From c9bf55b7fe1ab0a70d60432d8e28313b5d364722 Mon Sep 17 00:00:00 2001
From: HuangHai <10402852@qq.com>
Date: Fri, 27 Jun 2025 14:49:25 +0800
Subject: [PATCH] 'commit'

---
 dsRag/ElasticSearch/T6_XiangLiangQuery.py     |   9 +---
 dsRag/Util/EsSearchUtil.py                    |  39 ++++++++++++++----
 .../__pycache__/EsSearchUtil.cpython-310.pyc  | Bin 3156 -> 3824 bytes
 3 files changed, 33 insertions(+), 15 deletions(-)

diff --git a/dsRag/ElasticSearch/T6_XiangLiangQuery.py b/dsRag/ElasticSearch/T6_XiangLiangQuery.py
index 1628df80..25c3bd92 100644
--- a/dsRag/ElasticSearch/T6_XiangLiangQuery.py
+++ b/dsRag/ElasticSearch/T6_XiangLiangQuery.py
@@ -2,9 +2,7 @@ import logging
 import os
 from logging.handlers import RotatingFileHandler
 
-from gensim.models import KeyedVectors
-
-from Config.Config import ES_CONFIG, MS_MODEL_PATH, MS_MODEL_LIMIT
+from Config.Config import ES_CONFIG
 from ElasticSearch.Utils.ElasticsearchConnectionPool import ElasticsearchConnectionPool
 
 # 初始化日志
@@ -16,11 +14,6 @@ handler = RotatingFileHandler('Logs/start.log', maxBytes=1024 * 1024, backupCoun
 handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)s - %(message)s'))
 logger.addHandler(handler)
 
-# 1. 加载预训练的 Word2Vec 模型
-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: {model.vector_size}")
-
-
 
 def init_es_pool():
     # 初始化Elasticsearch连接池
diff --git a/dsRag/Util/EsSearchUtil.py b/dsRag/Util/EsSearchUtil.py
index 6ded7acc..21aa4b6e 100644
--- a/dsRag/Util/EsSearchUtil.py
+++ b/dsRag/Util/EsSearchUtil.py
@@ -1,11 +1,21 @@
+import logging
+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
 
+# 初始化日志
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.INFO)
+# 确保日志目录存在
+os.makedirs('Logs', exist_ok=True)
+handler = RotatingFileHandler('Logs/start.log', maxBytes=1024 * 1024, backupCount=5)
+handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)s - %(message)s'))
+logger.addHandler(handler)
 
 class EsSearchUtil:
+
     def __init__(self, es_config):
         """
         初始化Elasticsearch搜索工具
@@ -18,15 +28,30 @@ class EsSearchUtil:
             verify_certs=False
         )
 
-    def text_to_embedding(self, text):
+    def __init__(self, es_config):
+        from gensim.models import KeyedVectors
+        from Config.Config import MS_MODEL_PATH, MS_MODEL_LIMIT
+        
         # 加载预训练模型
-        model = KeyedVectors.load_word2vec_format(MS_MODEL_PATH, binary=False, limit=MS_MODEL_LIMIT)
+        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}")
+        
+        # 初始化Elasticsearch连接
+        self.es = Elasticsearch(
+            hosts=es_config['hosts'],
+            basic_auth=es_config['basic_auth'],
+            verify_certs=False
+        )
+        self.index_name = es_config['index_name']
+        
+    def text_to_embedding(self, text):
+        # 使用已加载的模型
         # 对文本分词并计算平均向量
         words = jieba.lcut(text)
-        vectors = [model[word] for word in words if word in model]
+        vectors = [self.model[word] for word in words if word in self.model]
         
         if not vectors:
-            return [0.0] * model.vector_size
+            return [0.0] * self.model.vector_size
             
