pentoai/vectory
Vectory provides a collection of tools to track and compare embedding versions.
This tool helps machine learning engineers manage and evaluate different versions of embedding models. You input CSV files describing your datasets and NumPy arrays of the embeddings generated by your models. It outputs visualizations and metrics that allow you to compare how well different embedding versions perform and track their lineage.
No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning engineer who needs to systematically track, compare, and visualize the performance of various embedding models and their outputs across different datasets.
Not ideal if you are not working with machine learning embeddings or if you need a simple, single-shot evaluation without needing to track multiple experiments over time.
Stars
71
Forks
—
Language
Python
License
MIT
Category
Last pushed
Nov 25, 2022
Commits (30d)
0
Dependencies
20
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/pentoai/vectory"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shibing624/similarities
Similarities: a toolkit for similarity calculation and semantic search....
explosion/sense2vec
🦆 Contextually-keyed word vectors
chakki-works/chakin
Simple downloader for pre-trained word vectors
sebischair/Lbl2Vec
Lbl2Vec learns jointly embedded label, document and word vectors to retrieve documents with...
pdrm83/sent2vec
How to encode sentences in a high-dimensional vector space, a.k.a., sentence embedding.