SentenceTransformer简单使用

时间：2025-05-08 07:24:02

SentenceTransformer简单使用

1 SentenceTransformer介绍

SentenceTransformer主要用于对句子、文本和图像进行嵌入。可用于文本和图像的相似度对比查找等

# SentenceTransformer官网地址
/

# 安装SentenceTransformer
pip install -U sentence-transformers -i /simple

2 基本使用

2.1 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.",
]

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

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

2.2 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 ()
emb1 = ("This is a red cat with a hat.")
emb2 = ("Have you seen my red cat?")

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

2.3 查找相似度较大的文本

它还可以跟Elasticsearch结合使用。


from sentence_transformers import SentenceTransformer, util
import torch

embedder = SentenceTransformer("E:\\model\\distiluse-base-multilingual-cased-v1")

# Corpus with example sentences
corpus = [
    "A man is eating food.",
    "A man is eating a piece of bread.",
    "The girl is carrying a baby.",
    "A man is riding a horse.",
    "A woman is playing violin.",
    "Two men pushed carts through the woods.",
    "A man is riding a white horse on an enclosed ground.",
    "A monkey is playing drums.",
    "A cheetah is running behind its prey.",
]
corpus_embeddings = (corpus, convert_to_tensor=True)

# Query sentences:
queries = [
    "A man is eating pasta.",
    "Someone in a gorilla costume is playing a set of drums.",
    "A cheetah chases prey on across a field.",
]

# Find the closest 5 sentences of the corpus for each query sentence based on cosine similarity
top_k = min(5, len(corpus))
for query in queries:
    query_embedding = (query, convert_to_tensor=True)

    # We use cosine-similarity and  to find the highest 5 scores
    cos_scores = util.cos_sim(query_embedding, corpus_embeddings)[0]
    top_results = (cos_scores, k=top_k)

    print("\n\n======================\n\n")
    print("Query:", query)
    print("\nTop 5 most similar sentences in corpus:")

    for score, idx in zip(top_results[0], top_results[1]):
        print(corpus[idx], "(Score: {:.4f})".format(score))

相关文章