'commit'

dsRag/T5_SentenceSave.py

@@ -1,6 +1,17 @@
+import logging
 from datetime import datetime
 from elasticsearch import Elasticsearch
 
+# 配置日志
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(levelname)s - %(message)s',
+    handlers=[
+        logging.FileHandler('sentence_save.log'),
+        logging.StreamHandler()
+    ]
+)
+
 from Config.Config import ES_CONFIG
 from T2_Txt2Vec import text_to_embedding
 
@@ -38,22 +49,20 @@ def check_text_exists(text, index_name="raw_texts"):
 def save_vector(text, index_name="knowledge_base"):
     """将文本向量化后保存到ES"""
     try:
-        # 向量化文本
+        logging.info(f"开始向量化文本: {text[:50]}...")
         vector = text_to_embedding(text)
         
-        # 准备文档
         doc = {
             "text": text,
             "vector": vector,
             "timestamp": datetime.now()
         }
         
-        # 保存到ES
         res = es.index(index=index_name, document=doc)
-        print(f"向量化文档已保存，ID: {res['_id']}")
+        logging.info(f"成功保存向量化文档到{index_name}, ID: {res['_id']}, 文本长度: {len(text)}")
         return res['_id']
     except Exception as e:
-        print(f"保存失败: {str(e)}")
+        logging.error(f"向量保存失败: {str(e)}", exc_info=True)
         raise
 
 def save_raw_text(text, index_name="raw_texts"):