fix: 更新数据库路径和日志配置，确保兼容性和可维护性

server/db_manager.py

@@ -15,7 +15,7 @@ class DBManager:
     """数据库管理器 - 只提供基础的数据库连接和会话管理"""
 
     def __init__(self):
-        self.db_path = os.path.join(config.save_dir, "data", "server.db")
+        self.db_path = os.path.join(config.save_dir, "database", "server.db")
         self.ensure_db_dir()
 
         # 创建SQLAlchemy引擎

server/routers/data_router.py

@@ -132,7 +132,7 @@ async def upload_file(
     if db_id:
         upload_dir = knowledge_base.get_db_upload_path(db_id)
     else:
-        upload_dir = os.path.join(config.save_dir, "data", "uploads")
+        upload_dir = os.path.join(config.save_dir, "database", "uploads")
 
     basename, ext = os.path.splitext(file.filename)
     filename = f"{basename}_{hashstr(basename, 4, with_salt=True)}{ext}".lower()

src/config/__init__.py

@@ -39,7 +39,7 @@ class Config(SimpleConfig):
     def __init__(self):
         super().__init__()
         self._config_items = {}
-        self.save_dir = "saves"
+        self.save_dir = os.getenv('SAVE_DIR', 'saves')
         self.filename = str(Path(f"{self.save_dir}/config/base.yaml"))
         os.makedirs(os.path.dirname(self.filename), exist_ok=True)
 

src/core/lightrag_based_kb.py

@@ -10,13 +10,16 @@ from datetime import datetime
 
 from lightrag import LightRAG, QueryParam
 from lightrag.llm.openai import openai_complete_if_cache, openai_embed
-from lightrag.utils import EmbeddingFunc
+from lightrag.utils import EmbeddingFunc, setup_logger
 from lightrag.kg.shared_storage import initialize_pipeline_status
 
 from src import config
 from src.utils import logger, hashstr, get_docker_safe_url
 from src.plugins import ocr
 
+work_dir = os.path.join(config.save_dir, "lightrag_data")
+log_dir = os.path.join(work_dir, "logs", "lightrag")
+setup_logger("lightrag", log_file_path=os.path.join(log_dir, f"lightrag_{datetime.now().strftime('%Y-%m-%d')}.log"))
 
 class LightRagBasedKB:
     """基于 LightRAG 的知识库管理类"""
@@ -167,43 +170,35 @@ class LightRagBasedKB:
             # 直接读取文本文件
             with open(file_path, 'r', encoding='utf-8') as f:
                 content = f.read()
-            return f"Using f.read() to process {file_path.name}\n\n{content}"
+            return f"# {file_path.name}\n\n{content}"
 
         elif file_ext in ['.doc', '.docx']:
             # 处理 Word 文档
-            try:
+            from docx import Document
-                from docx import Document
+            doc = Document(file_path)
-                doc = Document(file_path)
+            text = '\n'.join([para.text for para in doc.paragraphs])
-                text = '\n'.join([para.text for para in doc.paragraphs])
+            return f"# {file_path.name}\n\n{text}"
-                return f"Using python-docx to process {file_path.name}\n\n{text}"
-            except ImportError:
-                logger.warning("python-docx not installed, cannot process .docx files")
-                return f"# {file_path.name}\n\n[Cannot process .docx file - python-docx not installed]"
 
         elif file_ext in ['.jpg', '.jpeg', '.png', '.bmp']:
             # 使用 OCR 处理图片
             text = ocr.process_image(str(file_path))
-            return f"Using OCR to process {file_path.name}\n\n{text}"
+            return f"# {file_path.name}\n\n{text}"
 
         else:
             # 尝试作为文本文件读取
             import textract
             text = textract.process(file_path)
-            return f"Using textract to process {file_path.name}\n\n{text}"
+            return f"# {file_path.name}\n\n{text}"
 
     async def _process_url_to_markdown(self, url: str, params=None) -> str:
         """将 URL 转换为 markdown 格式"""
-        try:
+        import requests
-            import requests
+        from bs4 import BeautifulSoup
-            from bs4 import BeautifulSoup
 
-            response = requests.get(url, timeout=30)
+        response = requests.get(url, timeout=30)
-            soup = BeautifulSoup(response.content, 'html.parser')
+        soup = BeautifulSoup(response.content, 'html.parser')
-            text_content = soup.get_text()
+        text_content = soup.get_text()
-            return f"# {url}\n\n{text_content}"
+        return f"# {url}\n\n{text_content}"
-        except Exception as e:
-            logger.warning(f"Failed to scrape URL {url}: {e}")
-            return f"# {url}\n\n[Failed to scrape URL: {str(e)}]"
 
