cobalt-ai 0.3.8

ML model understanding and repair

Cobalt

Cobalt is a toolkit for illuminating and improving AI models and data.

Why Cobalt?

The time you have to understand and fix your model’s errors is limited, expensive and hard to scale to the size of your dataset. Cobalt automates the otherwise painful step of looking for patterns in how your models are performing. We're here to make topological data analysis easy to use.

Get Started

Create a new virtual environment and install Cobalt with pip.

pip install cobalt-ai

Then register your copy of Cobalt by opening a Python shell and running

import cobalt
cobalt.register_license()

See the setup instructions for more details.

Cobalt

BluelightAI Cobalt illuminates model errors and makes model performance comparisons easy in Python:

• Easily start analysis for a model or dataset with a few lines of code. Cobalt readily supports text, image, and tabular datasets.

• Automatically identify problematic groups of data in your model, saving days or weeks of troubleshooting effort.

• Quickly compare models and assess the deployment risk of each model for your use case. See here for an example comparing embedding models for product search.

• Use the groups discovered by Cobalt to track the most important metrics for model improvement: curate your data, retrain, fine-tune, or develop intuitive test cases based on Cobalt's intelligent groups.

• Explore an interactive visualization of your dataset, model errors, or embedding model using our TDA-based dimensionality reduction:

Documentation

See the documentation at docs.cobalt.bluelightai.com.

For an example on how to choose the "best embedding model for your ecommerce vector database", see here.

Community

• Slack

• Website

• LinkedIn

• YouTube