ProxyGPT

Lightweight OpenAI wrapper using FastAPI. Add rate limits to OpenAI usage, optionally log and store all API calls, and share regulated OpenAI API access without providing your secret key. Comes with additional modules to log and graph API results.

MIT License

Stars
11
ProxyGPT - v0.2.0-beta Latest Release

Published by Bklieger 10 months ago

ProxyGPT

ProxyGPT is a dockerized lightweight OpenAI wrapper using FastAPI. This solution allows you to add custom hourly and daily rate limits to your OpenAI API usage, and share OpenAI access with your team without providing your secret key. This is a more secure option for sharing credentials during development, as OpenAI has yet to provide an API key-specific usage cap. You can confine OpenAI API usage through ProxyGPT with hourly and daily rate limits, in addition to only exposing specific endpoints of the OpenAI API. ProxyGPT also allows you the ability to reset or remove your team's access to the OpenAI API for only the services or people using a specific instance of ProxyGPT, rather than needing to reset the original OpenAI API key which could impact other projects if multiple services are using the same key (which is not recommended in production).

ProxyGPT comes with several modules, which are additional features beyond a simple proxy. These include logging and graphics, which allows full logging of the request and response for the API calls, and produces a dashboard for analyzing the results of the API calls.

v0.2.0-beta

This is a new release of ProxyGPT which has matured to become a tool suitable for production. The addition of modules increases the value of using ProxyGPT beyond the rate limit feature.

ProxyGPT - v0.1.0

Published by Bklieger 10 months ago

ProxyGPT

ProxyGPT is a dockerized lightweight OpenAI wrapper using FastAPI. This solution allows you to add custom hourly and daily rate limits to your OpenAI API usage, and share OpenAI access with your team without providing your secret key. This is a more secure option for sharing credentials during development, as OpenAI has yet to provide an API key specific usage cap. You can confine OpenAI API usage through ProxyGPT with hourly and daily rate limits, in addition to only exposing specific endpoints of the OpenAI API. ProxyGPT also allows you the ability to reset or remove your team's access to the OpenAI API for only the services or people using a specific instance of ProxyGPT, rather than needing to reset the original OpenAI API key which could impact other projects if multiple services are using the same key.

This solution is only recommended in development. In production, the rate limit logic used in this application should be copied to your own application. In addition, you should use seperate OpenAI API keys for different projects and services.

v0.1.0

This is the initial release of ProxyGPT, with basic hourly and daily rate limits, docker support, and one ProxyGPT API key defined in environment variables. The software is designed as a tool for development, and can be modified to integrate with your codebase if you wish to use it in production.

ProxyGPT - v0.1.0-beta

Published by Bklieger about 1 year ago

ProxyGPT

ProxyGPT is a dockerized lightweight OpenAI wrapper using FastAPI. This solution allows you to add custom hourly and daily rate limits to your OpenAI API usage, and share OpenAI access with your team without providing your secret key. This is a more secure option for sharing credentials during development, as OpenAI has yet to provide an API key specific usage cap. You can confine OpenAI API usage through ProxyGPT with hourly and daily rate limits, in addition to only exposing specific endpoints of the OpenAI API. ProxyGPT also allows you the ability to reset or remove your team's access to the OpenAI API for only the services or people using a specific instance of ProxyGPT, rather than needing to reset the original OpenAI API key which could impact other projects if multiple services are using the same key.

This solution is only recommended in development. In production, the rate limit logic used in this application should be copied to your own application. In addition, you should use seperate OpenAI API keys for different projects and services.

v0.1.0-beta

This is the initial beta release of ProxyGPT, with basic hourly and daily rate limits, docker support, and one ProxyGPT API key defined in environment variables. The software is designed as a tool for development, and should be modified to integrate with your codebase if you wish to use it in production.