Sentence Transformers Embeddings

What it does

When your agent uses it

• Embedding documents for a RAG system without paying for an API
• Finding semantically similar sentences or duplicate questions
• Clustering or classifying text by meaning
• Fine-tuning an embedding model on your own sentence pairs

Example prompts

• “Embed these support tickets with all-MiniLM-L6-v2 and find the five closest to a new one.”
• “Pick a multilingual sentence-transformers model for our Spanish and German FAQ search.”
• “Fine-tune an embedding model on our labeled sentence pairs.”
• “Plug a local Sentence Transformers model into our LlamaIndex pipeline instead of OpenAI embeddings.”

Requirements

• Python with the `sentence-transformers` package

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

1. 1Start with all-MiniLM-L6-v2 - Good baseline
2. 2Normalize embeddings - Better for cosine similarity
3. 3Use GPU if available - 10× faster encoding
4. 4Batch encoding - More efficient
5. 5Cache embeddings - Expensive to recompute
6. 6Fine-tune for domain - Improves quality
7. 7Test different models - Quality varies by task
8. 8Monitor memory - Large models need more RAM

What it can do on your machine

Read from SKILL.md and the folder at commit 773a529. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com
  • huggingface.co
  • sbert.net

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sentence Transformers Embeddings loads about 1.6k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 90 tokens; SKILL.md has 216 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~90

When it runs · the whole SKILL.md, loaded when a task matches

~1.6k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Orchestra-Research/AI-Research-SKILLs at commit 773a529, republished under its MIT licence (© Orchestra-Research). 216 words, ~1,581 tokens.

name

sentence-transformers

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.

version

1.0.0

author

Orchestra Research

license

MIT

tags

Sentence Transformers, Embeddings, Semantic Similarity, RAG, Multilingual, Multimodal, Pre-Trained Models, Clustering, Semantic Search, Production

dependencies

sentence-transformers, transformers, torch

pip install sentence-transformers

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}")

# 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')

# 50+ languages
model = SentenceTransformer('paraphrase-multilingual-MiniLM-L12-v2')

# 100+ languages
model = SentenceTransformer('paraphrase-multilingual-mpnet-base-v2')

# Legal domain
model = SentenceTransformer('nlpaueb/legal-bert-base-uncased')

# Scientific papers
model = SentenceTransformer('allenai/specter')

# Code
model = SentenceTransformer('microsoft/codebert-base')

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)

# 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)

# 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
)

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')

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
)

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)

© Orchestra-Research, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in 15-rag/sentence-transformers of Orchestra-Research/AI-Research-SKILLs.

• SKILL.md
• references/models.md

Open the folder on GitHubat commit 773a529

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in Orchestra-Research/AI-Research-SKILLs, which our catalogue first saw on October 7, 2026.

• davila7/claude-code-templatescli-tool/components/skills/ai-research/rag-sentence-transformers
• OpenLAIR/dr-clawskills/rag/sentence-transformers