[0.0.3] Support Reverse Proxy and more!

Now we make it compatible with the official API (python, rust, PHP, etc.). You can use it as a proxy server between you and the OpenAI endpoint while maintaining its distribution ability to speed up requests!

First, run python -m openai_manager.serving --port 8000 --host localhost --api_key [your custom key]. Then set up the official python openai package:

import openai
openai.api_base = "http://localhost:8000/v1"
openai.api_key = "[your custom key]"

# run like normal
prompt = ["Once upon a time, "] * 10
response = openai.Completion.create(
    model="code-davinci-002",
    prompt=prompt,
    max_tokens=20,
)
print(response["choices"][0]["text"])

0.0.2 add second-level rate limit control

Now it is almost usable!
Install and try!

pip install openai-manager

[0.0.1] dev version; use at your own risk

PyPI: https://pypi.org/project/openai-manager/