置、服务类型和状态，是业务分析与服务区定位的核心表。
-字段列表：
-- id (varchar(32)) - 服务区唯一标识（主键，UUID) [示例: 0271d68ef93de9684b7ad8c7aae600b6]
-- version (integer) - 版本号 [示例: 3]
-- create_ts (timestamp(3)) - 创建时间 [示例: 2021-05-21 13:26:40.589]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp(3)) - 更新时间 [示例: 2021-07-10 15:41:28.795]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp(3)) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区]
-- service_area_no (varchar(255)) - 服务区编码（业务唯一标识）[示例: H0814]
-- company_id (varchar(32)) - 公司ID（外键关联bss_company.id）[示例: b1629f07c8d9ac81494fbc1de61f1ea5]
-- service_position (varchar(255)) - 经纬度坐标 [示例: 114.574721,26.825584]
-- service_area_type (varchar(50)) - 服务区类型（枚举：信息化服务区、智能化服务区）[示例: 信息化服务区]
-- service_state (varchar(50)) - 服务区状态（枚举：开放/关闭/上传数据）[示例: 开放]
-字段补充说明：
-- id 为主键，使用 UUID 编码，唯一标识每个服务区。
-- company_id 外键,关联服务区管理公司表(bss_company.id)
-- service_position 经纬度格式为"经度,纬度"
-- service_area_type 为枚举字段，包含两个取值：信息化服务区、智能化服务区。
-- 是多个表(bss_branch, bss_car_day_count等)的核心关联实体
-
-## bss_section_route_area_link（记录高速公路路段路线与服务区的关联关系）
-bss_section_route_area_link 表记录高速公路路段路线与服务区的关联关系，支撑路线规划与服务区运营管理。
-字段列表：
-- section_route_id (varchar(32)) - 路段路线ID [主键, 非空] [示例: v8elrsfs5f7lt7jl8a6p87smfzesn3rz, hxzi2iim238e3s1eajjt1enmh9o4h3wp]
-- service_area_id (varchar(32)) - 服务区ID [主键, 非空] [示例: 08e01d7402abd1d6a4d9fdd5df855ef8, 091662311d2c737029445442ff198c4c]
-字段补充说明：
-- 复合主键：section_route_id, service_area_id
-
-===Response Guidelines 
-**IMPORTANT**: All SQL queries MUST use Chinese aliases for ALL columns in SELECT clause.
-
-1. If the provided context is sufficient, please generate a valid SQL query without any explanations for the question. 
-2. If the provided context is almost sufficient but requires knowledge of a specific string in a particular column, please generate an intermediate SQL query to find the distinct strings in that column. Prepend the query with a comment saying intermediate_sql 
-3. If the provided context is insufficient, please explain why it can't be generated. 
-4. **Context Understanding**: If the question follows [CONTEXT]...[CURRENT] format, replace pronouns in [CURRENT] with specific entities from [CONTEXT].
-   - Example: If context mentions 'Nancheng Service Area has the most stalls', and current question is 'How many dining stalls does this service area have?', 
-     interpret it as 'How many dining stalls does Nancheng Service Area have?'
-5. Please use the most relevant table(s). 
-6. If the question has been asked and answered before, please repeat the answer exactly as it was given before. 
-7. Ensure that the output SQL is PostgreSQL-compliant and executable, and free of syntax errors. 
-8. Always add NULLS LAST to ORDER BY clauses to handle NULL values properly (e.g., ORDER BY total DESC NULLS LAST).
-9. **MANDATORY**: ALL columns in SELECT must have Chinese aliases. This is non-negotiable:
-   - Every column MUST use AS with a Chinese alias
-   - Raw column names without aliases are NOT acceptable
-   - Examples: 
-     * CORRECT: SELECT service_name AS 服务区名称, SUM(pay_sum) AS 总收入
-     * WRONG: SELECT service_name, SUM(pay_sum) AS total_revenue
-     * WRONG: SELECT service_name AS service_area, SUM(pay_sum) AS 总收入
-   - Common aliases: COUNT(*) AS 数量, SUM(...) AS 总计, AVG(...) AS 平均值, MAX(...) AS 最大值, MIN(...) AS 最小值
-
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 分析每个服务区关联的路线数量并找出覆盖路线最多的服务区
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT service_area_id AS 服务区ID, COUNT(section_route_id) AS 关联路线数 FROM bss_section_route_area_link GROUP BY service_area_id ORDER BY 关联路线数 DESC LIMIT 1;
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 哪些服务区只有单一方向的档口？
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT sa.service_area_name, COUNT(DISTINCT b.direction) AS direction_count, STRING_AGG(DISTINCT b.direction, ', ') AS directions FROM bss_service_area sa JOIN bss_branch b ON sa.id = b.service_area_id WHERE sa.delete_ts IS NULL AND b.delete_ts IS NULL GROUP BY sa.service_area_name HAVING COUNT(DISTINCT b.direction) = 1 ORDER BY sa.service_area_name;
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 分析各服务区关联的路段路线数量TOP10
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT sa.service_area_name AS 服务区名称, COUNT(sr.id) AS 关联路段数 FROM bss_section_route_area_link link JOIN bss_service_area sa ON link.service_area_id = sa.id JOIN bss_section_route sr ON link.section_route_id = sr.id WHERE sa.delete_ts IS NULL GROUP BY sa.service_area_name ORDER BY 关联路段数 DESC LIMIT 10;
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 每个服务区的营业档口数量（曾经有交易的）？
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT service_name, COUNT(DISTINCT branch_no) AS branch_count FROM bss_business_day_data WHERE delete_ts IS NULL GROUP BY service_name;
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 最近30天中车流量最高的服务区？
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT s.service_area_name, SUM(c.customer_count) AS total_cars FROM bss_car_day_count c JOIN bss_service_area s ON c.service_area_id = s.id WHERE c.count_date >= CURRENT_DATE - INTERVAL '30 day' GROUP BY s.service_area_name ORDER BY total_cars DESC NULLS LAST LIMIT 10;
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 各分公司管辖服务区的档口总数对比如何？
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT c.company_name, COUNT(DISTINCT b.id) AS total_branches FROM bss_company c JOIN bss_service_area sa ON c.id = sa.company_id JOIN bss_branch b ON sa.id = b.service_area_id WHERE c.delete_ts IS NULL AND sa.delete_ts IS NULL AND b.delete_ts IS NULL GROUP BY c.company_name ORDER BY total_branches DESC NULLS LAST;
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 请问哪个服务区的档口数量最多？
-2025-07-20 01:57:37 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:70 - [Vanna] SQL Prompt: [{'role': 'system', 'content': 'You are a PostgreSQL expert. \nPlease help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the respon...
-2025-07-20 01:57:37 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:115 - 
-Using model qwen-plus-latest for 2977.0 tokens (approx)
-2025-07-20 01:57:37 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:116 - Enable thinking: False, Stream mode: False
-2025-07-20 01:57:37 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:158 - 使用非流式处理模式
-2025-07-20 01:57:41 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:77 - [Vanna] LLM Response: SELECT sa.service_area_name AS 服务区名称, COUNT(b.id) AS 档口数量 FROM bss_service_area sa JOIN bss_branch b ON sa.id = b.service_area_id WHERE sa.delete_ts IS NULL AND b.delete_ts IS NULL GROUP BY sa.service...
-2025-07-20 01:57:41 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:80 - [Vanna] Extracted SQL: SELECT sa.service_area_name AS 服务区名称, COUNT(b.id) AS 档口数量 FROM bss_service_area sa JOIN bss_branch b ON sa.id = b.service_area_id WHERE sa.delete_ts IS NULL AND b.delete_ts IS NULL GROUP BY sa.service_area_name ORDER BY 档口数量 DESC LIMIT 1;
-2025-07-20 01:57:41 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:320 - 成功生成SQL:
- SELECT sa.service_area_name AS 服务区名称, COUNT(b.id) AS 档口数量 FROM bss_service_area sa JOIN bss_branch b ON sa.id = b.service_area_id WHERE sa.delete_ts IS NULL AND b.delete_ts IS NULL GROUP BY sa.service_area_name ORDER BY 档口数量 DESC LIMIT 1;
-2025-07-20 01:57:41 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:476 - 生成摘要 - 问题: 请问哪个服务区的档口数量最多？
-2025-07-20 01:57:41 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:477 - DataFrame 形状: (1, 2)
-2025-07-20 01:57:41 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:87 - system_content: You are a professional data analysis assistant. The user asked: '请问哪个服务区的档口数量最多？'
-
-Here is the pandas DataFrame data from the query results:|    | 服务区名称   |   档口数量 |
-|---:|:-------------|-----------:|
-|  0 | 南城服务区   |         39 |
-
-Please think and analyze in the context provided and respond accordingly.
-
-2025-07-20 01:57:41 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: Based on the user's question, please briefly summarize this data. Requirements:
-1. Provide only a brief summary without adding extra explanations
-2. If there are numbers in the data, maintain appropriate precision
-Please respond in Chinese. 
-2025-07-20 01:57:41 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:115 - 
-Using model qwen-plus-latest for 136.75 tokens (approx)
-2025-07-20 01:57:41 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:116 - Enable thinking: False, Stream mode: False
-2025-07-20 01:57:41 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:158 - 使用非流式处理模式
-2025-07-20 01:57:42 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:502 - 隐藏thinking内容 - 原始长度: 19, 处理后长度: 19
-2025-07-20 01:57:42 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:504 - 生成的摘要: 南城服务区的档口数量最多，共有39个。...
