'commit'

dsRag/Config/Config.py

@@ -5,4 +5,6 @@ ES_CONFIG = {
     "verify_certs": False,
     "ssl_show_warn": False,
     "default_index": "knowledge_base"
-}
+}
+
+WORD2VEC_MODEL_PATH = r"D:\Tencent_AILab_ChineseEmbedding\Tencent_AILab_ChineseEmbedding.txt"

dsRag/T2_Txt2Vec.py

@@ -5,10 +5,16 @@ pip install jieba
 '''
 
 from Util.EmbeddingUtil import *
+from Config.Config import *
+
 # 在加载模型后添加自定义词典
 jieba.load_userdict("./Dict/custom_dict.txt")  # 文件中包含: 花呗
 
 sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']
 
 for sentence in sentences:
-    x = text_to_embedding(sentence)
+    x = text_to_embedding(sentence)
+
+# 词汇数+向量维度
+with open(WORD2VEC_MODEL_PATH, 'r', encoding='utf-8') as f:
+    print("词汇数和向量维度：" + f.readline())  # 第一行为词汇数和向量维度，在这里不予展示

dsRag/T4_VectorSave.py

@@ -1,8 +1,9 @@
-from Config.Config import ES_CONFIG
+import datetime
+
 from elasticsearch import Elasticsearch
+
+from Config.Config import ES_CONFIG
 from T2_Txt2Vec import text_to_embedding
-import datetime
-import warnings
 
 # 初始化ES连接
 es = Elasticsearch(
@@ -12,16 +13,15 @@ es = Elasticsearch(
     ssl_show_warn=ES_CONFIG["ssl_show_warn"]
 )
 
-# 修改create_vector_index和save_to_es函数中使用ES_CONFIG["default_index"]
 def create_vector_index(index_name="knowledge_base"):
-    """创建带有向量字段的索引"""
+    """创建带有向量字段的索引(适配200维腾讯词向量)"""
     mapping = {
         "mappings": {
             "properties": {
                 "text": {"type": "text", "analyzer": "ik_max_word"},
                 "vector": {
                     "type": "dense_vector",
-                    "dims": 768,  # 需与text2vec模型维度一致
+                    "dims": 200,  # 修改为腾讯词向量实际维度
                     "index": True,
                     "similarity": "cosine"
                 },
@@ -34,7 +34,7 @@ def create_vector_index(index_name="knowledge_base"):
         if es.indices.exists(index=index_name):
             es.indices.delete(index=index_name)
         es.indices.create(index=index_name, body=mapping)
-        print(f"索引 {index_name} 创建成功")
+        print(f"索引 {index_name} 创建成功(200维)")
     except Exception as e:
         print(f"创建索引失败: {str(e)}")
         raise

dsRag/Util/EmbeddingUtil.py

@@ -1,14 +1,13 @@
 import logging
 import jieba
 from gensim.models import KeyedVectors
-
+from Config.Config import *
 # 配置日志
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 logger = logging.getLogger(__name__)
 
 # 初始化 Word2Vec 模型
-model_path = r"D:\Tencent_AILab_ChineseEmbedding\Tencent_AILab_ChineseEmbedding.txt"
-model = KeyedVectors.load_word2vec_format(model_path, binary=False, limit=10000)
+model = KeyedVectors.load_word2vec_format(WORD2VEC_MODEL_PATH, binary=False, limit=10000)
 logger.info(f"模型加载成功，词向量维度: {model.vector_size}")
 
 # 将文本转换为嵌入向量