feather -- a Python SDK to share and deploy models

TL;DR

Feather is a Python SDK that enables quick creation of shareable, user-friendly interfaces for machine learning models, facilitating easy deployment and interaction with models via URLs and APIs.

Contribution

This paper introduces Feather, a novel Python SDK that simplifies building and sharing interactive model interfaces with minimal code, supporting multi-step models and evaluation extensions.

Findings

Enables deployment of models with under 20 lines of code

Provides URLs and API endpoints for model access

Supports multi-step models and automatic evaluation

Abstract

At its core, feather was a tool that allowed model developers to build shareable user interfaces for their models in under 20 lines of code. Using the Python SDK, developers specified visual components that users would interact with. (e.g. a FileUpload component to allow users to upload a file). Our service then provided 1) a URL that allowed others to access and use the model visually via a user interface; 2) an API endpoint to allow programmatic requests to a model. In this paper, we discuss feather's motivations and the value we intended to offer AI researchers and developers. For example, the SDK can support multi-step models and can be extended to run automatic evaluation against held out datasets. We additionally provide comprehensive technical and implementation details. N.B. feather is presently a dormant project. We have open sourced our code for research purposes: https://github.com/feather-ai/