-2025-07-20 01:58:41 [DEBUG] [vanna.test_vanna] <string>:15 - 测试vanna模块日志 - 时间滚动配置

logs/vanna.log.2025-07-21

@@ -1,549 +0,0 @@
-2025-07-21 08:09:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 08:09:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:09:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 08:09:45 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-21 08:09:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 08:09:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 08:09:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 08:09:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 08:09:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 08:09:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 08:09:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 08:09:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 08:09:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 08:09:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 08:09:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:09:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001E7B0F11400>
-2025-07-21 08:09:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 08:09:46 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 08:09:46 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 08:09:48 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 08:09:48 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 08:09:48 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:09:48 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 08:09:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 08:09:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 08:09:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 08:09:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 08:09:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 08:09:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 08:09:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 08:09:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 08:09:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 08:09:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 08:09:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:09:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001E7B18C2E10>
-2025-07-21 08:09:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 08:09:48 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 08:09:48 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 08:09:50 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 08:21:57 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 08:21:57 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:21:57 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 08:21:57 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-21 08:21:57 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 08:21:57 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 08:21:57 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 08:21:57 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 08:21:57 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 08:21:57 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 08:21:57 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 08:21:57 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 08:21:57 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 08:21:57 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 08:21:57 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:21:57 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001098DCA91F0>
-2025-07-21 08:21:57 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 08:21:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 08:21:57 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 08:21:59 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 08:21:59 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 08:21:59 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:21:59 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 08:21:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 08:21:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 08:21:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 08:21:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 08:21:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 08:21:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 08:21:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 08:21:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 08:21:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 08:21:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 08:21:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:21:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001098FA1A300>
-2025-07-21 08:21:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 08:21:59 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 08:21:59 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 08:22:01 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 08:31:38 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 08:31:38 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:31:38 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 08:31:39 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-21 08:31:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 08:31:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 08:31:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 08:31:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 08:31:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 08:31:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 08:31:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 08:31:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 08:31:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 08:31:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 08:31:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:31:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000002BDDA2F1190>
-2025-07-21 08:31:39 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 08:31:39 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 08:31:39 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 08:31:40 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 08:31:40 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 08:31:40 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:31:40 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 08:31:40 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 08:31:40 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 08:31:40 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 08:31:40 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 08:31:40 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 08:31:40 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 08:31:40 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 08:31:40 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 08:31:40 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 08:31:40 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 08:31:40 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:31:40 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000002BDDC16A420>
-2025-07-21 08:31:40 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 08:31:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 08:31:40 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 08:31:42 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 08:35:04 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 08:35:04 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:35:04 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 08:35:04 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-21 08:35:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 08:35:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 08:35:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 08:35:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 08:35:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 08:35:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 08:35:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 08:35:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 08:35:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 08:35:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 08:35:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:35:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000025CCDAE7350>
-2025-07-21 08:35:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 08:35:04 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 08:35:04 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 08:35:06 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 08:35:06 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 08:35:06 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:35:06 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 08:35:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 08:35:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 08:35:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 08:35:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 08:35:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 08:35:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 08:35:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 08:35:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 08:35:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 08:35:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 08:35:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 08:35:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000025CCE09D5E0>
-2025-07-21 08:35:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 08:35:06 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 08:35:06 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 08:35:08 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 09:08:07 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 09:08:07 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 09:08:07 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 09:08:07 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-21 09:08:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 09:08:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 09:08:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 09:08:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 09:08:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 09:08:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 09:08:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 09:08:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 09:08:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 09:08:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 09:08:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 09:08:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000018828D4C1D0>
-2025-07-21 09:08:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 09:08:07 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 09:08:07 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 09:08:09 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 09:08:09 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 09:08:09 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 09:08:09 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 09:08:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 09:08:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 09:08:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 09:08:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 09:08:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 09:08:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 09:08:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 09:08:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 09:08:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 09:08:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 09:08:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 09:08:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001882A766390>
-2025-07-21 09:08:09 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 09:08:09 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 09:08:09 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 09:08:11 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 09:49:24 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 09:49:24 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 09:49:24 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 09:49:25 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-21 09:49:25 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 09:49:25 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 09:49:25 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 09:49:25 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 09:49:25 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 09:49:25 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 09:49:25 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 09:49:25 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 09:49:25 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 09:49:25 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 09:49:25 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 09:49:25 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001D064F8C560>
-2025-07-21 09:49:25 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 09:49:25 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 09:49:25 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 09:49:27 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 09:49:27 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 09:49:27 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 09:49:27 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 09:49:27 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 09:49:27 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 09:49:27 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 09:49:27 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 09:49:27 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 09:49:27 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 09:49:27 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 09:49:27 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 09:49:27 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 09:49:27 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 09:49:27 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 09:49:27 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001D0669C63F0>
-2025-07-21 09:49:27 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 09:49:27 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 09:49:27 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 09:49:28 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 11:28:44 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 11:28:44 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 11:28:44 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 11:28:45 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-21 11:28:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 11:28:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 11:28:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 11:28:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 11:28:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 11:28:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 11:28:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 11:28:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 11:28:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 11:28:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 11:28:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 11:28:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001C774721010>
-2025-07-21 11:28:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 11:28:45 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 11:28:45 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 11:28:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 11:28:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 11:28:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 11:28:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 11:28:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 11:28:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 11:28:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 11:28:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 11:28:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 11:28:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 11:28:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 11:28:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 11:28:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 11:28:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 11:28:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 11:28:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001C7764B1790>
-2025-07-21 11:28:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 11:28:47 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 11:28:47 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 11:28:49 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 11:53:52 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 11:53:52 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 11:53:52 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 11:53:52 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-21 11:53:52 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 11:53:52 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 11:53:52 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 11:53:52 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 11:53:52 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 11:53:52 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 11:53:52 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 11:53:52 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 11:53:52 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 11:53:52 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 11:53:52 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 11:53:52 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001B19C4A9490>
-2025-07-21 11:53:52 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 11:53:52 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 11:53:52 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 11:53:54 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 11:53:54 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 11:53:54 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 11:53:54 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 11:53:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 11:53:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 11:53:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 11:53:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 11:53:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 11:53:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 11:53:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 11:53:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 11:53:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 11:53:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 11:53:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 11:53:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001B19DEE20C0>
-2025-07-21 11:53:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 11:53:54 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 11:53:54 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 11:53:56 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 12:02:06 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 12:02:06 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 12:02:06 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 12:02:06 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-21 12:02:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 12:02:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 12:02:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 12:02:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 12:02:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 12:02:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 12:02:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 12:02:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 12:02:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 12:02:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 12:02:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 12:02:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x00000178136ABD40>
