sentence-transformers
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- sentence-transformers
- tags
- [ "Sentence Transformers", "Embeddings", "Semantic Similarity", "RAG", "Multilingual", "Multimodal", "Pre-Trained Models", "Clustering", "Semantic Search", "Production" ]
- author
- Orchestra Research
- license
- MIT
- version
- 1.0.0
- description
- Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.
- dependencies
- [ "sentence-transformers", "transformers", "torch" ]
02 资源文件 1
- 参考文档references/models.md2.9 KB
03 SKILL.md 正文
Sentence Transformers - State-of-the-Art Embeddings
Python framework for sentence and text embeddings using transformers.
When to use Sentence Transformers
Use when:
- Need high-quality embeddings for RAG
- Semantic similarity and search
- Text clustering and classification
- Multilingual embeddings (100+ languages)
- Running embeddings locally (no API)
- Cost-effective alternative to OpenAI embeddings
Metrics:
- 15,700+ GitHub stars
- 5000+ pre-trained models
- 100+ languages supported
- Based on PyTorch/Transformers
Use alternatives instead:
- OpenAI Embeddings: Need API-based, highest quality
- Instructor: Task-specific instructions
- Cohere Embed: Managed service
Quick start
Installation
pip install sentence-transformers
Basic usage
from sentence_transformers import SentenceTransformer
# Load model
model = SentenceTransformer('all-MiniLM-L6-v2')
# Generate embeddings
sentences = [
"This is an example sentence",
"Each sentence is converted to a vector"
]
embeddings = model.encode(sentences)
print(embeddings.shape) # (2, 384)
# Cosine similarity
from sentence_transformers.util import cos_sim
similarity = cos_sim(embeddings[0], embeddings[1])
print(f"Similarity: {similarity.item():.4f}")
Popular models
General purpose
# Fast, good quality (384 dim)
model = SentenceTransformer('all-MiniLM-L6-v2')
# Better quality (768 dim)
model = SentenceTransformer('all-mpnet-base-v2')
# Best quality (1024 dim, slower)
model = SentenceTransformer('all-roberta-large-v1')
Multilingual
# 50+ languages
model = SentenceTransformer('paraphrase-multilingual-MiniLM-L12-v2')
# 100+ languages
model = SentenceTransformer('paraphrase-multilingual-mpnet-base-v2')
Domain-specific
# Legal domain
model = SentenceTransformer('nlpaueb/legal-bert-base-uncased')
# Scientific papers
model = SentenceTransformer('allenai/specter')
# Code
model = SentenceTransformer('microsoft/codebert-base')
Semantic search
from sentence_transformers import SentenceTransformer, util
model = SentenceTransformer('all-MiniLM-L6-v2')
# Corpus
corpus = [
"Python is a programming language",
"Machine learning uses algorithms",
"Neural networks are powerful"
]
# Encode corpus
corpus_embeddings = model.encode(corpus, convert_to_tensor=True)
# Query
query = "What is Python?"
query_embedding = model.encode(query, convert_to_tensor=True)
# Find most similar
hits = util.semantic_search(query_embedding, corpus_embeddings, top_k=3)
print(hits)
Similarity computation
# Cosine similarity
similarity = util.cos_sim(embedding1, embedding2)
# Dot product
similarity = util.dot_score(embedding1, embedding2)
# Pairwise cosine similarity
similarities = util.cos_sim(embeddings, embeddings)
Batch encoding
# Efficient batch processing
sentences = ["sentence 1", "sentence 2", ...] * 1000
embeddings = model.encode(
sentences,
batch_size=32,
show_progress_bar=True,
convert_to_tensor=False # or True for PyTorch tensors
)
Fine-tuning
from sentence_transformers import InputExample, losses
from torch.utils.data import DataLoader
# Training data
train_examples = [
InputExample(texts=['sentence 1', 'sentence 2'], label=0.8),
InputExample(texts=['sentence 3', 'sentence 4'], label=0.3),
]
train_dataloader = DataLoader(train_examples, batch_size=16)
# Loss function
train_loss = losses.CosineSimilarityLoss(model)
