Sentence Transformers

orchestra-research/ai-research-skills/15-rag/sentence-transformers

by orchestra-research773a52944ba4MIT13K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 3 months ago

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.

Instructions onlyAI & Agents

AI-generated overview

Reference guide for using the Sentence Transformers Python library to generate text embeddings for search, clustering, and RAG.

What it does: This skill is an instructional reference for the Sentence Transformers Python framework, covering installation, model loading, and embedding generation. It shows how to compute cosine similarity, run semantic search, batch-encode text, and fine-tune models with training examples. It also lists popular general, multilingual, and domain-specific models, plus integration snippets for LangChain and LlamaIndex.
When to use it: Use it when you need to generate sentence or text embeddings locally for semantic search, clustering, classification, or retrieval-augmented generation. It is also useful when choosing among pre-trained embedding models or fine-tuning one for a specific domain.
Requirements: Requires Python with the sentence-transformers, transformers, and torch packages installed; a GPU is optional but speeds up encoding. Models are downloaded from Hugging Face, so network access is needed for first use. The skill ships no scripts, only instructions and a model reference file.

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

Basic usage

python

from sentence_transformers import SentenceTransformer
# Load modelmodel = SentenceTransformer('all-MiniLM-L6-v2')
# Generate embeddingssentences = [    "This is an example sentence",    "Each sentence is converted to a vector"]
embeddings = model.encode(sentences)print(embeddings.shape)  # (2, 384)
# Cosine similarityfrom sentence_transformers.util import cos_simsimilarity = cos_sim(embeddings[0], embeddings[1])print(f"Similarity: {similarity.item():.4f}")

from sentence_transformers import SentenceTransformer
# Load modelmodel = SentenceTransformer('all-MiniLM-L6-v2')
# Generate embeddingssentences = [    "This is an example sentence",    "Each sentence is converted to a vector"]
embeddings = model.encode(sentences)print(embeddings.shape)  # (2, 384)
# Cosine similarityfrom sentence_transformers.util import cos_simsimilarity = cos_sim(embeddings[0], embeddings[1])print(f"Similarity: {similarity.item():.4f}")

Popular models

General purpose

python

# 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')

# 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

python

# 50+ languagesmodel = SentenceTransformer('paraphrase-multilingual-MiniLM-L12-v2')
# 100+ languagesmodel = SentenceTransformer('paraphrase-multilingual-mpnet-base-v2')

# 50+ languagesmodel = SentenceTransformer('paraphrase-multilingual-MiniLM-L12-v2')
# 100+ languagesmodel = SentenceTransformer('paraphrase-multilingual-mpnet-base-v2')

Domain-specific

python

# Legal domainmodel = SentenceTransformer('nlpaueb/legal-bert-base-uncased')
# Scientific papersmodel = SentenceTransformer('allenai/specter')
# Codemodel = SentenceTransformer('microsoft/codebert-base')

# Legal domainmodel = SentenceTransformer('nlpaueb/legal-bert-base-uncased')
# Scientific papersmodel = SentenceTransformer('allenai/specter')
# Codemodel = SentenceTransformer('microsoft/codebert-base')

Semantic search

python

from sentence_transformers import SentenceTransformer, util
model = SentenceTransformer('all-MiniLM-L6-v2')
# Corpuscorpus = [    "Python is a programming language",    "Machine learning uses algorithms",    "Neural networks are powerful"]
# Encode corpuscorpus_embeddings = model.encode(corpus, convert_to_tensor=True)
# Queryquery = "What is Python?"query_embedding = model.encode(query, convert_to_tensor=True)
# Find most similarhits = util.semantic_search(query_embedding, corpus_embeddings, top_k=3)print(hits)

from sentence_transformers import SentenceTransformer, util
model = SentenceTransformer('all-MiniLM-L6-v2')
# Corpuscorpus = [    "Python is a programming language",    "Machine learning uses algorithms",    "Neural networks are powerful"]
# Encode corpuscorpus_embeddings = model.encode(corpus, convert_to_tensor=True)
# Queryquery = "What is Python?"query_embedding = model.encode(query, convert_to_tensor=True)
# Find most similarhits = util.semantic_search(query_embedding, corpus_embeddings, top_k=3)print(hits)

Similarity computation

python

# Cosine similaritysimilarity = util.cos_sim(embedding1, embedding2)
# Dot productsimilarity = util.dot_score(embedding1, embedding2)
# Pairwise cosine similaritysimilarities = util.cos_sim(embeddings, embeddings)