     # =============================================================================
     # data_router.py 中使用的核心方法

src/utils/db_migration.py

@@ -1,102 +0,0 @@
-"""
-数据库迁移工具：用于将独立的knowledge.db数据迁移到整合的server.db中
-"""
-
-import os
-import sqlite3
-import shutil
-from datetime import datetime
-from src import config
-from src.utils import logger
-
-def migrate_knowledge_db():
-    """
-    将独立的knowledge.db数据迁移到整合的server.db中
-
-    Returns:
-        bool: 迁移是否成功
-    """
-    # 确定数据库路径
-    knowledge_db_path = os.path.join(config.save_dir, "data", "knowledge.db")
-    server_db_path = os.path.join(config.save_dir, "data", "server.db")
-
-    # 检查源数据库是否存在
-    if not os.path.exists(knowledge_db_path):
-        logger.info("未找到knowledge.db数据库，无需迁移")
-        return False
-
-    # 确保目标数据库目录存在
-    os.makedirs(os.path.dirname(server_db_path), exist_ok=True)
-
-    try:
-        # 备份两个数据库
-        timestamp = datetime.now().strftime("%Y%m%d%H%M%S")
-        if os.path.exists(server_db_path):
-            shutil.copy2(server_db_path, f"{server_db_path}.bak.{timestamp}")
-            logger.info(f"已备份server.db到 {server_db_path}.bak.{timestamp}")
-
-        shutil.copy2(knowledge_db_path, f"{knowledge_db_path}.bak.{timestamp}")
-        logger.info(f"已备份knowledge.db到 {knowledge_db_path}.bak.{timestamp}")
-
-        # 连接到两个数据库
-        knowledge_conn = sqlite3.connect(knowledge_db_path)
-        server_conn = sqlite3.connect(server_db_path)
-
-        knowledge_cursor = knowledge_conn.cursor()
-        server_cursor = server_conn.cursor()
-
-        # 获取knowledge.db中的表
-        knowledge_cursor.execute("SELECT name FROM sqlite_master WHERE type='table';")
-        tables = knowledge_cursor.fetchall()
-
-        # 迁移每个表
-        for table in tables:
-            table_name = table[0]
-            if table_name.startswith('sqlite_'):
-                continue  # 跳过SQLite内部表
-
-            logger.info(f"正在迁移表 {table_name}...")
-
-            # 获取表结构
-            knowledge_cursor.execute(f"PRAGMA table_info({table_name});")
-            columns = knowledge_cursor.fetchall()
-
-            # 在server.db中创建表（如果不存在）
-            column_defs = ", ".join([f'"{col[1]}" {col[2]}' for col in columns])
-            create_table_sql = f'CREATE TABLE IF NOT EXISTS "{table_name}" ({column_defs});'
-            server_cursor.execute(create_table_sql)
-
-            # 获取数据
-            knowledge_cursor.execute(f'SELECT * FROM "{table_name}";')
-            rows = knowledge_cursor.fetchall()
-
-            if rows:
-                # 准备插入语句
-                placeholders = ", ".join(["?" for _ in range(len(columns))])
-                insert_sql = f'INSERT OR REPLACE INTO "{table_name}" VALUES ({placeholders});'
-
-                # 批量插入数据
-                server_cursor.executemany(insert_sql, rows)
-                logger.info(f"已迁移 {len(rows)} 条记录到表 {table_name}")
-
-        # 提交更改
-        server_conn.commit()
-
-        # 关闭连接
-        knowledge_cursor.close()
-        knowledge_conn.close()
-        server_cursor.close()
-        server_conn.close()
-
-        logger.info("数据库迁移完成")
-        logger.warning(f"请手动删除旧的knowledge.db文件: {knowledge_db_path}")
-        return True
-
-    except Exception as e:
-        logger.error(f"数据库迁移失败: {str(e)}")
-        return False
-
-if __name__ == "__main__":
-    # 当作为脚本运行时执行迁移
-    result = migrate_knowledge_db()
-    print(f"迁移{'成功' if result else '失败'}")

src/utils/logging_config.py

@@ -5,12 +5,13 @@ import pytz
 
 from loguru import logger as loguru_logger
 
-DATETIME = datetime.now(pytz.timezone('Asia/Shanghai')).strftime('%Y-%m-%d-%H%M%S')
+SAVE_DIR = os.getenv('SAVE_DIR', 'saves')
-# DATETIME = "debug" # 为了方便，调试的时候输出到 debug.log 文件
+DATETIME = datetime.now(pytz.timezone('Asia/Shanghai')).strftime('%Y-%m-%d')
-LOG_FILE = f'tmp/logs/project-{DATETIME}.log'
+LOG_FILE = f'{SAVE_DIR}/logs/yuxi-{DATETIME}.log'
+
 def setup_logger(name, level="DEBUG", console=True):
     """使用 loguru 设置日志记录器"""
-    os.makedirs("tmp/logs", exist_ok=True)
+    os.makedirs(f"{SAVE_DIR}/logs", exist_ok=True)  # 创建日志目录
 
     # 移除默认的 handler
     loguru_logger.remove()
@@ -31,7 +32,7 @@ def setup_logger(name, level="DEBUG", console=True):
         loguru_logger.add(
             lambda msg: print(msg, end=""),
             level=level,
-            format="<green>{time:YYYY-MM-DD HH:mm:ss}</green> - <level>{level}</level> - <cyan>{name}</cyan> - <level>{message}</level>",
+            format="<green>{time:MM-DD HH:mm:ss}</green> <level>{level}</level> <cyan>{name}</cyan>: <level>{message}</level>",
             colorize=True
         )
 

web/src/views/DataBaseInfoView.vue

@@ -1181,6 +1181,9 @@ const toggleAutoRefresh = (checked) => {
     display: flex;
     flex-direction: column;
     border-radius: 12px;
+    word-break: break-all;
+    word-break: break-word; /* 非标准，但某些浏览器支持 */
+    overflow-wrap: break-word; /* 标准写法 */
     gap: 20px;
 
     .results-overview {