# Train
model.fit(
train_objectives=[(train_dataloader, train_loss)],
epochs=10,
warmup_steps=100
)
# Save
model.save('my-finetuned-model')
LangChain integration
from langchain_community.embeddings import HuggingFaceEmbeddings
embeddings = HuggingFaceEmbeddings(
model_name="sentence-transformers/all-mpnet-base-v2"
)
# Use with vector stores
from langchain_chroma import Chroma
vectorstore = Chroma.from_documents(
documents=docs,
embedding=embeddings
)
LlamaIndex integration
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
embed_model = HuggingFaceEmbedding(
model_name="sentence-transformers/all-mpnet-base-v2"
)
from llama_index.core import Settings
Settings.embed_model = embed_model
# Use in index
index = VectorStoreIndex.from_documents(documents)
Model selection guide
| Model | Dimensions | Speed | Quality | Use Case |
|---|---|---|---|---|
| all-MiniLM-L6-v2 | 384 | Fast | Good | General, prototyping |
| all-mpnet-base-v2 | 768 | Medium | Better | Production RAG |
| all-roberta-large-v1 | 1024 | Slow | Best | High accuracy needed |
| paraphrase-multilingual | 768 | Medium | Good | Multilingual |
Best practices
- Start with all-MiniLM-L6-v2 - Good baseline
- Normalize embeddings - Better for cosine similarity
- Use GPU if available - 10× faster encoding
- Batch encoding - More efficient
- Cache embeddings - Expensive to recompute
- Fine-tune for domain - Improves quality
- Test different models - Quality varies by task
- Monitor memory - Large models need more RAM
Performance
| Model | Speed (sentences/sec) | Memory | Dimension |
|---|---|---|---|
| MiniLM | ~2000 | 120MB | 384 |
| MPNet | ~600 | 420MB | 768 |
| RoBERTa | ~300 | 1.3GB | 1024 |
Resources
- GitHub: https://github.com/UKPLab/sentence-transformers ⭐ 15,700+
- Models: https://huggingface.co/sentence-transformers
- Docs: https://www.sbert.net
- License: Apache 2.0
04 同仓库更多 Skills
blender-web-3d
Work with Blender from Claude — headless CLI or the Blender MCP — to build, modify, render, and publish any 3D model as a stunning, fast Three.js/Next.js web experience (gltf-transform meshopt/KTX2, AgX colour pipeline, custom GLSL shaders and material patches, procedural sky/planet, bloom, adaptive quality, runtime batching, baked lightmaps, Vercel deploy). Use whenever the user wants to create, improve, fix, render, or iterate on a Blender model or scene — "improve the model", "make it look stunning", "render this", "make a 3D web demo", "export to GLB", "use blender", "looks wrong in the browser", "optimize the 3D scene", "add shaders", "it's slow", or screenshot-driven feedback on a 3D asset. Also for debugging a Three.js viewer that renders black, glows wrong, or loses/detaches parts, and for choosing Blender MCP vs headless CLI. Ships a runnable demo model and viewer template.
guizang-ppt-skill
生成横向翻页网页 PPT(单 HTML 文件),含 WebGL 背景、章节幕封、数据大字报、图片网格等模板。提供两种风格:① "电子杂志 × 电子墨水"(衬线 + 流体背景 + 暖色) ② "瑞士国际主义"(无衬线 + 网格点阵 + IKB/柠檬黄/柠檬绿/安全橙高亮)。当用户需要制作分享 / 演讲 / 发布会风格的网页 PPT,或提到"杂志风 PPT"、"瑞士风 PPT"、"Swiss Style"、"horizontal swipe deck"时使用。
youtube-clipper
YouTube 视频智能剪辑工具。下载视频和字幕,AI 分析生成精细章节(几分钟级别), 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频,并生成总结文案。 使用场景:当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词:视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video
slack-gif-creator
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
create-master
基于佛教经典文献,生成特定高僧大德的 AI 教学角色
writing-dna-skill
从至少 20 篇完整文章中蒸馏可复用的写作 DNA,分析语言、文章结构、选题逻辑、素材策略、认知框架和视觉风格,并生成 Writing-DNA.md;按该 DNA 写作时会读取全部蒸馏产物和 5 篇相关原文。用于中英文作者、账号、品牌或出版物的风格分析与一致性写作。 Distill reusable Writing DNA from at least 20 complete articles for Chinese or English authors, publications, brands, and accounts; use for language, structure, topic logic, source strategy, cognitive-frame, and visual-style analysis.