'commit'

dsRag/Milvus/X4_InsertData.py

@@ -6,6 +6,9 @@ import jieba
 import os
 import time
 
+# 需要进行标记的标签
+selectedTags = ["MATH_DATA_2", "小学数学"]
+
 # 1. 加载预训练的 Word2Vec 模型
 model_path = MS_MODEL_PATH
 model = KeyedVectors.load_word2vec_format(model_path, binary=False, limit=MS_MODEL_LIMIT)
@@ -40,16 +43,16 @@ for filename in os.listdir(txt_dir):
             first_line = f.readline().strip()
             # 读取全部内容用于后续查询
             full_content = first_line + '\n' + f.read()
-            
+
             if not first_line:
                 print(f"跳过空文件: {filename}")
                 continue
-                
+
             print(f"正在处理文件: {filename}")
 
             # 5. 获取当前时间和会话ID
             timestamp = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
-            tags = {"tags": ["MATH_DATA_1", "小学数学"], "full_content": full_content} # 添加完整内容
+            tags = {"tags": selectedTags, "full_content": full_content}  # 添加完整内容
 
             # 6. 将第一行文本转换为嵌入向量
             embedding = text_to_embedding(first_line)