What types of embeddings can I generate with this skill?

You can generate embeddings for sentences, texts, and images using over 5000 pre-trained models available in the framework.

Is this framework suitable for production use?

Yes, Sentence Transformers is designed for production embedding generation and offers high-quality performance.

Can I fine-tune models for specific tasks?

Yes, the framework supports fine-tuning of models, allowing you to improve performance on domain-specific tasks.

How do I install Sentence Transformers?

You can install the framework using pip with the command: `pip install sentence-transformers`.

What are the advantages of using local embeddings over API-based services?

Using local embeddings eliminates API call costs and latency, providing a more efficient solution for embedding generation.

Sentence Transformers

Name: Sentence Transformers
Availability: InStock
Author: davila7

Free

Generate high-quality embeddings for text and images.

by davila730.2k stars on davila7/claude-code-templates

Updated Aug 10, 2026

Get this skill

Free · Opens the source repo

What Sentence Transformers does

Sentence Transformers is a Python framework designed for generating embeddings from sentences, texts, and images using transformer models. It provides access to over 5000 pre-trained models that excel in tasks such as semantic similarity, clustering, and retrieval. With support for multilingual and multimodal models, this framework is particularly useful for applications in production environments where high-quality embeddings are crucial for tasks like retrieval-augmented generation (RAG) and semantic search.

The framework is built on top of PyTorch and the Transformers library, ensuring that users can leverage state-of-the-art models with ease. It allows for local execution without the need for API calls, making it a cost-effective alternative to other embedding services like OpenAI's embeddings. Users can quickly install the package and start generating embeddings with just a few lines of code. The framework also includes utilities for computing similarity scores, batch processing, and even fine-tuning models for specific domains.

Whether you are working on a semantic search engine, a clustering application, or need embeddings for multilingual tasks, Sentence Transformers provides the flexibility and performance needed to meet your requirements. The extensive model selection allows users to choose models based on their specific needs, whether they prioritize speed, quality, or domain specificity. This makes it an excellent choice for developers and designers looking to integrate advanced embedding capabilities into their applications.

When to use it

Use Sentence Transformers when you need to generate embeddings for tasks like semantic search, clustering, or when working with multilingual data.

When not to use it

Avoid this skill if you require the highest quality embeddings from an API or if you need task-specific instructions that may not be covered by pre-trained models.

What you can build with it

Semantic Search Implementation

Use Sentence Transformers to encode a corpus of documents and perform semantic search queries to find the most relevant results.

Text Clustering

Generate embeddings for a large dataset of texts and apply clustering algorithms to group similar items together.

Multilingual Applications

Leverage the multilingual capabilities to generate embeddings for texts in over 100 languages, facilitating global applications.

How to install Sentence Transformers

View source

1. Install with the skills CLI

npx skills add davila7/claude-code-templates/rag-sentence-transformers --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by davila7

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

Frequently asked questions about Sentence Transformers

Similar skills

Spring Boot Testing

Master testing techniques for Spring Boot 4 applications.

GitHub Issues

Manage GitHub issues efficiently with MCP tools.

Geofeed Tuner

Optimize your IP geolocation feeds in CSV format.

Batch Files

Master Windows batch scripting for automation and task management.

Adobe Illustrator Scripting

Automate your Illustrator workflows with ExtendScript.

Plugin Structure

Create and organize Claude Code plugins effectively.