-2025-07-21 12:02:06 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 12:02:06 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 12:02:06 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 12:02:08 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 12:02:08 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 12:02:08 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 12:02:08 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 12:02:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 12:02:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 12:02:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 12:02:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 12:02:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 12:02:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 12:02:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 12:02:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 12:02:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 12:02:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 12:02:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 12:02:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000017813DCE420>
-2025-07-21 12:02:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 12:02:08 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 12:02:08 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 12:02:10 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 18:36:33 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 18:36:33 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 18:36:33 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 18:37:42 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 18:37:42 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 18:37:42 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 18:37:42 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-21 18:37:42 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 18:37:42 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 18:37:42 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 18:37:42 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 18:37:42 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 18:37:42 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 18:37:42 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 18:37:42 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 18:37:42 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 18:37:42 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 18:37:42 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 18:37:42 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001F06165DC70>
-2025-07-21 18:37:42 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 18:37:42 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 18:37:42 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 18:37:43 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 18:37:43 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 18:37:43 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 18:37:43 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 18:37:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 18:37:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 18:37:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 18:37:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 18:37:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 18:37:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 18:37:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 18:37:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 18:37:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 18:37:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 18:37:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 18:37:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001F063496D20>
-2025-07-21 18:37:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 18:37:44 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 18:37:44 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 18:37:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 19:39:54 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 19:39:54 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 19:39:54 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 19:39:54 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-21 19:39:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 19:39:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 19:39:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 19:39:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 19:39:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 19:39:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 19:39:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 19:39:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 19:39:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 19:39:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 19:39:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 19:39:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000002563CC68F50>
-2025-07-21 19:39:54 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 19:39:54 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 19:39:54 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 19:39:56 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 19:39:56 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 19:39:56 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 19:39:56 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 19:39:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 19:39:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 19:39:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 19:39:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 19:39:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 19:39:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 19:39:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 19:39:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 19:39:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 19:39:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 19:39:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 19:39:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000002563EAEAD80>
-2025-07-21 19:39:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 19:39:56 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 19:39:56 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 19:39:57 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 20:09:09 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 20:09:09 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 20:09:09 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 20:09:10 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-21 20:09:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 20:09:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 20:09:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 20:09:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 20:09:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 20:09:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 20:09:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 20:09:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 20:09:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 20:09:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 20:09:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 20:09:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001EFD75B1BB0>
-2025-07-21 20:09:10 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 20:09:10 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 20:09:10 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 20:09:11 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 20:09:11 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 20:09:11 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 20:09:11 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 20:09:11 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 20:09:11 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 20:09:11 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 20:09:11 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 20:09:11 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 20:09:11 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 20:09:11 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 20:09:11 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 20:09:11 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 20:09:11 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 20:09:11 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 20:09:11 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001EFD8FF6E70>
-2025-07-21 20:09:11 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 20:09:11 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 20:09:11 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 20:09:13 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 23:16:59 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 23:16:59 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 23:16:59 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 23:16:59 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-21 23:16:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 23:16:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 23:16:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 23:16:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 23:16:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 23:16:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 23:16:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 23:16:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 23:16:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 23:16:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 23:16:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 23:16:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000002B7BC661CD0>
-2025-07-21 23:16:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 23:16:59 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 23:16:59 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 23:17:00 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 23:17:00 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 23:17:00 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 23:17:00 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 23:17:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 23:17:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 23:17:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 23:17:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 23:17:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 23:17:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 23:17:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 23:17:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 23:17:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 23:17:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 23:17:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 23:17:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000002B7BE436FF0>
-2025-07-21 23:17:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 23:17:00 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 23:17:00 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 23:17:02 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 23:58:03 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 23:58:03 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 23:58:03 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 23:58:04 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-21 23:58:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 23:58:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 23:58:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 23:58:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 23:58:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 23:58:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 23:58:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 23:58:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 23:58:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 23:58:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 23:58:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 23:58:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001D22D98E840>
-2025-07-21 23:58:04 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 23:58:04 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 23:58:04 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 23:58:05 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-21 23:58:05 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-21 23:58:05 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 23:58:05 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-21 23:58:05 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-21 23:58:05 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-21 23:58:05 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-21 23:58:05 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-21 23:58:05 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-21 23:58:05 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-21 23:58:05 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-21 23:58:05 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-21 23:58:05 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-21 23:58:05 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-21 23:58:05 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-21 23:58:05 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001D22DFAED20>
-2025-07-21 23:58:05 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-21 23:58:05 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-21 23:58:05 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-21 23:58:06 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db

logs/vanna.log.2025-07-22

@@ -1,1486 +0,0 @@
-2025-07-22 01:03:06 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 01:03:06 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 01:03:06 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 01:03:07 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000022E4EDBB830>
-2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 01:03:07 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 01:03:07 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 01:03:08 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 01:03:08 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 01:03:08 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 01:03:08 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000022E4F300350>
-2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 01:03:08 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 01:03:08 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 01:03:09 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 11:33:44 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 11:33:44 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 11:33:44 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 11:33:44 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001F8D8D51D90>
-2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 11:33:44 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 11:33:44 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 11:33:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 11:33:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 11:33:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 11:33:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001F8D97D3230>
-2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 11:33:46 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 11:33:46 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 11:33:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 11:53:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 11:53:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 11:53:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 11:53:46 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000024333E01DC0>
-2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 11:53:46 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 11:53:46 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 11:53:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 11:53:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 11:53:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 11:53:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000024335C330B0>
-2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 11:53:47 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 11:53:47 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 11:53:49 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 11:56:58 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 11:56:58 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 11:56:58 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 11:56:59 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x00000281E9462A20>
-2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 11:56:59 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 11:56:59 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 11:57:00 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 11:57:00 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 11:57:00 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 11:57:00 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x00000281E9B23080>
-2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 11:57:01 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 11:57:01 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 11:57:02 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 12:08:43 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 12:08:43 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 12:08:43 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 12:08:43 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000002198FF31D60>
-2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 12:08:43 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 12:08:43 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 12:08:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 12:08:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 12:08:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 12:08:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000021991D13170>
-2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 12:08:45 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 12:08:45 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 12:08:47 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 12:26:17 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 12:26:17 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 12:26:17 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 12:26:17 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000025BB4681D60>
-2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 12:26:17 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 12:26:17 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 12:26:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 12:26:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 12:26:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 12:26:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000025BB5F38050>
-2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 12:26:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 12:26:19 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 12:26:20 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 13:24:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 13:24:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 13:24:45 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 13:24:45 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001C7F90D1D30>
