</>
pythonbeginner

Sentence Transformers Local Embeddings

Generate high-quality text embeddings locally using Sentence Transformers without API calls.

python
from sentence_transformers import SentenceTransformer
import numpy as np

model = SentenceTransformer('all-MiniLM-L6-v2')

sentences = [
    'Machine learning powers modern AI.',
    'Deep learning is a subset of ML.',
    'Python is a popular programming language.',
    'The weather is sunny today.',
]

embeddings = model.encode(sentences, normalize_embeddings=True)

# Cosine similarity (dot product of normalised vectors)
sim_matrix = embeddings @ embeddings.T

for i, s in enumerate(sentences):
    most_similar = np.argsort(sim_matrix[i])[::-1][1]
    print(f'{s!r} -> most similar: {sentences[most_similar]!r} ({sim_matrix[i][most_similar]:.3f})')

Use Cases

  • semantic search
  • local embeddings
  • text similarity

Tags

#sentence-transformers#embeddings#local#nlp

Related Snippets

Similar patterns you can reuse in the same workflow.

pythonadvanced

Semantic Chunking for RAG Documents

Split documents into semantically coherent chunks using embedding similarity for better RAG retrieval.

Best for: RAG optimization

#chunking#rag
typescriptbeginner

Generate Text Embeddings with OpenAI

Create vector embeddings for semantic search and similarity matching using text-embedding-3-small.

Best for: semantic search

#openai#embeddings
typescriptadvanced

RAG Pipeline (Retrieve + Augment + Generate)

Minimal RAG implementation: embed a query, retrieve top-k chunks, inject into prompt.

Best for: document Q&A

#rag#embeddings
typescriptintermediate

Pinecone Vector Store Operations

Store and query vector embeddings with Pinecone for semantic search and similarity matching.

Best for: Semantic search engines

#pinecone#vector-store