Sentence-Transformers 速查表
Sentence-Transformers 是一个将文本编码为密集向量的 Python 库，基于预训练的 Transformer 模型。广泛应用于语义搜索、聚类、文本相似度计算、RAG 嵌入等场景。
更新: 2026-07-20·7 条命令
快速开始
``bash
pip install sentence-transformers
python -c "
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('all-MiniLM-L6-v2')
emb = model.encode('你好世界')
print(emb.shape) # (384,)
"
``
启动模式(1)
| 命令 | 难度 | ||
|---|---|---|---|
pip install sentence-transformers安装 Sentence-Transformers | 基础 | pip install sentence-transformers |
ai-embedding(6)
| 命令 | 难度 | ||
|---|---|---|---|
st encode将文本编码为嵌入向量 | 基础 | python -c 'from sentence_transformers import SentenceTransformer; model = SentenceTransformer("all-MiniLM-L6-v2"); emb = model.encode("Hello world"); print(emb.shape)'
| |
st encode batch批量编码多段文本 | 基础 | python -c 'from sentence_transformers import SentenceTransformer; model = SentenceTransformer("all-MiniLM-L6-v2"); embs = model.encode(["Hello", "World"]); print(embs.shape)'
| |
st similarity计算两个文本的语义相似度 | 基础 | python -c 'from sentence_transformers import SentenceTransformer, util; model = SentenceTransformer("all-MiniLM-L6-v2"); emb1 = model.encode("I love cats"); emb2 = model.encode("I like dogs"); print(util.cos_sim(emb1, emb2))'
| |
st paraphrase mining发现语义相似的句子对 | 高级 | python -c 'from sentence_transformers import SentenceTransformer, util; model = SentenceTransformer("all-MiniLM-L6-v2"); sentences=["I love cats","I like dogs","Cars are fast"]; embs = model.encode(sentences); pairs = util.paraphrase_mining(embs, sentences); print(pairs[0])'
| |
st semantic search在文档集中搜索最相关的文本 | 中级 | python -c 'from sentence_transformers import SentenceTransformer, util; model = SentenceTransformer("all-MiniLM-L6-v2"); corpus=["AI is great","I love programming"]; query="machine learning"; c_emb = model.encode(corpus); q_emb = model.encode(query); print(util.cos_sim(q_emb, c_emb))'
| |
st cross-encoder使用 Cross-Encoder 进行精排 | 高级 | python -c 'from sentence_transformers import CrossEncoder; model = CrossEncoder("cross-encoder/ms-marco-MiniLM-L6-v2"); pairs=[("Query","Doc1"),("Query","Doc2")]; print(model.predict(pairs))'
|
常见问题
本速查表数据整理自各工具官方文档。最后更新: 2026-07-20。