-2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 13:24:45 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 13:24:45 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 13:24:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 13:24:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 13:24:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 13:24:46 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001C7FAAF3080>
-2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 13:24:46 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 13:24:46 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 13:24:48 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 13:32:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 13:32:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 13:32:18 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 13:32:18 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001438F619A00>
-2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 13:32:18 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 13:32:18 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 13:32:19 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 13:32:19 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 13:32:19 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 13:32:19 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x000001438FDA3080>
-2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 13:32:20 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 13:32:20 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 13:32:21 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 17:38:36 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 17:38:36 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 17:38:36 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 17:38:36 [DEBUG] [vanna.PromptLoader] load_prompts.py:37 - 成功加载提示词配置: C:\Projects\cursor_projects\Vanna-Chainlit-Chromadb\customllm\llm_prompts.yaml
-2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000023E05F45FA0>
-2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 17:38:36 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 17:38:36 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 17:38:37 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 17:38:37 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 17:38:37 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 17:38:37 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000023E07CF30B0>
-2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 17:38:38 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 17:38:38 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 17:38:39 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 20:45:56 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:55 - 创建QIANWEN+PGVECTOR实例
-2025-07-22 20:45:56 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:74 - 已配置使用PgVector，连接字符串: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 20:45:56 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:79 - 已配置使用API嵌入模型: text-embedding-v4
-2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:29 - 传入的 config 参数如下：
-2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   api_key: sk-db68e37f00974031935395315bfe07f0
-2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
-2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   model: qwen-plus-latest
-2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   allow_llm_to_see_data: True
-2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   temperature: 0.6
-2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   n_results: 6
-2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   language: Chinese
-2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   stream: False
-2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   enable_thinking: False
-2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   connection_string: postgresql://postgres:postgres@192.168.67.1:5432/highway_pgvector_db
-2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:31 -   embedding_function: <core.embedding_function.EmbeddingFunction object at 0x0000023E09531AF0>
-2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:37 - temperature is changed to: 0.6
-2025-07-22 20:45:56 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:48 - 错误SQL提示配置: ENABLE_ERROR_SQL_PROMPT = True
-2025-07-22 20:45:56 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:11 - QianWenChat init
-2025-07-22 20:45:57 [INFO] [vanna.VannaFactory] vanna_llm_factory.py:86 - 已连接到业务数据库: 192.168.67.1:6432/highway_db
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:270 - 尝试为问题生成SQL: 请问系统中哪个服务区档口最多？
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 最近一周哪个服务区总车流量最高？取前5名。 | similarity: 0.6381
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 统计每个路线名称下服务区的数量，并按服务区数量降序排列。 | similarity: 0.6209
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 找出2023年4月平均每日订单数最高的服务区TOP3？ | similarity: 0.6178
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 昨日车流量最低的服务区是哪一个？ | similarity: 0.6156
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 查询2023年4月订单数环比增长最快的服务区（相比3月）？ | similarity: 0.6115
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 查询2023年4月1日各服务区总收入排名前5的明细（包含订单总数）？ | similarity: 0.6092
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - SQL 阈值过滤: 总数=6, 阈值=0.65, 最少保留=3
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:348 - SQL 过滤结果: 保留 3 条, 过滤掉 3 条 (满足阈值: 0, 强制保留: 3)
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 1: similarity=0.6381 ✗
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 2: similarity=0.6209 ✗
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 3: similarity=0.6178 ✗
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区每日经营数据统计表
--- 描述: 高速公路服务区每日经营数据统计表，记... | similarity: 0.5484
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路路线与服务区关联表
--- 描述: 高速公路路线与服务区关联表，用于管理各路段... | similarity: 0.5339
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 服务区信息映射表
--- 描述: 服务区信息映射表，用于管理高速公路上各服务区的编码与... | similarity: 0.5318
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区基础信息表
--- 描述: 高速公路服务区基础信息表，存储服务区名称、编... | similarity: 0.5285
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路段路线信息表
--- 描述: 路段路线信息表，记录服务区所属路段及路线名称，支撑高速... | similarity: 0.5115
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区每日车辆流量统计表
--- 描述: 高速公路服务区每日车辆流量统计表，记... | similarity: 0.4766
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DDL 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DDL 过滤结果: 保留 5 条, 过滤掉 1 条 (全部满足阈值)
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 1: similarity=0.5484 ✓
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 2: similarity=0.5339 ✓
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 3: similarity=0.5318 ✓
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 4: similarity=0.5285 ✓
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 5: similarity=0.5115 ✓
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area_mapper（服务区信息映射表）
-bss_service_a... | similarity: 0.5681
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route_area_link（高速公路路线与服务区关联表）
-bss_... | similarity: 0.5468
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_business_day_data（高速公路服务区每日经营数据统计表）
-bss_bus... | similarity: 0.5467
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（高速公路服务区基础信息表）
-bss_service_area... | similarity: 0.5392
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route（路段路线信息表）
-bss_section_route 表路... | similarity: 0.5061
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_car_day_count（高速公路服务区每日车辆流量统计表）
-bss_car_day... | similarity: 0.5058
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DOC 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DOC 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 1: similarity=0.5681 ✓
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 2: similarity=0.5468 ✓
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 3: similarity=0.5467 ✓
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 4: similarity=0.5392 ✓
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 5: similarity=0.5061 ✓
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 6: similarity=0.5058 ✓
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:104 - 开始生成SQL提示词，问题: 请问系统中哪个服务区档口最多？
-2025-07-22 20:45:57 [WARNING] [vanna.BaseLLMChat] pgvector.py:666 - 向量查询未找到任何相关的错误SQL示例，问题: 请问系统中哪个服务区档口最多？
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:159 - 未找到相关的错误SQL示例
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:87 - system_content: You are a PostgreSQL expert. 
-Please help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the response guidelines and format instructions.
-
-===Tables 
--- 中文名: 高速公路服务区每日经营数据统计表
--- 描述: 高速公路服务区每日经营数据统计表，记录各服务区按日维度的业务指标及操作信息。
-create table public.bss_business_day_data (
-  id varchar(32) not null     -- 主键ID，主键,
-  version integer not null    -- 数据版本号,
-  create_ts timestamp         -- 创建时间,
-  created_by varchar(50)      -- 创建人,
-  update_ts timestamp         -- 更新时间,
-  updated_by varchar(50)      -- 更新人,
-  delete_ts timestamp         -- 删除时间,
-  deleted_by varchar(50)      -- 删除人,
-  oper_date date              -- 统计日期,
-  service_no varchar(255)     -- 服务区编码,
-  service_name varchar(255)   -- 服务区名称,
-  branch_no varchar(255)      -- 档口编码,
-  branch_name varchar(255)    -- 档口名称,
-  wx numeric(19,4)            -- 微信支付金额,
-  wx_order integer            -- 微信订单数量,
-  zfb numeric(19,4)           -- 支付宝支付金额,
-  zf_order integer            -- 支付宝订单数量,
-  rmb numeric(19,4)           -- 现金支付金额,
-  rmb_order integer           -- 现金订单数量,
-  xs numeric(19,4)            -- 行吧支付金额,
-  xs_order integer            -- 行吧支付订单数,
-  jd numeric(19,4)            -- 金豆支付金额,
-  jd_order integer            -- 金豆支付订单数,
-  order_sum integer           -- 订单总数,
-  pay_sum numeric(19,4)       -- 总支付金额,
-  source_type integer         -- 数据来源类型,
-  primary key (id)
-)
-
--- 中文名: 高速公路路线与服务区关联表
--- 描述: 高速公路路线与服务区关联表，用于管理各路段所属的服务区信息。
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线唯一标识，主键,
-  service_area_id varchar(32) not null -- 服务区唯一标识，主键,
-  primary key (section_route_id, service_area_id)
-)
-
--- 中文名: 服务区信息映射表
--- 描述: 服务区信息映射表，用于管理高速公路上各服务区的编码与名称对应关系。
-create table public.bss_service_area_mapper (
-  id varchar(32) not null     -- 唯一标识符，主键,
-  version integer not null    -- 数据版本号,
-  create_ts timestamp         -- 创建时间,
-  created_by varchar(50)      -- 创建人,
-  update_ts timestamp         -- 更新时间,
-  updated_by varchar(50)      -- 更新人,
-  delete_ts timestamp         -- 删除时间,
-  deleted_by varchar(50)      -- 删除人,
-  service_name varchar(255)   -- 服务区名称,
-  service_no varchar(255)     -- 服务区编码,
-  service_area_id varchar(32) -- 服务区业务ID,
-  source_system_type varchar(50) -- 数据来源系统,
-  source_type integer         -- 来源系统类型ID,
-  primary key (id)
-)
-
--- 中文名: 高速公路服务区基础信息表
--- 描述: 高速公路服务区基础信息表，存储服务区名称、编码及全生命周期管理数据。
-create table public.bss_service_area (
-  id varchar(32) not null     -- 唯一标识符，主键,
-  version integer not null    -- 数据版本号,
-  create_ts timestamp         -- 创建时间,
-  created_by varchar(50)      -- 创建人,
-  update_ts timestamp         -- 更新时间,
-  updated_by varchar(50)      -- 更新人,
-  delete_ts timestamp         -- 删除时间,
-  deleted_by varchar(50)      -- 删除人,
-  service_area_name varchar(255) -- 服务区名称,
-  service_area_no varchar(255) -- 服务区编码,
-  company_id varchar(32)      -- 所属公司ID,
-  service_position varchar(255) -- 经纬度坐标,
-  service_area_type varchar(50) -- 服务区类型,
-  service_state varchar(50)   -- 运营状态,
-  primary key (id)
-)
-
--- 中文名: 路段路线信息表
--- 描述: 路段路线信息表，记录服务区所属路段及路线名称，支撑高速路网运营管理。
-create table public.bss_section_route (
-  id varchar(32) not null     -- 主键ID，主键,
-  version integer not null    -- 数据版本号,
-  create_ts timestamp         -- 创建时间,
-  created_by varchar(50)      -- 创建人,
-  update_ts timestamp         -- 更新时间,
-  updated_by varchar(50)      -- 更新人,
-  delete_ts timestamp         -- 删除时间,
-  deleted_by varchar(50)      -- 删除人,
-  section_name varchar(255)   -- 路段名称,
-  route_name varchar(255)     -- 路线名称,
-  code varchar(255)           -- 路段编号,
-  primary key (id)
-)
-
-
-===Additional Context 
-
-## bss_service_area_mapper（服务区信息映射表）
-bss_service_area_mapper 表服务区信息映射表，用于管理高速公路上各服务区的编码与名称对应关系。
-字段列表：
-- id (varchar(32)) - 唯一标识符 [主键, 非空] [示例: 00e1e893909211ed8ee6fa163eaf653f, 013867f5962211ed8ee6fa163eaf653f]
-- version (integer) - 数据版本号 [非空] [示例: 1]
-- create_ts (timestamp) - 创建时间 [示例: 2023-01-10 10:54:03, 2023-01-17 12:47:29]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2023-01-10 10:54:07, 2023-01-17 12:47:32]
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- service_name (varchar(255)) - 服务区名称 [示例: 信丰西服务区, 南康北服务区]
-- service_no (varchar(255)) - 服务区编码 [示例: 1067, 1062]
-- service_area_id (varchar(32)) - 服务区业务ID [示例: 97cd6cd516a551409a4d453a58f9e170, fdbdd042962011ed8ee6fa163eaf653f]
-- source_system_type (varchar(50)) - 数据来源系统 [示例: 驿美, 驿购]
-- source_type (integer) - 来源系统类型ID [示例: 3, 1]
-字段补充说明：
-- id 为主键
-- source_system_type 为枚举字段，包含取值：司乘管理、商业管理、驿购、驿美、手工录入
-- source_type 为枚举字段，包含取值：5、0、1、3、4
-
-## bss_section_route_area_link（高速公路路线与服务区关联表）
-bss_section_route_area_link 表高速公路路线与服务区关联表，用于管理各路段所属的服务区信息。
-字段列表：
-- section_route_id (varchar(32)) - 路段路线唯一标识 [主键, 非空] [示例: v8elrsfs5f7lt7jl8a6p87smfzesn3rz, hxzi2iim238e3s1eajjt1enmh9o4h3wp]
-- service_area_id (varchar(32)) - 服务区唯一标识 [主键, 非空] [示例: 08e01d7402abd1d6a4d9fdd5df855ef8, 091662311d2c737029445442ff198c4c]
-字段补充说明：
-- 复合主键：section_route_id, service_area_id
-
-## bss_business_day_data（高速公路服务区每日经营数据统计表）
-bss_business_day_data 表高速公路服务区每日经营数据统计表，记录各服务区按日维度的业务指标及操作信息。
-字段列表：
-- id (varchar(32)) - 主键ID [主键, 非空] [示例: 00827DFF993D415488EA1F07CAE6C440, 00e799048b8cbb8ee758eac9c8b4b820]
-- version (integer) - 数据版本号 [非空] [示例: 1]
-- create_ts (timestamp) - 创建时间 [示例: 2023-04-02 08:31:51, 2023-04-02 02:30:08]
-- created_by (varchar(50)) - 创建人 [示例: xingba]
-- update_ts (timestamp) - 更新时间 [示例: 2023-04-02 08:31:51, 2023-04-02 02:30:08]
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- oper_date (date) - 统计日期 [示例: 2023-04-01]
-- service_no (varchar(255)) - 服务区编码 [示例: 1028, H0501]
-- service_name (varchar(255)) - 服务区名称 [示例: 宜春服务区, 庐山服务区]
-- branch_no (varchar(255)) - 档口编码 [示例: 1, H05016]
-- branch_name (varchar(255)) - 档口名称 [示例: 宜春南区, 庐山鲜徕客东区]
-- wx (numeric(19,4)) - 微信支付金额 [示例: 4790.0000, 2523.0000]
-- wx_order (integer) - 微信订单数量 [示例: 253, 133]
-- zfb (numeric(19,4)) - 支付宝支付金额 [示例: 229.0000, 0.0000]
-- zf_order (integer) - 支付宝订单数量 [示例: 15, 0]
-- rmb (numeric(19,4)) - 现金支付金额 [示例: 1058.5000, 124.0000]
-- rmb_order (integer) - 现金订单数量 [示例: 56, 12]
-- xs (numeric(19,4)) - 行吧支付金额 [示例: 0.0000, 40.0000]
-- xs_order (integer) - 行吧支付订单数 [示例: 0, 1]
-- jd (numeric(19,4)) - 金豆支付金额 [示例: 0.0000]
-- jd_order (integer) - 金豆支付订单数 [示例: 0]
-- order_sum (integer) - 订单总数 [示例: 324, 146]
-- pay_sum (numeric(19,4)) - 总支付金额 [示例: 6077.5000, 2687.0000]
-- source_type (integer) - 数据来源类型 [示例: 1, 0, 4]
-字段补充说明：
-- id 为主键
-- source_type 为枚举字段，包含取值：0、4、1、2、3
-
-## bss_service_area（高速公路服务区基础信息表）
-bss_service_area 表高速公路服务区基础信息表，存储服务区名称、编码及全生命周期管理数据。
-字段列表：
-- id (varchar(32)) - 唯一标识符 [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
-- version (integer) - 数据版本号 [非空] [示例: 3, 6]
-- create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人 [示例: ]
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
-- service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
-- company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
-- service_position (varchar(255)) - 经纬度坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
-- service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
-- service_state (varchar(50)) - 运营状态 [示例: 开放, 关闭]
-字段补充说明：
-- id 为主键
-- service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
-- service_state 为枚举字段，包含取值：开放、关闭、上传数据
-
-## bss_section_route（路段路线信息表）
-bss_section_route 表路段路线信息表，记录服务区所属路段及路线名称，支撑高速路网运营管理。
-字段列表：
-- id (varchar(32)) - 主键ID [主键, 非空] [示例: 04ri3j67a806uw2c6o6dwdtz4knexczh, 0g5mnefxxtukql2cq6acul7phgskowy7]
-- version (integer) - 数据版本号 [非空] [示例: 1, 0]
-- create_ts (timestamp) - 创建时间 [示例: 2021-10-29 19:43:50, 2022-03-04 16:07:16]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- section_name (varchar(255)) - 路段名称 [示例: 昌栗, 昌宁]
-- route_name (varchar(255)) - 路线名称 [示例: 昌栗, 昌韶]
-- code (varchar(255)) - 路段编号 [示例: SR0001, SR0002]
-字段补充说明：
-- id 为主键
-- created_by 为枚举字段，包含取值：admin
-
-## bss_car_day_count（高速公路服务区每日车辆流量统计表）
-bss_car_day_count 表高速公路服务区每日车辆流量统计表，记录各类型车辆数量及变更历史。
-字段列表：
-- id (varchar(32)) - 主键ID [主键, 非空] [示例: 00022c1c99ff11ec86d4fa163ec0f8fc, 00022caa99ff11ec86d4fa163ec0f8fc]
-- version (integer) - 数据版本号 [非空] [示例: 1]
-- create_ts (timestamp) - 创建时间 [示例: 2022-03-02 16:01:43, 2022-02-02 14:18:55]
-- created_by (varchar(50)) - 创建人
-- update_ts (timestamp) - 更新时间 [示例: 2022-03-02 16:01:43, 2022-02-02 14:18:55]
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- customer_count (bigint) - 车辆数量 [示例: 1114, 295]
-- car_type (varchar(100)) - 车辆类别 [示例: 其他]
-- count_date (date) - 统计日期 [示例: 2022-03-02, 2022-02-02]
-- service_area_id (varchar(32)) - 服务区ID [示例: 17461166e7fa3ecda03534a5795ce985, 81f4eb731fb0728aef17ae61f1f1daef]
-字段补充说明：
-- id 为主键
-- car_type 为枚举字段，包含取值：其他、危化品、城际、过境
-
-===Response Guidelines 
-**IMPORTANT**: All SQL queries MUST use Chinese aliases for ALL columns in SELECT clause.
-
-1. If the provided context is sufficient, please generate a valid SQL query without any explanations for the question. 
-2. If the provided context is almost sufficient but requires knowledge of a specific string in a particular column, please generate an intermediate SQL query to find the distinct strings in that column. Prepend the query with a comment saying intermediate_sql 
-3. If the provided context is insufficient, please explain why it can't be generated. 
-4. **Context Understanding**: If the question follows [CONTEXT]...[CURRENT] format, replace pronouns in [CURRENT] with specific entities from [CONTEXT].
-   - Example: If context mentions 'Nancheng Service Area has the most stalls', and current question is 'How many dining stalls does this service area have?', 
-     interpret it as 'How many dining stalls does Nancheng Service Area have?'
-5. Please use the most relevant table(s). 
-6. If the question has been asked and answered before, please repeat the answer exactly as it was given before. 
-7. Ensure that the output SQL is PostgreSQL-compliant and executable, and free of syntax errors. 
-8. Always add NULLS LAST to ORDER BY clauses to handle NULL values properly (e.g., ORDER BY total DESC NULLS LAST).
-9. **MANDATORY**: ALL columns in SELECT must have Chinese aliases. This is non-negotiable:
-   - Every column MUST use AS with a Chinese alias
-   - Raw column names without aliases are NOT acceptable
-   - Examples: 
-     * CORRECT: SELECT service_name AS 服务区名称, SUM(pay_sum) AS 总收入
-     * WRONG: SELECT service_name, SUM(pay_sum) AS total_revenue
-     * WRONG: SELECT service_name AS service_area, SUM(pay_sum) AS 总收入
-   - Common aliases: COUNT(*) AS 数量, SUM(...) AS 总计, AVG(...) AS 平均值, MAX(...) AS 最大值, MIN(...) AS 最小值
-
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 最近一周哪个服务区总车流量最高？取前5名。
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT s.service_area_name AS 服务区名称, SUM(c.customer_count) AS 总车流量 FROM bss_car_day_count c JOIN bss_service_area s ON c.service_area_id = s.id WHERE c.count_date >= CURRENT_DATE - 7 AND c.delete_ts IS NULL AND s.delete_ts IS NULL GROUP BY s.service_area_name ORDER BY 总车流量 DESC LIMIT 5;
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 统计每个路线名称下服务区的数量，并按服务区数量降序排列。
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT sr.route_name AS 路线名称, COUNT(DISTINCT link.service_area_id) AS 服务区数量 FROM bss_section_route sr JOIN bss_section_route_area_link link ON sr.id = link.section_route_id WHERE sr.delete_ts IS NULL GROUP BY sr.route_name ORDER BY 服务区数量 DESC;
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 找出2023年4月平均每日订单数最高的服务区TOP3？
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT service_name AS 服务区名称, AVG(order_sum) AS 日均订单数 FROM bss_business_day_data WHERE oper_date BETWEEN '2023-04-01' AND '2023-04-30' AND delete_ts IS NULL GROUP BY service_name ORDER BY 日均订单数 DESC LIMIT 3;
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 请问系统中哪个服务区档口最多？
-2025-07-22 20:45:57 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:70 - [Vanna] SQL Prompt: [{'role': 'system', 'content': "You are a PostgreSQL expert. \nPlease help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the respon...
