dayyass/muse-as-service
REST API for sentence tokenization and embedding using Multilingual Universal Sentence Encoder.
This service helps developers who need to process text in multiple languages by providing an easy way to convert sentences into numerical representations (embeddings) and split them into individual words or sub-word units (tokenization). It takes raw text as input and outputs structured tokens or numerical vectors, making it easier to compare and analyze text programmatically. It is ideal for machine learning engineers or data scientists building multilingual NLP applications.
No commits in the last 6 months. Available on PyPI.
Use this if you are a developer working on multiple text-based projects and need a centralized, memory-efficient way to get multilingual sentence embeddings and tokenization without installing large TensorFlow dependencies repeatedly.
Not ideal if you only need to process text in a single language or prefer to integrate sentence embedding models directly into your application's codebase.
Stars
51
Forks
5
Language
Python
License
MIT
Category
Last pushed
Sep 05, 2021
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/dayyass/muse-as-service"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
FlagOpen/FlagEmbedding
Retrieval and Retrieval-augmented LLMs
qdrant/fastembed
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
Blaizzy/mlx-embeddings
MLX-Embeddings is the best package for running Vision and Language Embedding models locally on...
Merck/Sapiens
Sapiens is a human antibody language model based on BERT.
amansrivastava17/embedding-as-service
One-Stop Solution to encode sentence to fixed length vectors from various embedding techniques