From ae7e658c1a77ba75ef23a5287ff88c5f365720ff Mon Sep 17 00:00:00 2001
From: weiweiw <14335254+weiweiw22@user.noreply.gitee.com>
Date: Tue, 14 Jan 2025 12:41:19 +0800
Subject: [PATCH] =?UTF-8?q?=E5=A2=9E=E5=8A=A0=E6=97=A5=E5=BF=97?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../chatchat/server/knowledge_base/utils.py            | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/libs/chatchat-server/chatchat/server/knowledge_base/utils.py b/libs/chatchat-server/chatchat/server/knowledge_base/utils.py
index ab4cdd4..2216295 100644
--- a/libs/chatchat-server/chatchat/server/knowledge_base/utils.py
+++ b/libs/chatchat-server/chatchat/server/knowledge_base/utils.py
@@ -22,6 +22,7 @@ from chatchat.server.file_rag.text_splitter import (
 from chatchat.server.utils import run_in_process_pool, run_in_thread_pool
 from chatchat.utils import build_logger
 import re
+import threading
 
 logger = build_logger()
 
@@ -228,7 +229,7 @@ def make_text_splitter(splitter_name, chunk_size, chunk_overlap):
     """
     根据参数获取特定的分词器
     """
-    logger.info(f"make_text_splitter start....splitter_name:{splitter_name}")
+    logger.info(f"threadid:{threading.get_ident()}, make_text_splitter start....splitter_name:{splitter_name}")
     splitter_name = splitter_name or "SpacyTextSplitter"
     try:
         if (
@@ -378,7 +379,7 @@ class KnowledgeFile:
             else:
                 print("文件不存在")
 
-        logger.info(f"********docs2texts")
+        logger.info(f"threadid:{threading.get_ident()},********docs2texts")
         docs = docs or self.file2docs(refresh=refresh)
         #remove the redundant line break after loading, by weiweiwang 2025/1/13
         for doc in docs:
@@ -388,9 +389,9 @@ class KnowledgeFile:
         if not docs:
             return []
         if self.ext not in [".csv"]:
-            logger.info(f"self.ext not in csv")
+            logger.info(f"threadid:{threading.get_ident()}, self.ext not in csv")
             if text_splitter is None:
-                logger.info(f"text_splitter is None")
+                logger.info(f" threadid:{threading.get_ident()}, text_splitter is None")
                 text_splitter = make_text_splitter(
                     splitter_name=self.text_splitter_name,
                     chunk_size=chunk_size,
@@ -451,6 +452,7 @@ def files2docs_in_thread_file2docs(
     *, file: KnowledgeFile, **kwargs
 ) -> Tuple[bool, Tuple[str, str, List[Document]]]:
     try:
+        logger.info(f"file2docs 从文件 {file.kb_name}/{file.filename}， threadid:{threading.get_ident()}")
         return True, (file.kb_name, file.filename, file.file2text(**kwargs))
     except Exception as e:
         msg = f"从文件 {file.kb_name}/{file.filename} 加载文档时出错：{e}"