-2025-07-22 20:45:57 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:115 - 
-Using model qwen-plus-latest for 2957.0 tokens (approx)
-2025-07-22 20:45:57 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:116 - Enable thinking: False, Stream mode: False
-2025-07-22 20:45:57 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:158 - 使用非流式处理模式
-2025-07-22 20:46:00 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:77 - [Vanna] LLM Response: SELECT service_name AS 服务区名称, COUNT(DISTINCT branch_no) AS 档口数量 FROM bss_business_day_data WHERE delete_ts IS NULL GROUP BY service_name ORDER BY 档口数量 DESC LIMIT 1;
-2025-07-22 20:46:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:80 - [Vanna] Extracted SQL: SELECT service_name AS 服务区名称, COUNT(DISTINCT branch_no) AS 档口数量 FROM bss_business_day_data WHERE delete_ts IS NULL GROUP BY service_name ORDER BY 档口数量 DESC LIMIT 1;
-2025-07-22 20:46:00 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:320 - 成功生成SQL:
- SELECT service_name AS 服务区名称, COUNT(DISTINCT branch_no) AS 档口数量 FROM bss_business_day_data WHERE delete_ts IS NULL GROUP BY service_name ORDER BY 档口数量 DESC LIMIT 1;
-2025-07-22 20:54:14 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:270 - 尝试为问题生成SQL: Previous conversation context:
-human: 请问系统中哪个服务区档口最多？
-ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
-
-Current user question:
-human: 请问这个服务区有几个餐饮档口？
-
-Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
-2025-07-22 20:54:16 [DEBUG] [vanna.EmbeddingFunction] embedding_function.py:169 - 成功生成embedding向量，维度: 1024
-2025-07-22 20:54:19 [DEBUG] [vanna.EmbeddingFunction] embedding_function.py:169 - 成功生成embedding向量，维度: 1024
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 统计每个路线名称下服务区的数量，并按服务区数量降序排列。 | similarity: 0.6985
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 分析庐山服务区2023年4月各档口收入占比（仅显示前3名）？ | similarity: 0.6528
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 最近一周哪个服务区总车流量最高？取前5名。 | similarity: 0.6383
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 查询2023年4月1日各服务区总收入排名前5的明细（包含订单总数）？ | similarity: 0.636
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 找出2023年4月平均每日订单数最高的服务区TOP3？ | similarity: 0.6116
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 计算每个服务区的“状态影响指数”=日均营收 × 平均车流量，并按此指数排序TOP 10？ | similarity: 0.6106
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - SQL 阈值过滤: 总数=6, 阈值=0.65, 最少保留=3
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:348 - SQL 过滤结果: 保留 3 条, 过滤掉 3 条 (满足阈值: 2, 强制保留: 1)
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 1: similarity=0.6985 ✓
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 2: similarity=0.6528 ✓
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 3: similarity=0.6383 ✗
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区每日经营数据统计表
--- 描述: 高速公路服务区每日经营数据统计表，记... | similarity: 0.6253
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路路线与服务区关联表
--- 描述: 高速公路路线与服务区关联表，用于管理各路段... | similarity: 0.5987
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区基础信息表
--- 描述: 高速公路服务区基础信息表，存储服务区名称、编... | similarity: 0.5917
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 服务区信息映射表
--- 描述: 服务区信息映射表，用于管理高速公路上各服务区的编码与... | similarity: 0.574
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路段路线信息表
--- 描述: 路段路线信息表，记录服务区所属路段及路线名称，支撑高速... | similarity: 0.5615
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区每日车辆流量统计表
--- 描述: 高速公路服务区每日车辆流量统计表，记... | similarity: 0.5517
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DDL 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DDL 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 1: similarity=0.6253 ✓
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 2: similarity=0.5987 ✓
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 3: similarity=0.5917 ✓
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 4: similarity=0.574 ✓
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 5: similarity=0.5615 ✓
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 6: similarity=0.5517 ✓
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_business_day_data（高速公路服务区每日经营数据统计表）
-bss_bus... | similarity: 0.6161
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area_mapper（服务区信息映射表）
-bss_service_a... | similarity: 0.6125
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（高速公路服务区基础信息表）
-bss_service_area... | similarity: 0.6007
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route_area_link（高速公路路线与服务区关联表）
-bss_... | similarity: 0.5907
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_car_day_count（高速公路服务区每日车辆流量统计表）
-bss_car_day... | similarity: 0.5816
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route（路段路线信息表）
-bss_section_route 表路... | similarity: 0.5589
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DOC 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DOC 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 1: similarity=0.6161 ✓
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 2: similarity=0.6125 ✓
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 3: similarity=0.6007 ✓
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 4: similarity=0.5907 ✓
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 5: similarity=0.5816 ✓
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 6: similarity=0.5589 ✓
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:104 - 开始生成SQL提示词，问题: Previous conversation context:
-human: 请问系统中哪个服务区档口最多？
-ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
-
-Current user question:
-human: 请问这个服务区有几个餐饮档口？
-
-Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
-2025-07-22 20:54:19 [WARNING] [vanna.BaseLLMChat] pgvector.py:666 - 向量查询未找到任何相关的错误SQL示例，问题: Previous conversation context:
-human: 请问系统中哪个服务区档口最多？
-ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
-
-Current user question:
-human: 请问这个服务区有几个餐饮档口？
-
-Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:159 - 未找到相关的错误SQL示例
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:87 - system_content: You are a PostgreSQL expert. 
-Please help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the response guidelines and format instructions.
-
-===Tables 
--- 中文名: 高速公路服务区每日经营数据统计表
--- 描述: 高速公路服务区每日经营数据统计表，记录各服务区按日维度的业务指标及操作信息。
-create table public.bss_business_day_data (
-  id varchar(32) not null     -- 主键ID，主键,
-  version integer not null    -- 数据版本号,
-  create_ts timestamp         -- 创建时间,
-  created_by varchar(50)      -- 创建人,
-  update_ts timestamp         -- 更新时间,
-  updated_by varchar(50)      -- 更新人,
-  delete_ts timestamp         -- 删除时间,
-  deleted_by varchar(50)      -- 删除人,
-  oper_date date              -- 统计日期,
-  service_no varchar(255)     -- 服务区编码,
-  service_name varchar(255)   -- 服务区名称,
-  branch_no varchar(255)      -- 档口编码,
-  branch_name varchar(255)    -- 档口名称,
-  wx numeric(19,4)            -- 微信支付金额,
-  wx_order integer            -- 微信订单数量,
-  zfb numeric(19,4)           -- 支付宝支付金额,
-  zf_order integer            -- 支付宝订单数量,
-  rmb numeric(19,4)           -- 现金支付金额,
-  rmb_order integer           -- 现金订单数量,
-  xs numeric(19,4)            -- 行吧支付金额,
-  xs_order integer            -- 行吧支付订单数,
-  jd numeric(19,4)            -- 金豆支付金额,
-  jd_order integer            -- 金豆支付订单数,
-  order_sum integer           -- 订单总数,
-  pay_sum numeric(19,4)       -- 总支付金额,
-  source_type integer         -- 数据来源类型,
-  primary key (id)
-)
-
--- 中文名: 高速公路路线与服务区关联表
--- 描述: 高速公路路线与服务区关联表，用于管理各路段所属的服务区信息。
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线唯一标识，主键,
-  service_area_id varchar(32) not null -- 服务区唯一标识，主键,
-  primary key (section_route_id, service_area_id)
-)
-
--- 中文名: 高速公路服务区基础信息表
--- 描述: 高速公路服务区基础信息表，存储服务区名称、编码及全生命周期管理数据。
-create table public.bss_service_area (
-  id varchar(32) not null     -- 唯一标识符，主键,
-  version integer not null    -- 数据版本号,
-  create_ts timestamp         -- 创建时间,
-  created_by varchar(50)      -- 创建人,
-  update_ts timestamp         -- 更新时间,
-  updated_by varchar(50)      -- 更新人,
-  delete_ts timestamp         -- 删除时间,
-  deleted_by varchar(50)      -- 删除人,
-  service_area_name varchar(255) -- 服务区名称,
-  service_area_no varchar(255) -- 服务区编码,
-  company_id varchar(32)      -- 所属公司ID,
-  service_position varchar(255) -- 经纬度坐标,
-  service_area_type varchar(50) -- 服务区类型,
-  service_state varchar(50)   -- 运营状态,
-  primary key (id)
-)
-
--- 中文名: 服务区信息映射表
--- 描述: 服务区信息映射表，用于管理高速公路上各服务区的编码与名称对应关系。
-create table public.bss_service_area_mapper (
-  id varchar(32) not null     -- 唯一标识符，主键,
-  version integer not null    -- 数据版本号,
-  create_ts timestamp         -- 创建时间,
-  created_by varchar(50)      -- 创建人,
-  update_ts timestamp         -- 更新时间,
-  updated_by varchar(50)      -- 更新人,
-  delete_ts timestamp         -- 删除时间,
-  deleted_by varchar(50)      -- 删除人,
-  service_name varchar(255)   -- 服务区名称,
-  service_no varchar(255)     -- 服务区编码,
-  service_area_id varchar(32) -- 服务区业务ID,
-  source_system_type varchar(50) -- 数据来源系统,
-  source_type integer         -- 来源系统类型ID,
-  primary key (id)
-)
-
--- 中文名: 路段路线信息表
--- 描述: 路段路线信息表，记录服务区所属路段及路线名称，支撑高速路网运营管理。
-create table public.bss_section_route (
-  id varchar(32) not null     -- 主键ID，主键,
-  version integer not null    -- 数据版本号,
-  create_ts timestamp         -- 创建时间,
-  created_by varchar(50)      -- 创建人,
-  update_ts timestamp         -- 更新时间,
-  updated_by varchar(50)      -- 更新人,
-  delete_ts timestamp         -- 删除时间,
-  deleted_by varchar(50)      -- 删除人,
-  section_name varchar(255)   -- 路段名称,
-  route_name varchar(255)     -- 路线名称,
-  code varchar(255)           -- 路段编号,
-  primary key (id)
-)
-
--- 中文名: 高速公路服务区每日车辆流量统计表
--- 描述: 高速公路服务区每日车辆流量统计表，记录各类型车辆数量及变更历史。
-create table public.bss_car_day_count (
-  id varchar(32) not null     -- 主键ID，主键,
-  version integer not null    -- 数据版本号,
