diff --git a/server/db_manager.py b/server/db_manager.py
index 2e4752fd..24308c71 100644
--- a/server/db_manager.py
+++ b/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
diff --git a/server/routers/data_router.py b/server/routers/data_router.py
index 2c397eb9..c36cae06 100644
--- a/server/routers/data_router.py
+++ b/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()
diff --git a/src/config/__init__.py b/src/config/__init__.py
index c9efd1f6..b21f0732 100644
--- a/src/config/__init__.py
+++ b/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)
diff --git a/src/core/lightrag_based_kb.py b/src/core/lightrag_based_kb.py
index ec274351..bf6750da 100644
--- a/src/core/lightrag_based_kb.py
+++ b/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
- doc = Document(file_path)
- text = '\n'.join([para.text for para in doc.paragraphs])
- 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]"
+ from docx import Document
+ doc = Document(file_path)
+ text = '\n'.join([para.text for para in doc.paragraphs])
+ return f"# {file_path.name}\n\n{text}"
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
- from bs4 import BeautifulSoup
+ import requests
+ from bs4 import BeautifulSoup
- response = requests.get(url, timeout=30)
- soup = BeautifulSoup(response.content, 'html.parser')
- text_content = soup.get_text()
- 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)}]"
+ response = requests.get(url, timeout=30)
+ soup = BeautifulSoup(response.content, 'html.parser')
+ text_content = soup.get_text()
+ return f"# {url}\n\n{text_content}"
# =============================================================================
# data_router.py 中使用的核心方法
diff --git a/src/utils/db_migration.py b/src/utils/db_migration.py
deleted file mode 100644
index 40c966ff..00000000
--- a/src/utils/db_migration.py
+++ /dev/null
@@ -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'}")
diff --git a/src/utils/logging_config.py b/src/utils/logging_config.py
index c3692937..90d33cdf 100644
--- a/src/utils/logging_config.py
+++ b/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')
-# DATETIME = "debug" # 为了方便，调试的时候输出到 debug.log 文件
-LOG_FILE = f'tmp/logs/project-{DATETIME}.log'
+SAVE_DIR = os.getenv('SAVE_DIR', 'saves')
+DATETIME = datetime.now(pytz.timezone('Asia/Shanghai')).strftime('%Y-%m-%d')
+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="{time:YYYY-MM-DD HH:mm:ss} - {level} - {name} - {message}",
+ format="{time:MM-DD HH:mm:ss} {level} {name}: {message}",
colorize=True
)
diff --git a/web/src/views/DataBaseInfoView.vue b/web/src/views/DataBaseInfoView.vue
index df6b6251..64d647c0 100644
--- a/web/src/views/DataBaseInfoView.vue
+++ b/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 {