Metadata-Version: 2.1
Name: emopoint
Version: 0.1.0
Summary: A library for mapping text into a multidimensional embedding space representing emotion
License: Apache 2
Author: Tim Kellogg
Author-email: timothy.kellogg@gmail.com
Requires-Python: >=3.8,<4.0
Classifier: License :: Other/Proprietary License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Requires-Dist: numpy (>=1.0)
Description-Content-Type: text/markdown

Extract emotional information from embeddings.

When working with LLMs, various embedding models capture emotional information 
that might be useful to work with (or without!). 

An emopoint is a simplified embedding with interpretable dimensions:
 1. joy vs sadness
 2. anger vs fear
 3. disgust vs surprise

So, for example OpenAI's `text-embedding-3-small` returns embeddings with 1536
dimensions. This library will convert those into 3 dimensions, losing most
information except for what directly relates to emotion.

This library enables two modes:
 1. Isolate emotion, converting it into 3D emopoint vectors
 2. Remove emotion, stay in original dimensionality

# Install
Install using your language's package manager:

* [NPM](https://www.npmjs.com/package/emopoint)
*