-  create_ts timestamp         -- 创建时间,
-  created_by varchar(50)      -- 创建人,
-  update_ts timestamp         -- 更新时间,
-  updated_by varchar(50)      -- 更新人,
-  delete_ts timestamp         -- 删除时间,
-  deleted_by varchar(50)      -- 删除人,
-  customer_count bigint       -- 车辆数量,
-  car_type varchar(100)       -- 车辆类别,
-  count_date date             -- 统计日期,
-  service_area_id varchar(32) -- 服务区ID,
-  primary key (id)
-)
-
-
-===Additional Context 
-
-## bss_business_day_data（高速公路服务区每日经营数据统计表）
-bss_business_day_data 表高速公路服务区每日经营数据统计表，记录各服务区按日维度的业务指标及操作信息。
-字段列表：
-- id (varchar(32)) - 主键ID [主键, 非空] [示例: 00827DFF993D415488EA1F07CAE6C440, 00e799048b8cbb8ee758eac9c8b4b820]
-- version (integer) - 数据版本号 [非空] [示例: 1]
-- create_ts (timestamp) - 创建时间 [示例: 2023-04-02 08:31:51, 2023-04-02 02:30:08]
-- created_by (varchar(50)) - 创建人 [示例: xingba]
-- update_ts (timestamp) - 更新时间 [示例: 2023-04-02 08:31:51, 2023-04-02 02:30:08]
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- oper_date (date) - 统计日期 [示例: 2023-04-01]
-- service_no (varchar(255)) - 服务区编码 [示例: 1028, H0501]
-- service_name (varchar(255)) - 服务区名称 [示例: 宜春服务区, 庐山服务区]
-- branch_no (varchar(255)) - 档口编码 [示例: 1, H05016]
-- branch_name (varchar(255)) - 档口名称 [示例: 宜春南区, 庐山鲜徕客东区]
-- wx (numeric(19,4)) - 微信支付金额 [示例: 4790.0000, 2523.0000]
-- wx_order (integer) - 微信订单数量 [示例: 253, 133]
-- zfb (numeric(19,4)) - 支付宝支付金额 [示例: 229.0000, 0.0000]
-- zf_order (integer) - 支付宝订单数量 [示例: 15, 0]
-- rmb (numeric(19,4)) - 现金支付金额 [示例: 1058.5000, 124.0000]
-- rmb_order (integer) - 现金订单数量 [示例: 56, 12]
-- xs (numeric(19,4)) - 行吧支付金额 [示例: 0.0000, 40.0000]
-- xs_order (integer) - 行吧支付订单数 [示例: 0, 1]
-- jd (numeric(19,4)) - 金豆支付金额 [示例: 0.0000]
-- jd_order (integer) - 金豆支付订单数 [示例: 0]
-- order_sum (integer) - 订单总数 [示例: 324, 146]
-- pay_sum (numeric(19,4)) - 总支付金额 [示例: 6077.5000, 2687.0000]
-- source_type (integer) - 数据来源类型 [示例: 1, 0, 4]
-字段补充说明：
-- id 为主键
-- source_type 为枚举字段，包含取值：0、4、1、2、3
-
-## bss_service_area_mapper（服务区信息映射表）
-bss_service_area_mapper 表服务区信息映射表，用于管理高速公路上各服务区的编码与名称对应关系。
-字段列表：
-- id (varchar(32)) - 唯一标识符 [主键, 非空] [示例: 00e1e893909211ed8ee6fa163eaf653f, 013867f5962211ed8ee6fa163eaf653f]
-- version (integer) - 数据版本号 [非空] [示例: 1]
-- create_ts (timestamp) - 创建时间 [示例: 2023-01-10 10:54:03, 2023-01-17 12:47:29]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2023-01-10 10:54:07, 2023-01-17 12:47:32]
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- service_name (varchar(255)) - 服务区名称 [示例: 信丰西服务区, 南康北服务区]
-- service_no (varchar(255)) - 服务区编码 [示例: 1067, 1062]
-- service_area_id (varchar(32)) - 服务区业务ID [示例: 97cd6cd516a551409a4d453a58f9e170, fdbdd042962011ed8ee6fa163eaf653f]
-- source_system_type (varchar(50)) - 数据来源系统 [示例: 驿美, 驿购]
-- source_type (integer) - 来源系统类型ID [示例: 3, 1]
-字段补充说明：
-- id 为主键
-- source_system_type 为枚举字段，包含取值：司乘管理、商业管理、驿购、驿美、手工录入
-- source_type 为枚举字段，包含取值：5、0、1、3、4
-
-## bss_service_area（高速公路服务区基础信息表）
-bss_service_area 表高速公路服务区基础信息表，存储服务区名称、编码及全生命周期管理数据。
-字段列表：
-- id (varchar(32)) - 唯一标识符 [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
-- version (integer) - 数据版本号 [非空] [示例: 3, 6]
-- create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人 [示例: ]
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
-- service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
-- company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
-- service_position (varchar(255)) - 经纬度坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
-- service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
-- service_state (varchar(50)) - 运营状态 [示例: 开放, 关闭]
-字段补充说明：
-- id 为主键
-- service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
-- service_state 为枚举字段，包含取值：开放、关闭、上传数据
-
-## bss_section_route_area_link（高速公路路线与服务区关联表）
-bss_section_route_area_link 表高速公路路线与服务区关联表，用于管理各路段所属的服务区信息。
-字段列表：
-- section_route_id (varchar(32)) - 路段路线唯一标识 [主键, 非空] [示例: v8elrsfs5f7lt7jl8a6p87smfzesn3rz, hxzi2iim238e3s1eajjt1enmh9o4h3wp]
-- service_area_id (varchar(32)) - 服务区唯一标识 [主键, 非空] [示例: 08e01d7402abd1d6a4d9fdd5df855ef8, 091662311d2c737029445442ff198c4c]
-字段补充说明：
-- 复合主键：section_route_id, service_area_id
-
-## bss_car_day_count（高速公路服务区每日车辆流量统计表）
-bss_car_day_count 表高速公路服务区每日车辆流量统计表，记录各类型车辆数量及变更历史。
-字段列表：
-- id (varchar(32)) - 主键ID [主键, 非空] [示例: 00022c1c99ff11ec86d4fa163ec0f8fc, 00022caa99ff11ec86d4fa163ec0f8fc]
-- version (integer) - 数据版本号 [非空] [示例: 1]
-- create_ts (timestamp) - 创建时间 [示例: 2022-03-02 16:01:43, 2022-02-02 14:18:55]
-- created_by (varchar(50)) - 创建人
-- update_ts (timestamp) - 更新时间 [示例: 2022-03-02 16:01:43, 2022-02-02 14:18:55]
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- customer_count (bigint) - 车辆数量 [示例: 1114, 295]
-- car_type (varchar(100)) - 车辆类别 [示例: 其他]
-- count_date (date) - 统计日期 [示例: 2022-03-02, 2022-02-02]
-- service_area_id (varchar(32)) - 服务区ID [示例: 17461166e7fa3ecda03534a5795ce985, 81f4eb731fb0728aef17ae61f1f1daef]
-字段补充说明：
-- id 为主键
-- car_type 为枚举字段，包含取值：其他、危化品、城际、过境
-
-## bss_section_route（路段路线信息表）
-bss_section_route 表路段路线信息表，记录服务区所属路段及路线名称，支撑高速路网运营管理。
-字段列表：
-- id (varchar(32)) - 主键ID [主键, 非空] [示例: 04ri3j67a806uw2c6o6dwdtz4knexczh, 0g5mnefxxtukql2cq6acul7phgskowy7]
-- version (integer) - 数据版本号 [非空] [示例: 1, 0]
-- create_ts (timestamp) - 创建时间 [示例: 2021-10-29 19:43:50, 2022-03-04 16:07:16]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- section_name (varchar(255)) - 路段名称 [示例: 昌栗, 昌宁]
-- route_name (varchar(255)) - 路线名称 [示例: 昌栗, 昌韶]
-- code (varchar(255)) - 路段编号 [示例: SR0001, SR0002]
-字段补充说明：
-- id 为主键
-- created_by 为枚举字段，包含取值：admin
-
-===Response Guidelines 
-**IMPORTANT**: All SQL queries MUST use Chinese aliases for ALL columns in SELECT clause.
-
-1. If the provided context is sufficient, please generate a valid SQL query without any explanations for the question. 
-2. If the provided context is almost sufficient but requires knowledge of a specific string in a particular column, please generate an intermediate SQL query to find the distinct strings in that column. Prepend the query with a comment saying intermediate_sql 
-3. If the provided context is insufficient, please explain why it can't be generated. 
-4. **Context Understanding**: If the question follows [CONTEXT]...[CURRENT] format, replace pronouns in [CURRENT] with specific entities from [CONTEXT].
-   - Example: If context mentions 'Nancheng Service Area has the most stalls', and current question is 'How many dining stalls does this service area have?', 
-     interpret it as 'How many dining stalls does Nancheng Service Area have?'
-5. Please use the most relevant table(s). 
-6. If the question has been asked and answered before, please repeat the answer exactly as it was given before. 
-7. Ensure that the output SQL is PostgreSQL-compliant and executable, and free of syntax errors. 
-8. Always add NULLS LAST to ORDER BY clauses to handle NULL values properly (e.g., ORDER BY total DESC NULLS LAST).
-9. **MANDATORY**: ALL columns in SELECT must have Chinese aliases. This is non-negotiable:
-   - Every column MUST use AS with a Chinese alias
-   - Raw column names without aliases are NOT acceptable
-   - Examples: 
-     * CORRECT: SELECT service_name AS 服务区名称, SUM(pay_sum) AS 总收入
-     * WRONG: SELECT service_name, SUM(pay_sum) AS total_revenue
-     * WRONG: SELECT service_name AS service_area, SUM(pay_sum) AS 总收入
-   - Common aliases: COUNT(*) AS 数量, SUM(...) AS 总计, AVG(...) AS 平均值, MAX(...) AS 最大值, MIN(...) AS 最小值
-
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 统计每个路线名称下服务区的数量，并按服务区数量降序排列。
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT sr.route_name AS 路线名称, COUNT(DISTINCT link.service_area_id) AS 服务区数量 FROM bss_section_route sr JOIN bss_section_route_area_link link ON sr.id = link.section_route_id WHERE sr.delete_ts IS NULL GROUP BY sr.route_name ORDER BY 服务区数量 DESC;
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 分析庐山服务区2023年4月各档口收入占比（仅显示前3名）？
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT branch_name AS 档口名称, ROUND(SUM(pay_sum)::numeric, 2) AS 收入总额 FROM bss_business_day_data WHERE service_name = '庐山服务区' AND oper_date BETWEEN '2023-04-01' AND '2023-04-30' AND delete_ts IS NULL GROUP BY branch_name ORDER BY 收入总额 DESC LIMIT 3;
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 最近一周哪个服务区总车流量最高？取前5名。
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT s.service_area_name AS 服务区名称, SUM(c.customer_count) AS 总车流量 FROM bss_car_day_count c JOIN bss_service_area s ON c.service_area_id = s.id WHERE c.count_date >= CURRENT_DATE - 7 AND c.delete_ts IS NULL AND s.delete_ts IS NULL GROUP BY s.service_area_name ORDER BY 总车流量 DESC LIMIT 5;
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: Previous conversation context:
-human: 请问系统中哪个服务区档口最多？
-ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
-
-Current user question:
-human: 请问这个服务区有几个餐饮档口？
-
-Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
-2025-07-22 20:54:19 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:70 - [Vanna] SQL Prompt: [{'role': 'system', 'content': "You are a PostgreSQL expert. \nPlease help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the respon...
-2025-07-22 20:54:19 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:115 - 
-Using model qwen-plus-latest for 3195.75 tokens (approx)
-2025-07-22 20:54:19 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:116 - Enable thinking: False, Stream mode: False
-2025-07-22 20:54:19 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:158 - 使用非流式处理模式
-2025-07-22 20:54:23 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:77 - [Vanna] LLM Response: SELECT 
-    service_name AS 服务区名称,
-    COUNT(*) AS 餐饮档口数量
-FROM 
-    bss_business_day_data
-WHERE 
-    service_name = '南城服务区'
-    AND branch_name LIKE '%餐饮%'
-    AND delete_ts IS NULL
-GROUP BY 
-    serv...
