Skip to main content

ProxAI is a lightweight abstraction layer for foundational AI model connections.

Project description

ProxAI

ProxAI is a lightweight abstraction layer for foundational AI model connections. It enables easy switching between providers and models for benchmarking or any other purposes. ProxAI adheres to the Zen of Python principles and prioritizes simplicity.

Installation

Package Installation

The simplest way to get ProxAI is via pip:

$ pip install proxai

Foundation Model API Keys

Before using ProxAI, set up access to third-party model providers as many as you wish. The principle is that more is better. Add your keys to ~/.zshrc and run source ~/.zshrc before running ProxAI.

Usage

To-Do: "example code", "documents", "examples".

Contributing to ProxAI

We are looking for contributors! We welcome all kinds of contributors, from fixing small typos to implementing bigger features. While we are working on a simple community guideline, don't wait for it. Feel free to jump in and contribute.

To be able to run on your local machine, follow these commands:

$ python3 -m venv .venv
$ source .venv/bin/activate
$ git clone https://github.com/proxai/proxai.git
$ cd proxai
$ pip install poetry
$ poetry install
$ python3 examples/ask_about_model.py

Please note that this project is released with a Code of Conduct. By contributing to this project, you agree to abide by its terms.

License

proxai was created by github@proxai.co. github@proxai.co retains all rights to the source and it may not be reproduced, distributed, or used to create derivative works.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

proxai-0.1.0.tar.gz (9.8 kB view details)

Uploaded Source

Built Distribution

proxai-0.1.0-py3-none-any.whl (14.4 kB view details)

Uploaded Python 3

File details

Details for the file proxai-0.1.0.tar.gz.

File metadata

  • Download URL: proxai-0.1.0.tar.gz
  • Upload date:
  • Size: 9.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.2 CPython/3.9.6 Darwin/22.6.0

File hashes

Hashes for proxai-0.1.0.tar.gz
Algorithm Hash digest
SHA256 ad865341ce4b8ca146af33b08a4d59ef1a756a9f8f9a3689e99195ca00778f79
MD5 d7f22984096daeab07675c7436940742
BLAKE2b-256 2adfd4910a39c4e2f12fd9391c1087dc153b632419855fbe21d099af39da2834

See more details on using hashes here.

File details

Details for the file proxai-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: proxai-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 14.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.2 CPython/3.9.6 Darwin/22.6.0

File hashes

Hashes for proxai-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2358a86c716790566296826721858e70e6f85dfa28ab4bdf7dcbe31060da19ec
MD5 cb81d7d1ed4496afc64d3be90ac860e4
BLAKE2b-256 c010169e581b582af5a533a5fc5e70f2c383f10529a8f527b698e5f248906604

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page