         # 计算平均向量
         avg_vector = [sum(dim)/len(vectors) for dim in zip(*vectors)]
diff --git a/dsRag/Util/__pycache__/EsSearchUtil.cpython-310.pyc b/dsRag/Util/__pycache__/EsSearchUtil.cpython-310.pyc
index f57645b76a53df43ffe44389e2a7afbeccdc4c35..b32117713734e67046d521e9d0bddaa3ab66bb1b 100644
GIT binary patch
delta 2037
zcmZt{O>f*(@V#fR*Xvzxl1&PYC?P5;bZJQ`s8tJTC<H>0svugp7?s7@_p<TUUWfOb
zkVG3TQY$qrq%_(i0@4E?J#h#ppeOzT;^ZqzNe>AA01`9L+q8UGdgGb#e9ye`FMI!d
zv=h6oL*V&+;@!D@eT4jq#Dh-`h|_S?bpV`j8WJyiQ;!18LKYdGK{KA|nZPr`Tx59`
zC4y|`g?*EH1yR^^1Zfs;QsB~NiJLsft@REA(%^Y+^8$C)4bK(sW*OA_IEZTD!e+m4
z5qpjB5_c~X?p|Wv0H^0kwR{(XBGXlx4xWn>KM7imsUQ?*{1y*|1h)HX=&K~CE8)xf
zTxy<;8|p3K+hQqDNiBZw;z}8LM^xg=WGsvu0U`b5E@oY2sU7)CFE1xTrNtS)esN)b
zGG1sUE7b!BeN|6_NL1D6)1wCthGJ2KEq|Aegi?M3zScJehR>Y^V}f9{JjN+!mx*U^
zqxXh70B!OCEW%~#<p6_H0A>MJ<R!rJyu!=84=|heL)wE|Bb3p?Ekk1OWU*Uiqay~O
zX<n#WJ#Muic2kLPR+fQ#i^zd)gPo#--7ndR4(5hu5{{Y!fH8$6qN~shzzyu^su7v1
zCM9jw%(V?}wjs`SqfKg7lHats)h11=S@@KE#;`Ss)22K>OaR)$1bSQ0vPGaB;F4O2
z6NtMwEh%AyY+OCsnSv0lnV{v%<un%tQIIS=0kPcq=H~Y2A8lXT+_`=G&f1ObYhV2F
z<HtMSu5aJixO?T3-+uUR`}?n+AMNE0^0EXVb%GWbOEujA*K-@9rGjWIin$1t96||q
zGH%TVjj`+{_jFMAApqV`82h~TK`i;Ri=tkejb-E~X-+Gr7EDA#$kYs4vvFDkfh3kS
z6|4xU>&=9c!(gSFll^EB%dH*CJ&2(LIj{>Vhz$aGjDUZIft6@Ktr$a;85XsmsrFyx
zTpdcZ`<Q^CD?I89fP`$)He8KWc7@DRJx_L<y+SV0t8|U3hq=+9Yoy7V#t_u}3I!Px
zX3b8_HF}+(+^W$wI?#^Xbe)31dk=a=Zy2B&1<-)bT_~-BH?T(*iDdY0(_yl~-e>2t
z%&JsA0<zFeHug+vVjY2{i=h+8oKt5!gzHw1qxp&FfL09C8SVaTEO$@{lnu2IrA8=V
za^)zh7(9sJqUN)btE`H;fcxR|NjPAIkbRIwnrjAP#`nyyzL4l><cK!063kak9ZPB^
zVhOs6;VIAY7aO(A@JVeLoa%^i0;P_40Oe~*TociZ;2ajq5p;>u<`@-fvhvoU+%bAu
zcmI}==JW*0qv+Sf`2fd<&>HMil3LmR(c^J%R8UkN>waxLKB5byf%fg*8#BGM#=AS#
zhwtE!!BF}MY%ym+30VtT^N=l;vubEB@;F+=2?T~tCv$<^e|aeC?6RPyw|>fBppz$1
z>;+Wrjq-ivar|`Zf6TaZ%QG_Iwan1lTlGSVzUf(6__B(|47qDqP9P)eM^>m}rdUgs
z=Y>4>Uk5rP-rZk3<Q_&{CSOFM!(FfVR0qd2EAc-)WM#OYu*US@6hH$hg~hRn&Fqrh
z@3>CI$(Q>ieyvv0Jl=R{cgkXw_V<Xfx$KXkB+i_C5<n+)#e@HrY#$UFA~~y9hI|Pn
z_W?+41x)-yq~`0>Q*Yp3<)Yw$RB66vH!Xq4l-@iEY@5P;)bTm*{myiRyPZ7VYpR|Y
idmPr)LMSHiKC8U|AU#^5HY-ubDA6)2!=7<yh5Ze9|K9=t

delta 1312
zcmZWpJ8vCD6rRVv?%un8TsaAef-y-EZ3u=Kj3}HGI1mY>h{zH`D><vZcgELi?ZcT}
zJF#^wBgImj0wmayhDbE2{R60xC{s;CK}Cl|Nt1JCjh)Ap=Iq&-Z@&4?H)roZZ$E!)
zx(ouJ!0(S6_tt;y67pAbkDiY|gBd{t%}9h#meHI=jAG6+o?DS+ax1fQCvtK(aw)k@
zge{x{BAiDo@&sKWq5C&d-wCM>KF^Y>PKT9D)NsA&Sl63Xdg04kuq;VL1&NrTf*p{E
z3oa~pT4G8#!abmo4Vfo8kU5a~q6?WTrbQqoAoIi|oYX)1oif@9xpIM0dChY+H_IT^
zuB_r=Srj4DRwc7Fh2=gYDroxr2JJLo^H29Jn6hDT7}YlrYO+CVP*iilzUNO!ZT(`8
z=~KGL9+Nd{6nbNJi#(!F=pn6Ug*~E&WW$*uE95Z+gab8rwR=c^Ac)%IV~&2@`2u7(
zgS1H0j<&NjPwOEi&2RR(!9_TBM8;&*-=kw7+a`(~k}*9`eq{IA3J3;(2|&T-Kh)NP
zQVFou&PyS)c6kCY+F#1jsveg4=FJQ6{x8~ak?bxs_ubhha=zV1CLrO}R<3y_!5Y=a
zja;NT5W3rPSeL3grBr8Nc@Bm;3nBCr8l`8lG7&MVSb!bzTB-7+R_LWdGqt^u%0UuY
z*>J1Y-Ig@2(%nRAzMF1_mg*tQs^!C4+sIQzezHA^Tj+7EY6c0h5M`>HMtEG8vCIcj
zh_o1?xC+;%n9usuV!fjccah%Kep(3mFfNi@KI7UpZ|VvFp%c<w2?E|lTIhPBowhSg
zcZ9Z4W}xa?^QU)t_Qd>FMDTw#rkyW0bDi&K*gWl=TfPcp(1pmU-p7FL1`}B7F(GEJ
z@pVm6t%Sv+|2nI5`2&P4;O1A<;Os{jKF07GO|ZT*P^pMpqNSssy9K?gont@WK{BpR
zh}9xaw71aO(rq`!_0FbL*WNt9RP<F71@8rya4%DzAm~!_Q*d>E5>sR7t0%NJoGLXL
zUYBwpcreW6dBme$&!6!7zB@5#*20d$uR;g%<v$N)KI>p4iz?0MP4idKkarQdTo!BT
kXuf@%wxVHs$*dCz+FJsGtxVper~~iHBR$%qQ>@Ql0AvLrv;Y7A