-2025-07-22 20:54:23 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:80 - [Vanna] Extracted SQL: SELECT 
-    service_name AS 服务区名称,
-    COUNT(*) AS 餐饮档口数量
-FROM 
-    bss_business_day_data
-WHERE 
-    service_name = '南城服务区'
-    AND branch_name LIKE '%餐饮%'
-    AND delete_ts IS NULL
-GROUP BY 
-    service_name;
-2025-07-22 20:54:23 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:320 - 成功生成SQL:
- SELECT 
-    service_name AS 服务区名称,
-    COUNT(*) AS 餐饮档口数量
-FROM 
-    bss_business_day_data
-WHERE 
-    service_name = '南城服务区'
-    AND branch_name LIKE '%餐饮%'
-    AND delete_ts IS NULL
-GROUP BY 
-    service_name;
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:270 - 尝试为问题生成SQL: Previous conversation context:
-human: 请问系统中哪个服务区档口最多？
-ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
-
-Current user question:
-human: 请问这个服务区有几个餐饮档口？
-
-Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 统计每个路线名称下服务区的数量，并按服务区数量降序排列。 | similarity: 0.6985
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 分析庐山服务区2023年4月各档口收入占比（仅显示前3名）？ | similarity: 0.6528
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 最近一周哪个服务区总车流量最高？取前5名。 | similarity: 0.6383
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 查询2023年4月1日各服务区总收入排名前5的明细（包含订单总数）？ | similarity: 0.636
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 找出2023年4月平均每日订单数最高的服务区TOP3？ | similarity: 0.6116
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:153 - SQL Match: 计算每个服务区的“状态影响指数”=日均营收 × 平均车流量，并按此指数排序TOP 10？ | similarity: 0.6106
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - SQL 阈值过滤: 总数=6, 阈值=0.65, 最少保留=3
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:348 - SQL 过滤结果: 保留 3 条, 过滤掉 3 条 (满足阈值: 2, 强制保留: 1)
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 1: similarity=0.6985 ✓
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 2: similarity=0.6528 ✓
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - SQL 保留 3: similarity=0.6383 ✗
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区每日经营数据统计表
--- 描述: 高速公路服务区每日经营数据统计表，记... | similarity: 0.6253
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路路线与服务区关联表
--- 描述: 高速公路路线与服务区关联表，用于管理各路段... | similarity: 0.5987
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区基础信息表
--- 描述: 高速公路服务区基础信息表，存储服务区名称、编... | similarity: 0.5917
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 服务区信息映射表
--- 描述: 服务区信息映射表，用于管理高速公路上各服务区的编码与... | similarity: 0.574
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 路段路线信息表
--- 描述: 路段路线信息表，记录服务区所属路段及路线名称，支撑高速... | similarity: 0.5615
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:210 - DDL Match: -- 中文名: 高速公路服务区每日车辆流量统计表
--- 描述: 高速公路服务区每日车辆流量统计表，记... | similarity: 0.5517
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DDL 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DDL 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 1: similarity=0.6253 ✓
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 2: similarity=0.5987 ✓
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 3: similarity=0.5917 ✓
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 4: similarity=0.574 ✓
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 5: similarity=0.5615 ✓
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DDL 保留 6: similarity=0.5517 ✓
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_business_day_data（高速公路服务区每日经营数据统计表）
-bss_bus... | similarity: 0.6161
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area_mapper（服务区信息映射表）
-bss_service_a... | similarity: 0.6125
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_service_area（高速公路服务区基础信息表）
-bss_service_area... | similarity: 0.6007
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route_area_link（高速公路路线与服务区关联表）
-bss_... | similarity: 0.5907
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_car_day_count（高速公路服务区每日车辆流量统计表）
-bss_car_day... | similarity: 0.5816
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:269 - Doc Match: ## bss_section_route（路段路线信息表）
-bss_section_route 表路... | similarity: 0.5589
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:328 - DOC 阈值过滤: 总数=6, 阈值=0.5, 最少保留=3
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:341 - DOC 过滤结果: 保留 6 条, 过滤掉 0 条 (全部满足阈值)
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 1: similarity=0.6161 ✓
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 2: similarity=0.6125 ✓
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 3: similarity=0.6007 ✓
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 4: similarity=0.5907 ✓
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 5: similarity=0.5816 ✓
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] pgvector.py:354 - DOC 保留 6: similarity=0.5589 ✓
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:104 - 开始生成SQL提示词，问题: Previous conversation context:
-human: 请问系统中哪个服务区档口最多？
-ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
-
-Current user question:
-human: 请问这个服务区有几个餐饮档口？
-
-Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
-2025-07-22 20:54:40 [WARNING] [vanna.BaseLLMChat] pgvector.py:666 - 向量查询未找到任何相关的错误SQL示例，问题: Previous conversation context:
-human: 请问系统中哪个服务区档口最多？
-ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
-
-Current user question:
-human: 请问这个服务区有几个餐饮档口？
-
-Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:159 - 未找到相关的错误SQL示例
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:87 - system_content: You are a PostgreSQL expert. 
-Please help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the response guidelines and format instructions.
-
-===Tables 
--- 中文名: 高速公路服务区每日经营数据统计表
--- 描述: 高速公路服务区每日经营数据统计表，记录各服务区按日维度的业务指标及操作信息。
-create table public.bss_business_day_data (
-  id varchar(32) not null     -- 主键ID，主键,
-  version integer not null    -- 数据版本号,
-  create_ts timestamp         -- 创建时间,
-  created_by varchar(50)      -- 创建人,
-  update_ts timestamp         -- 更新时间,
-  updated_by varchar(50)      -- 更新人,
-  delete_ts timestamp         -- 删除时间,
-  deleted_by varchar(50)      -- 删除人,
-  oper_date date              -- 统计日期,
-  service_no varchar(255)     -- 服务区编码,
-  service_name varchar(255)   -- 服务区名称,
-  branch_no varchar(255)      -- 档口编码,
-  branch_name varchar(255)    -- 档口名称,
-  wx numeric(19,4)            -- 微信支付金额,
-  wx_order integer            -- 微信订单数量,
-  zfb numeric(19,4)           -- 支付宝支付金额,
-  zf_order integer            -- 支付宝订单数量,
-  rmb numeric(19,4)           -- 现金支付金额,
-  rmb_order integer           -- 现金订单数量,
-  xs numeric(19,4)            -- 行吧支付金额,
-  xs_order integer            -- 行吧支付订单数,
-  jd numeric(19,4)            -- 金豆支付金额,
-  jd_order integer            -- 金豆支付订单数,
-  order_sum integer           -- 订单总数,
-  pay_sum numeric(19,4)       -- 总支付金额,
-  source_type integer         -- 数据来源类型,
-  primary key (id)
-)
-
--- 中文名: 高速公路路线与服务区关联表
--- 描述: 高速公路路线与服务区关联表，用于管理各路段所属的服务区信息。
-create table public.bss_section_route_area_link (
-  section_route_id varchar(32) not null -- 路段路线唯一标识，主键,
-  service_area_id varchar(32) not null -- 服务区唯一标识，主键,
-  primary key (section_route_id, service_area_id)
-)
-
--- 中文名: 高速公路服务区基础信息表
--- 描述: 高速公路服务区基础信息表，存储服务区名称、编码及全生命周期管理数据。
-create table public.bss_service_area (
-  id varchar(32) not null     -- 唯一标识符，主键,
-  version integer not null    -- 数据版本号,
-  create_ts timestamp         -- 创建时间,
-  created_by varchar(50)      -- 创建人,
-  update_ts timestamp         -- 更新时间,
-  updated_by varchar(50)      -- 更新人,
-  delete_ts timestamp         -- 删除时间,
-  deleted_by varchar(50)      -- 删除人,
-  service_area_name varchar(255) -- 服务区名称,
-  service_area_no varchar(255) -- 服务区编码,
-  company_id varchar(32)      -- 所属公司ID,
-  service_position varchar(255) -- 经纬度坐标,
-  service_area_type varchar(50) -- 服务区类型,
-  service_state varchar(50)   -- 运营状态,
-  primary key (id)
-)
-
--- 中文名: 服务区信息映射表
--- 描述: 服务区信息映射表，用于管理高速公路上各服务区的编码与名称对应关系。
-create table public.bss_service_area_mapper (
-  id varchar(32) not null     -- 唯一标识符，主键,
-  version integer not null    -- 数据版本号,
-  create_ts timestamp         -- 创建时间,
-  created_by varchar(50)      -- 创建人,
-  update_ts timestamp         -- 更新时间,
-  updated_by varchar(50)      -- 更新人,
-  delete_ts timestamp         -- 删除时间,
-  deleted_by varchar(50)      -- 删除人,
-  service_name varchar(255)   -- 服务区名称,
-  service_no varchar(255)     -- 服务区编码,
-  service_area_id varchar(32) -- 服务区业务ID,
-  source_system_type varchar(50) -- 数据来源系统,
-  source_type integer         -- 来源系统类型ID,
-  primary key (id)
-)
-
--- 中文名: 路段路线信息表
--- 描述: 路段路线信息表，记录服务区所属路段及路线名称，支撑高速路网运营管理。
-create table public.bss_section_route (
-  id varchar(32) not null     -- 主键ID，主键,
-  version integer not null    -- 数据版本号,
-  create_ts timestamp         -- 创建时间,
-  created_by varchar(50)      -- 创建人,
-  update_ts timestamp         -- 更新时间,
-  updated_by varchar(50)      -- 更新人,
-  delete_ts timestamp         -- 删除时间,
-  deleted_by varchar(50)      -- 删除人,
-  section_name varchar(255)   -- 路段名称,
-  route_name varchar(255)     -- 路线名称,
-  code varchar(255)           -- 路段编号,
-  primary key (id)
-)
-
--- 中文名: 高速公路服务区每日车辆流量统计表
--- 描述: 高速公路服务区每日车辆流量统计表，记录各类型车辆数量及变更历史。
-create table public.bss_car_day_count (
-  id varchar(32) not null     -- 主键ID，主键,
-  version integer not null    -- 数据版本号,
-  create_ts timestamp         -- 创建时间,
-  created_by varchar(50)      -- 创建人,
-  update_ts timestamp         -- 更新时间,
-  updated_by varchar(50)      -- 更新人,
-  delete_ts timestamp         -- 删除时间,
-  deleted_by varchar(50)      -- 删除人,
-  customer_count bigint       -- 车辆数量,
-  car_type varchar(100)       -- 车辆类别,
-  count_date date             -- 统计日期,
-  service_area_id varchar(32) -- 服务区ID,
-  primary key (id)
-)
-
-
-===Additional Context 
-
-## bss_business_day_data（高速公路服务区每日经营数据统计表）
-bss_business_day_data 表高速公路服务区每日经营数据统计表，记录各服务区按日维度的业务指标及操作信息。
-字段列表：
-- id (varchar(32)) - 主键ID [主键, 非空] [示例: 00827DFF993D415488EA1F07CAE6C440, 00e799048b8cbb8ee758eac9c8b4b820]
-- version (integer) - 数据版本号 [非空] [示例: 1]
-- create_ts (timestamp) - 创建时间 [示例: 2023-04-02 08:31:51, 2023-04-02 02:30:08]
-- created_by (varchar(50)) - 创建人 [示例: xingba]