# Cosine similaritysimilarity = util.cos_sim(embedding1, embedding2)
# Dot productsimilarity = util.dot_score(embedding1, embedding2)
# Pairwise cosine similaritysimilarities = util.cos_sim(embeddings, embeddings)

Batch encoding

python

# Efficient batch processingsentences = ["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)

# Efficient batch processingsentences = ["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

python

from sentence_transformers import InputExample, lossesfrom torch.utils.data import DataLoader
# Training datatrain_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 functiontrain_loss = losses.CosineSimilarityLoss(model)
# Trainmodel.fit(    train_objectives=[(train_dataloader, train_loss)],    epochs=10,    warmup_steps=100)
# Savemodel.save('my-finetuned-model')

from sentence_transformers import InputExample, lossesfrom torch.utils.data import DataLoader
# Training datatrain_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 functiontrain_loss = losses.CosineSimilarityLoss(model)
# Trainmodel.fit(    train_objectives=[(train_dataloader, train_loss)],    epochs=10,    warmup_steps=100)
# Savemodel.save('my-finetuned-model')

LangChain integration

python

from langchain_community.embeddings import HuggingFaceEmbeddings
embeddings = HuggingFaceEmbeddings(    model_name="sentence-transformers/all-mpnet-base-v2")
# Use with vector storesfrom langchain_chroma import Chroma
vectorstore = Chroma.from_documents(    documents=docs,    embedding=embeddings)

from langchain_community.embeddings import HuggingFaceEmbeddings
embeddings = HuggingFaceEmbeddings(    model_name="sentence-transformers/all-mpnet-base-v2")
# Use with vector storesfrom langchain_chroma import Chroma
vectorstore = Chroma.from_documents(    documents=docs,    embedding=embeddings)

LlamaIndex integration

python

from llama_index.embeddings.huggingface import HuggingFaceEmbedding
embed_model = HuggingFaceEmbedding(    model_name="sentence-transformers/all-mpnet-base-v2")
from llama_index.core import SettingsSettings.embed_model = embed_model
# Use in indexindex = VectorStoreIndex.from_documents(documents)

from llama_index.embeddings.huggingface import HuggingFaceEmbedding
embed_model = HuggingFaceEmbedding(    model_name="sentence-transformers/all-mpnet-base-v2")
from llama_index.core import SettingsSettings.embed_model = embed_model
# Use in indexindex = 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

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

Source and attribution

Source:orchestra-research/ai-research-skillsin15-rag/sentence-transformersat commit773a529

License: MIT

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

More from orchestra-research/ai-research-skills

Speculative Decoding

orchestra-research

Guides accelerating LLM inference with speculative decoding, Medusa multi-head prediction, and lookahead decoding.

AI & Agents13Kupdated 3 months ago

Systems Paper Writing

orchestra-research

Guides paragraph-level structure and page budgets for writing systems conference papers such as OSDI, SOSP, ASPLOS and NSDI.

Writing & Content13Kupdated 3 months ago

Moe Training

orchestra-research

Guides training and inference of Mixture of Experts models with DeepSpeed or HuggingFace, covering routing, load balancing and expert parallelism.

AI & Agents13Kupdated 3 months ago

Presenting Conference Talks

orchestra-research

Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.

Awaiting classification13Kupdated 3 months ago

Model Pruning

orchestra-research

Guides LLM pruning with Wanda, SparseGPT, magnitude and N:M methods to cut model size and speed inference.

AI & Agents13Kupdated 3 months ago

Outlines

orchestra-research

Guides use of the Outlines library for structured, schema-constrained text generation with local models.

AI & Agents13Kupdated 3 months ago

Model	Speed (sentences/sec)	Memory	Dimension
MiniLM	~2000	120MB	384
MPNet	~600	420MB	768
RoBERTa	~300	1.3GB	1024

Sentence Transformers

Sentence Transformers - State-of-the-Art Embeddings

When to use Sentence Transformers

Quick start

Installation

Basic usage

Popular models

General purpose

Multilingual

Domain-specific

Semantic search

Similarity computation

Batch encoding

Fine-tuning

LangChain integration

LlamaIndex integration

Model selection guide

Best practices

Performance

Resources

Source and attribution

More from orchestra-research/ai-research-skills

Speculative Decoding

Systems Paper Writing

Moe Training

Presenting Conference Talks

Model Pruning

Outlines

More in AI & Agents

Ppt Template Creator

Skill Development

Plugin Structure

Command Development

Claude Md Improver

Find Skills