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.
|
|
|
|
from WxMini.Milvus.Config.MulvusConfig import *
|
|
|
|
|
from WxMini.Milvus.Utils.MilvusCollectionManager import MilvusCollectionManager
|
|
|
|
|
from WxMini.Milvus.Utils.MilvusConnectionPool import *
|
|
|
|
|
from gensim.models import KeyedVectors
|
|
|
|
|
|
|
|
|
|
# 加载预训练的 Word2Vec 模型
|
|
|
|
|
model_path = "D:/Tencent_AILab_ChineseEmbedding/Tencent_AILab_ChineseEmbedding.txt" # 替换为你的 Word2Vec 模型路径
|
|
|
|
|
model = KeyedVectors.load_word2vec_format(model_path, binary=False, limit=10000)
|
|
|
|
|
|
|
|
|
|
# 将文本转换为嵌入向量
|
|
|
|
|
def text_to_embedding(text):
|
|
|
|
|
words = text.split()
|
|
|
|
|
embeddings = [model[word] for word in words if word in model]
|
|
|
|
|
if embeddings:
|
|
|
|
|
return sum(embeddings) / len(embeddings) # 取词向量的平均值
|
|
|
|
|
else:
|
|
|
|
|
return [0.0] * model.vector_size # 如果文本中没有有效词,返回零向量
|
|
|
|
|
|
|
|
|
|
# 1. 使用连接池管理 Milvus 连接
|
|
|
|
|
milvus_pool = MilvusConnectionPool(host=MS_HOST, port=MS_PORT, max_connections=MS_MAX_CONNECTIONS)
|
|
|
|
|
|
|
|
|
|
# 2. 从连接池中获取一个连接
|
|
|
|
|
connection = milvus_pool.get_connection()
|
|
|
|
|
|
|
|
|
|
# 3. 初始化集合管理器
|
|
|
|
|
collection_name = MS_COLLECTION_NAME
|
|
|
|
|
collection_manager = MilvusCollectionManager(collection_name)
|
|
|
|
|
|
|
|
|
|
# 4. 插入数据
|
|
|
|
|
texts = [
|
|
|
|
|
"我今天心情不太好,因为工作压力很大。", # 第一个对话文本
|
|
|
|
|
"我最近在学习 Python,感觉很有趣。", # 第二个对话文本
|
|
|
|
|
"我打算周末去爬山,放松一下。", # 第三个对话文本
|
|
|
|
|
"吉林省广告产业园是东师理想的办公地点。" # 第四个对话文本
|
|
|
|
|
]
|
|
|
|
|
embeddings = [text_to_embedding(text) for text in texts] # 使用文本模型生成向量
|
|
|
|
|
|
|
|
|
|
# 5. 插入数据,确保字段顺序与集合定义一致
|
|
|
|
|
entities = [texts, embeddings] # 第一个列表是 text 字段,第二个列表是 embedding 字段
|
|
|
|
|
collection_manager.insert_data(entities)
|
|
|
|
|
print("数据插入成功。")
|
|
|
|
|
|
|
|
|
|
# 6. 释放连接
|
|
|
|
|
milvus_pool.release_connection(connection)
|
|
|
|
|
|
|
|
|
|
# 7. 关闭连接池
|
|
|
|
|
milvus_pool.close()
|