-- update_ts (timestamp) - 更新时间 [示例: 2023-04-02 08:31:51, 2023-04-02 02:30:08]
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- oper_date (date) - 统计日期 [示例: 2023-04-01]
-- service_no (varchar(255)) - 服务区编码 [示例: 1028, H0501]
-- service_name (varchar(255)) - 服务区名称 [示例: 宜春服务区, 庐山服务区]
-- branch_no (varchar(255)) - 档口编码 [示例: 1, H05016]
-- branch_name (varchar(255)) - 档口名称 [示例: 宜春南区, 庐山鲜徕客东区]
-- wx (numeric(19,4)) - 微信支付金额 [示例: 4790.0000, 2523.0000]
-- wx_order (integer) - 微信订单数量 [示例: 253, 133]
-- zfb (numeric(19,4)) - 支付宝支付金额 [示例: 229.0000, 0.0000]
-- zf_order (integer) - 支付宝订单数量 [示例: 15, 0]
-- rmb (numeric(19,4)) - 现金支付金额 [示例: 1058.5000, 124.0000]
-- rmb_order (integer) - 现金订单数量 [示例: 56, 12]
-- xs (numeric(19,4)) - 行吧支付金额 [示例: 0.0000, 40.0000]
-- xs_order (integer) - 行吧支付订单数 [示例: 0, 1]
-- jd (numeric(19,4)) - 金豆支付金额 [示例: 0.0000]
-- jd_order (integer) - 金豆支付订单数 [示例: 0]
-- order_sum (integer) - 订单总数 [示例: 324, 146]
-- pay_sum (numeric(19,4)) - 总支付金额 [示例: 6077.5000, 2687.0000]
-- source_type (integer) - 数据来源类型 [示例: 1, 0, 4]
-字段补充说明：
-- id 为主键
-- source_type 为枚举字段，包含取值：0、4、1、2、3
-
-## bss_service_area_mapper（服务区信息映射表）
-bss_service_area_mapper 表服务区信息映射表，用于管理高速公路上各服务区的编码与名称对应关系。
-字段列表：
-- id (varchar(32)) - 唯一标识符 [主键, 非空] [示例: 00e1e893909211ed8ee6fa163eaf653f, 013867f5962211ed8ee6fa163eaf653f]
-- version (integer) - 数据版本号 [非空] [示例: 1]
-- create_ts (timestamp) - 创建时间 [示例: 2023-01-10 10:54:03, 2023-01-17 12:47:29]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2023-01-10 10:54:07, 2023-01-17 12:47:32]
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- service_name (varchar(255)) - 服务区名称 [示例: 信丰西服务区, 南康北服务区]
-- service_no (varchar(255)) - 服务区编码 [示例: 1067, 1062]
-- service_area_id (varchar(32)) - 服务区业务ID [示例: 97cd6cd516a551409a4d453a58f9e170, fdbdd042962011ed8ee6fa163eaf653f]
-- source_system_type (varchar(50)) - 数据来源系统 [示例: 驿美, 驿购]
-- source_type (integer) - 来源系统类型ID [示例: 3, 1]
-字段补充说明：
-- id 为主键
-- source_system_type 为枚举字段，包含取值：司乘管理、商业管理、驿购、驿美、手工录入
-- source_type 为枚举字段，包含取值：5、0、1、3、4
-
-## bss_service_area（高速公路服务区基础信息表）
-bss_service_area 表高速公路服务区基础信息表，存储服务区名称、编码及全生命周期管理数据。
-字段列表：
-- id (varchar(32)) - 唯一标识符 [主键, 非空] [示例: 0271d68ef93de9684b7ad8c7aae600b6, 08e01d7402abd1d6a4d9fdd5df855ef8]
-- version (integer) - 数据版本号 [非空] [示例: 3, 6]
-- create_ts (timestamp) - 创建时间 [示例: 2021-05-21 13:26:40.589000, 2021-05-20 19:51:46.314000]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间 [示例: 2021-07-10 15:41:28.795000, 2021-07-11 09:33:08.455000]
-- updated_by (varchar(50)) - 更新人 [示例: admin]
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人 [示例: ]
-- service_area_name (varchar(255)) - 服务区名称 [示例: 白鹭湖停车区, 南昌南服务区]
-- service_area_no (varchar(255)) - 服务区编码 [示例: H0814, H0105]
-- company_id (varchar(32)) - 所属公司ID [示例: b1629f07c8d9ac81494fbc1de61f1ea5, ee9bf1180a2b45003f96e597a4b7f15a]
-- service_position (varchar(255)) - 经纬度坐标 [示例: 114.574721,26.825584, 115.910549,28.396355]
-- service_area_type (varchar(50)) - 服务区类型 [示例: 信息化服务区]
-- service_state (varchar(50)) - 运营状态 [示例: 开放, 关闭]
-字段补充说明：
-- id 为主键
-- service_area_type 为枚举字段，包含取值：信息化服务区、智能化服务区
-- service_state 为枚举字段，包含取值：开放、关闭、上传数据
-
-## bss_section_route_area_link（高速公路路线与服务区关联表）
-bss_section_route_area_link 表高速公路路线与服务区关联表，用于管理各路段所属的服务区信息。
-字段列表：
-- section_route_id (varchar(32)) - 路段路线唯一标识 [主键, 非空] [示例: v8elrsfs5f7lt7jl8a6p87smfzesn3rz, hxzi2iim238e3s1eajjt1enmh9o4h3wp]
-- service_area_id (varchar(32)) - 服务区唯一标识 [主键, 非空] [示例: 08e01d7402abd1d6a4d9fdd5df855ef8, 091662311d2c737029445442ff198c4c]
-字段补充说明：
-- 复合主键：section_route_id, service_area_id
-
-## bss_car_day_count（高速公路服务区每日车辆流量统计表）
-bss_car_day_count 表高速公路服务区每日车辆流量统计表，记录各类型车辆数量及变更历史。
-字段列表：
-- id (varchar(32)) - 主键ID [主键, 非空] [示例: 00022c1c99ff11ec86d4fa163ec0f8fc, 00022caa99ff11ec86d4fa163ec0f8fc]
-- version (integer) - 数据版本号 [非空] [示例: 1]
-- create_ts (timestamp) - 创建时间 [示例: 2022-03-02 16:01:43, 2022-02-02 14:18:55]
-- created_by (varchar(50)) - 创建人
-- update_ts (timestamp) - 更新时间 [示例: 2022-03-02 16:01:43, 2022-02-02 14:18:55]
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- customer_count (bigint) - 车辆数量 [示例: 1114, 295]
-- car_type (varchar(100)) - 车辆类别 [示例: 其他]
-- count_date (date) - 统计日期 [示例: 2022-03-02, 2022-02-02]
-- service_area_id (varchar(32)) - 服务区ID [示例: 17461166e7fa3ecda03534a5795ce985, 81f4eb731fb0728aef17ae61f1f1daef]
-字段补充说明：
-- id 为主键
-- car_type 为枚举字段，包含取值：其他、危化品、城际、过境
-
-## bss_section_route（路段路线信息表）
-bss_section_route 表路段路线信息表，记录服务区所属路段及路线名称，支撑高速路网运营管理。
-字段列表：
-- id (varchar(32)) - 主键ID [主键, 非空] [示例: 04ri3j67a806uw2c6o6dwdtz4knexczh, 0g5mnefxxtukql2cq6acul7phgskowy7]
-- version (integer) - 数据版本号 [非空] [示例: 1, 0]
-- create_ts (timestamp) - 创建时间 [示例: 2021-10-29 19:43:50, 2022-03-04 16:07:16]
-- created_by (varchar(50)) - 创建人 [示例: admin]
-- update_ts (timestamp) - 更新时间
-- updated_by (varchar(50)) - 更新人
-- delete_ts (timestamp) - 删除时间
-- deleted_by (varchar(50)) - 删除人
-- section_name (varchar(255)) - 路段名称 [示例: 昌栗, 昌宁]
-- route_name (varchar(255)) - 路线名称 [示例: 昌栗, 昌韶]
-- code (varchar(255)) - 路段编号 [示例: SR0001, SR0002]
-字段补充说明：
-- id 为主键
-- created_by 为枚举字段，包含取值：admin
-
-===Response Guidelines 
-**IMPORTANT**: All SQL queries MUST use Chinese aliases for ALL columns in SELECT clause.
-
-1. If the provided context is sufficient, please generate a valid SQL query without any explanations for the question. 
-2. If the provided context is almost sufficient but requires knowledge of a specific string in a particular column, please generate an intermediate SQL query to find the distinct strings in that column. Prepend the query with a comment saying intermediate_sql 
-3. If the provided context is insufficient, please explain why it can't be generated. 
-4. **Context Understanding**: If the question follows [CONTEXT]...[CURRENT] format, replace pronouns in [CURRENT] with specific entities from [CONTEXT].
-   - Example: If context mentions 'Nancheng Service Area has the most stalls', and current question is 'How many dining stalls does this service area have?', 
-     interpret it as 'How many dining stalls does Nancheng Service Area have?'
-5. Please use the most relevant table(s). 
-6. If the question has been asked and answered before, please repeat the answer exactly as it was given before. 
-7. Ensure that the output SQL is PostgreSQL-compliant and executable, and free of syntax errors. 
-8. Always add NULLS LAST to ORDER BY clauses to handle NULL values properly (e.g., ORDER BY total DESC NULLS LAST).
-9. **MANDATORY**: ALL columns in SELECT must have Chinese aliases. This is non-negotiable:
-   - Every column MUST use AS with a Chinese alias
-   - Raw column names without aliases are NOT acceptable
-   - Examples: 
-     * CORRECT: SELECT service_name AS 服务区名称, SUM(pay_sum) AS 总收入
-     * WRONG: SELECT service_name, SUM(pay_sum) AS total_revenue
-     * WRONG: SELECT service_name AS service_area, SUM(pay_sum) AS 总收入
-   - Common aliases: COUNT(*) AS 数量, SUM(...) AS 总计, AVG(...) AS 平均值, MAX(...) AS 最大值, MIN(...) AS 最小值
-
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 统计每个路线名称下服务区的数量，并按服务区数量降序排列。
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT sr.route_name AS 路线名称, COUNT(DISTINCT link.service_area_id) AS 服务区数量 FROM bss_section_route sr JOIN bss_section_route_area_link link ON sr.id = link.section_route_id WHERE sr.delete_ts IS NULL GROUP BY sr.route_name ORDER BY 服务区数量 DESC;
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 分析庐山服务区2023年4月各档口收入占比（仅显示前3名）？
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT branch_name AS 档口名称, ROUND(SUM(pay_sum)::numeric, 2) AS 收入总额 FROM bss_business_day_data WHERE service_name = '庐山服务区' AND oper_date BETWEEN '2023-04-01' AND '2023-04-30' AND delete_ts IS NULL GROUP BY branch_name ORDER BY 收入总额 DESC LIMIT 3;
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: 最近一周哪个服务区总车流量最高？取前5名。
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:97 - assistant_content: SELECT s.service_area_name AS 服务区名称, SUM(c.customer_count) AS 总车流量 FROM bss_car_day_count c JOIN bss_service_area s ON c.service_area_id = s.id WHERE c.count_date >= CURRENT_DATE - 7 AND c.delete_ts IS NULL AND s.delete_ts IS NULL GROUP BY s.service_area_name ORDER BY 总车流量 DESC LIMIT 5;
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:92 - 
-user_content: Previous conversation context:
-human: 请问系统中哪个服务区档口最多？
-ai: 根据查询结果，系统中档口数量最多的服务区是**南城服务区**，共有**38个档口**。
-
-Current user question:
-human: 请问这个服务区有几个餐饮档口？
-
-Please analyze the conversation history to understand any references (like "this service area", "that branch", etc.) in the current question, and generate the appropriate SQL query.
-2025-07-22 20:54:40 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:70 - [Vanna] SQL Prompt: [{'role': 'system', 'content': "You are a PostgreSQL expert. \nPlease help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the respon...
-2025-07-22 20:54:40 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:115 - 
-Using model qwen-plus-latest for 3195.75 tokens (approx)
-2025-07-22 20:54:40 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:116 - Enable thinking: False, Stream mode: False
-2025-07-22 20:54:40 [INFO] [vanna.BaseLLMChat] qianwen_chat.py:158 - 使用非流式处理模式
-2025-07-22 20:54:48 [DEBUG] [vanna.BaseLLMChat] base_llm_chat.py:77 - [Vanna] LLM Response: SELECT 
-    service_name AS 服务区名称,
-    COUNT(*) AS 餐饮档口数量
-FROM 
-    bss_business_day_data
-WHERE 
-    service_name = '南城服务区'
-    AND branch_name LIKE '%餐饮%'
-    AND delete_ts IS NULL
-GROUP BY 
-    serv...
-2025-07-22 20:54:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:80 - [Vanna] Extracted SQL: SELECT 
-    service_name AS 服务区名称,
-    COUNT(*) AS 餐饮档口数量
-FROM 
-    bss_business_day_data
-WHERE 
-    service_name = '南城服务区'
-    AND branch_name LIKE '%餐饮%'
-    AND delete_ts IS NULL
-GROUP BY 
-    service_name;
-2025-07-22 20:54:48 [INFO] [vanna.BaseLLMChat] base_llm_chat.py:320 - 成功生成SQL:
- SELECT 
-    service_name AS 服务区名称,
-    COUNT(*) AS 餐饮档口数量
-FROM 
-    bss_business_day_data
-WHERE 
-    service_name = '南城服务区'
-    AND branch_name LIKE '%餐饮%'
-    AND delete_ts IS NULL
-GROUP BY 
-    service_name;