jina-ai/embedding-fingerprints

Identify which embedding model produced a vector using digit-level tokenization and a tiny transformer

24
/ 100
Experimental

This project helps machine learning engineers identify which embedding model was used to create a given vector. You provide an embedding vector, and it tells you which model (like OpenAI's, Cohere's, or a specific variant) likely generated it. This is for machine learning practitioners and MLOps engineers who need to manage or understand the origin of various embedding datasets.

Use this if you have a collection of embedding vectors and need to determine which specific model produced each one without prior metadata.

Not ideal if you already know the origin of your embedding vectors or if you need to reconstruct the original text from the embeddings.

embedding-management model-governance vector-search machine-learning-operations data-lineage
No License No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 3 / 25
Community 5 / 25

How are scores calculated?

Stars

16

Forks

1

Language

Python

License

Last pushed

Mar 07, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/jina-ai/embedding-fingerprints"

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