'commit'

dsSchoolBuddy/ElasticSearch/T3_InsertData.py

@@ -1,13 +1,14 @@
-import warnings
 import os
 import time
-from Config import Config
+import warnings
+
 from elasticsearch import Elasticsearch
 from langchain_core.documents import Document
-from Util.VectorUtil import text_to_vector_db  # 导入向量化工具函数
 from langchain_openai import OpenAIEmbeddings  # 直接导入嵌入模型
 from pydantic import SecretStr  # 用于包装API密钥
 
+from Config import Config
+
 # 抑制HTTPS相关警告
 warnings.filterwarnings('ignore', message='Connecting to .* using TLS with verify_certs=False is insecure')
 warnings.filterwarnings('ignore', message='Unverified HTTPS request is being made to host')
@@ -96,36 +97,6 @@ def insert_long_text_to_es(long_text: str, tags: list = None) -> bool:
         return False
 
 
-def process_text_directory(txt_dir: str) -> None:
-    """
-    处理指定目录下的所有文本文件，将其向量化并插入到Elasticsearch
-    
-    参数:
-        txt_dir: 包含文本文件的目录路径
-    """
-    for filename in os.listdir(txt_dir):
-        if filename.endswith('.txt'):
-            filepath = os.path.join(txt_dir, filename)
-            with open(filepath, 'r', encoding='utf-8') as f:
-                full_content = f.read()
-
-                if not full_content:
-                    print(f"跳过空文件: {filename}")
-                    continue
-
-                print(f"正在处理文件: {filename}")
-
-                # 提取标签
-                x = filename.split("_")
-                if len(x) >= 2:
-                    selected_tags = [x[0] + "_" + x[1]]
-                else:
-                    selected_tags = ["uncategorized"]
-
-                # 插入文本
-                insert_long_text_to_es(full_content, selected_tags)
-
-
 def main():
     # 示例1：插入单个长文本
     long_text = """混凝土是一种广泛使用的建筑材料，由水泥、砂、石子和水混合而成。它具有高强度、耐久性和良好的可塑性，被广泛应用于建筑、桥梁、道路等土木工程领域。