yuniko-software/bge-m3-onnx

ONNX implementation of the BGE-M3 multilingual embedding model and tokenizer with native C#, Java, and Python implementations. Generates all three embedding types: dense, sparse, and ColBERT vectors.

45
/ 100
Emerging

This project helps developers integrate advanced multilingual text understanding into their applications. It takes raw text in many languages and converts it into numerical representations (embeddings) suitable for tasks like search or recommendation systems. This is for software developers building applications that need to process and compare text efficiently, especially across different languages.

Use this if you are a developer building an application that needs to understand and compare text across multiple languages, requiring fast, local processing without external API calls.

Not ideal if you are an end-user without programming experience, as this is a developer tool requiring coding knowledge to implement.

multilingual-NLP information-retrieval text-embedding cross-language-search AI-application-development
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 13 / 25

How are scores calculated?

Stars

30

Forks

5

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/yuniko-software/bge-m3-onnx"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.