'commit'

dsRag/ElasticSearch/T6_XiangLiangQuery.py

@@ -1,16 +1,12 @@
 import logging
 
 from Config.Config import ES_CONFIG
+from Util.EsSearchUtil import EsSearchUtil
 
 # 初始化日志
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.INFO)
 
-
-
-# 导入EsSearchUtil
-from Util.EsSearchUtil import EsSearchUtil
-
 # 初始化EsSearchUtil
 es_search_util = EsSearchUtil(ES_CONFIG)
 

dsRag/Util/EsSearchUtil.py

@@ -3,6 +3,8 @@ import os
 from logging.handlers import RotatingFileHandler
 import jieba
 from elasticsearch import Elasticsearch
+from gensim.models import KeyedVectors
+from Config.Config import MS_MODEL_PATH, MS_MODEL_LIMIT
 
 from ElasticSearch.Utils.ElasticsearchConnectionPool import ElasticsearchConnectionPool
 
@@ -16,14 +18,13 @@ handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)s - %(message)
 logger.addHandler(handler)
 
 class EsSearchUtil:
-
     def __init__(self, es_config):
         """
-        初始化Elasticsearch搜索工具
+                初始化Elasticsearch搜索工具
-        :param es_config: Elasticsearch配置字典，包含hosts, username, password, index_name等
+                :param es_config: Elasticsearch配置字典，包含hosts, username, password, index_name等
-        """
+                """
         self.es_config = es_config
-        
+
         # 初始化连接池
         self.es_pool = ElasticsearchConnectionPool(
             hosts=es_config['hosts'],
@@ -31,7 +32,7 @@ class EsSearchUtil:
             verify_certs=es_config.get('verify_certs', False),
             max_connections=50
         )
-        
+
         # 保留直接连接用于兼容
         from elasticsearch import Elasticsearch
         self.es = Elasticsearch(
@@ -39,14 +40,14 @@ class EsSearchUtil:
             basic_auth=es_config['basic_auth'],
             verify_certs=es_config.get('verify_certs', False)
         )
-        
+
         # 确保es_conn属性存在以兼容旧代码
         self.es_conn = self.es
 
-    def __init__(self, es_config):
+        # 确保es_conn属性存在以兼容旧代码
-        from gensim.models import KeyedVectors
+        self.es_conn = self.es
-        from Config.Config import MS_MODEL_PATH, MS_MODEL_LIMIT
+
-        
+
         # 加载预训练模型
         self.model = KeyedVectors.load_word2vec_format(MS_MODEL_PATH, binary=False, limit=MS_MODEL_LIMIT)
         logger.info(f"模型加载成功，词向量维度: {self.model.vector_size}")