SentenceTransformer的安装及简单使用教程

前言：

SentenceTransformers相关资源

来源：诚通网盘 | 提取码：7598

立即下载

镜像源在线安装：

pip install -U sentence-transformers -i https://pypi.tuna.tsinghua.edu.cn/simple

安装成功后如图：

离线安装：

离线安装的话我们首先要下载sentence_transformers离线安装包

sentence_transformers离线安装包

来源：诚通网盘 | 提取码：7598

立即下载

安装前需要先下载离线包然后解压，然后切换到解压后的目录

然后运行命令：

python setup.py install

安装完成后如图：

比较两个句子的相似度

from sentence_transformers import SentenceTransformer, util

model = SentenceTransformer("all-MiniLM-L6-v2")

# Sentences are encoded by calling model.encode()
emb1 = model.encode("This is a black cat with a hat.")
emb2 = model.encode("Have you seen my white cat?")

cos_sim = util.cos_sim(emb1, emb2)
print("Cosine-Similarity:", cos_sim)

结果：

实现文本的嵌入

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("all-MiniLM-L6-v2")

# Our sentences we like to encode
sentences = [
    "This framework generates embeddings for each input sentence",
    "Sentences are passed as a list of string.",
    "The quick brown fox jumps over the lazy dog.",
    "This is a black cat with a hat."
]

# Sentences are encoded by calling model.encode()
sentence_embeddings = model.encode(sentences)

# Print the embeddings
for sentence, embedding in zip(sentences, sentence_embeddings):
    print("Sentence:", sentence)
    print("Embedding:", embedding)

结果：

常见错误：

原因：

在线下载模型失败

解决办法：

离线下载sentence-transformers模型，解压到项目目录

文件下载：

all-MiniLM-L6-v2模型下载

来源：诚通网盘 | 提取码：7598

立即下载

stsb-xlm-r-multilingual模型下载

来源：诚通网盘 | 提取码：7598

立即下载