Reverse proxy server for various LLM APIs. Features translation between API formats, user management, anti-abuse, API key rotation, DALL-E support, and optional prompt/response logging.

Go to file

nai-degen daf6a123d5 adjusts Agnai.chat and RisuAI rate limiting		2023-10-04 09:39:59 -05:00
.husky	Add temporary user tokens (khanon/oai-reverse-proxy!42 )	2023-09-09 22:21:38 +00:00
docker	Add docs and support for Render.com deployments (khanon/oai-reverse-proxy!9 )	2023-05-15 21:47:30 +00:00
docs	updates huggingface docs to clarify gatekeeper	2023-09-24 11:00:25 +00:00
src	adjusts Agnai.chat and RisuAI rate limiting	2023-10-04 09:39:59 -05:00
.env.example	improves AWS .env.example and config.ts docs	2023-10-03 20:29:49 -05:00
.gitattributes	initial commit	2023-04-08 01:54:44 -05:00
.gitignore	strips reverse proxy originating IP headers	2023-09-29 03:00:55 -05:00
.prettierrc	Implement AWS Bedrock support (khanon/oai-reverse-proxy!45 )	2023-10-01 01:40:18 +00:00
README.md	Anthropic endpoint improvements (khanon/oai-reverse-proxy!16 )	2023-05-30 03:13:17 +00:00
package-lock.json	address npm audit; adds zod-error package	2023-10-03 19:05:46 -05:00
package.json	address npm audit; adds zod-error package	2023-10-03 19:05:46 -05:00
render.yaml	Add docs and support for Render.com deployments (khanon/oai-reverse-proxy!9 )	2023-05-15 21:47:30 +00:00
tsconfig.json	Add tokenizers and configurable context size limits (khanon/oai-reverse-proxy!28 )	2023-07-22 00:11:32 +00:00

README.md

OAI Reverse Proxy

Reverse proxy server for the OpenAI and Anthropic APIs. Forwards text generation requests while rejecting administrative/billing requests. Includes optional rate limiting and prompt filtering to prevent abuse.

What is this?
Why?
Usage Instructions
- Deploy to Huggingface (Recommended)
- Deploy to Repl.it (WIP)
Local Development

What is this?

If you would like to provide a friend access to an API via keys you own, you can use this to keep your keys safe while still allowing them to generate text with the API. You can also use this if you'd like to build a client-side application which uses the OpenAI or Anthropic APIs, but don't want to build your own backend. You should never embed your real API keys in a client-side application. Instead, you can have your frontend connect to this reverse proxy and forward requests to the downstream service.

This keeps your keys safe and allows you to use the rate limiting and prompt filtering features of the proxy to prevent abuse.

Why?

OpenAI keys have full account permissions. They can revoke themselves, generate new keys, modify spend quotas, etc. You absolutely should not share them, post them publicly, nor embed them in client-side applications as they can be easily stolen.

This proxy only forwards text generation requests to the downstream service and rejects requests which would otherwise modify your account.

Usage Instructions

If you'd like to run your own instance of this proxy, you'll need to deploy it somewhere and configure it with your API keys. A few easy options are provided below, though you can also deploy it to any other service you'd like.

Deploy to Huggingface (Recommended)

See here for instructions on how to deploy to a Huggingface Space.

Deploy to Render

See here for instructions on how to deploy to Render.com.

Local Development

To run the proxy locally for development or testing, install Node.js >= 18.0.0 and follow the steps below.

Clone the repo
Install dependencies with npm install
Create a .env file in the root of the project and add your API keys. See the .env.example file for an example.
Start the server in development mode with npm run start:dev.

You can also use npm run start:dev:tsc to enable project-wide type checking at the cost of slower startup times. npm run type-check can be used to run type checking without starting the server.