Metadata-Version: 2.1
Name: emb-opt
Version: 1.0.2
Summary: A lightweight framework to efficiently screen vector databases
Home-page: https://github.com/DarkMatterAI/emb_opt
Author: Karl Heyer
Author-email: karl@darkmatterai.co
License: Apache Software License 2.0
Keywords: nbdev jupyter notebook python
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Natural Language :: English
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: License :: OSI Approved :: Apache Software License
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: pydantic (>=2.0)
Requires-Dist: scipy
Requires-Dist: httpx
Provides-Extra: dev
Requires-Dist: faiss-cpu ; extra == 'dev'
Requires-Dist: qdrant-client ; extra == 'dev'
Requires-Dist: matplotlib ; extra == 'dev'
Requires-Dist: datasets ; extra == 'dev'

# emb_opt

<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->

`emb_opt` uses reinforcement learning and hill climbing algorithms to
efficiently find high scoring items in embedding spaces, such as vector
databases or generative model latent spaces.

See the [documentation](https://darkmatterai.github.io/emb_opt/) site
for documentation and tutorials

## Install

``` sh
pip install emb_opt
```

## Supported Backends

`emb_opt` currently supports
[Faiss](https://github.com/facebookresearch/faiss),
[HuggingFace](https://huggingface.co/docs/datasets/faiss_es) and
[Qdrant](https://qdrant.tech/) backends
