'commit'

dsSchoolBuddy/ElasticSearch/T1_RebuildMapping.py

@@ -1,8 +1,7 @@
 from Config import Config
 from ElasticSearch.Utils.EsSearchUtil import EsSearchUtil, disableWarning
 
-# 禁用警告
-disableWarning()
+
 
 # 创建EsSearchUtil实例
 search_util = EsSearchUtil(Config.ES_CONFIG)

dsSchoolBuddy/ElasticSearch/Utils/EsSearchUtil.py

@@ -18,9 +18,6 @@ def disableWarning():
     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')
 
-# 初始化配置
-disableWarning()
-
 # 初始化日志
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.INFO)
@@ -31,6 +28,8 @@ class EsSearchUtil:
                 初始化Elasticsearch搜索工具
                 :param es_config: Elasticsearch配置字典，包含hosts, username, password, index_name等
                 """
+        # 禁用警告
+        disableWarning()
         self.es_config = es_config
 
         # 初始化连接池
@@ -154,16 +153,15 @@ def insert_long_text_to_es(long_text: str, tags: list = None) -> bool:
         bool: 插入是否成功
     """
     try:
-        # 1. 初始化Elasticsearch连接
-        es = Elasticsearch(
-            hosts=Config.ES_CONFIG['hosts'],
-            basic_auth=Config.ES_CONFIG['basic_auth'],
-            verify_certs=False
-        )
+        # 1. 创建EsSearchUtil实例以使用连接池
+        search_util = EsSearchUtil(Config.ES_CONFIG)
+        
+        # 2. 从连接池获取连接
+        conn = search_util.es_pool.get_connection()
 
-        # 2. 检查索引是否存在，不存在则创建
+        # 3. 检查索引是否存在，不存在则创建
         index_name = Config.ES_CONFIG['index_name']
-        if not es.indices.exists(index=index_name):
+        if not conn.indices.exists(index=index_name):
             # 定义mapping结构
             mapping = {
                 "mappings": {
@@ -186,33 +184,33 @@ def insert_long_text_to_es(long_text: str, tags: list = None) -> bool:
                     }
                 }
             }
-            es.indices.create(index=index_name, body=mapping)
+            conn.indices.create(index=index_name, body=mapping)
             print(f"索引 '{index_name}' 创建成功")
 
-        # 3. 切割文本
+        # 4. 切割文本
         text_chunks = split_text_into_chunks(long_text)
 
-        # 4. 准备标签
+        # 5. 准备标签
         if tags is None:
             tags = ["general_text"]
 
-        # 5. 获取当前时间
+        # 6. 获取当前时间
         timestamp = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
 
-        # 6. 创建嵌入模型
+        # 7. 创建嵌入模型
         embeddings = OpenAIEmbeddings(
             model=Config.EMBED_MODEL_NAME,
             base_url=Config.EMBED_BASE_URL,
             api_key=SecretStr(Config.EMBED_API_KEY)
         )
 
-        # 7. 为每个文本块生成向量并插入
+        # 8. 为每个文本块生成向量并插入
         for i, chunk in enumerate(text_chunks):
             # 生成文本块的哈希值作为文档ID
             doc_id = hashlib.md5(chunk.encode('utf-8')).hexdigest()
 
             # 检查文档是否已存在
-            if es.exists(index=index_name, id=doc_id):
+            if conn.exists(index=index_name, id=doc_id):
                 print(f"文档块 {i+1} 已存在，跳过插入: {doc_id}")
                 continue
 
@@ -228,13 +226,17 @@ def insert_long_text_to_es(long_text: str, tags: list = None) -> bool:
             }
 
             # 插入数据到Elasticsearch
-            es.index(index=index_name, id=doc_id, document=doc)
+            conn.index(index=index_name, id=doc_id, document=doc)
             print(f"文档块 {i+1} 插入成功: {doc_id}")
 
         return True
     except Exception as e:
         print(f"插入数据失败: {e}")
         return False
+    finally:
+        # 确保释放连接回连接池
+        if 'conn' in locals() and 'search_util' in locals():
+            search_util.es_pool.release_connection(conn)