You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
21 lines
624 B
21 lines
624 B
'''
|
|
conda activate rag
|
|
pip install gensim[complete]
|
|
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)
|
|
|
|
# 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
|