https://github.com/connectai-e/chatgpt-severless-proxy

利用阿里云函数给openai搭建反向代理，🤹🏻‍♂️支持负载均衡和自定义token
https://github.com/connectai-e/chatgpt-severless-proxy

Last synced: 8 months ago
JSON representation

利用阿里云函数给openai搭建反向代理，🤹🏻‍♂️支持负载均衡和自定义token

• Host: GitHub
• URL: https://github.com/connectai-e/chatgpt-severless-proxy
• Owner: ConnectAI-E
• License: mit
• Created: 2023-03-30T09:37:45.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2023-03-30T14:14:29.000Z (about 3 years ago)
• Last Synced: 2025-02-17T03:12:28.069Z (over 1 year ago)
• Language: Go
• Homepage:
• Size: 25.4 KB
• Stars: 2
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# ChatGPT-Severless-Proxy

![GitHub](https://img.shields.io/github/license/leizhenpeng/ChatGPT-Severless-Proxy)

![GitHub](https://img.shields.io/badge/build-pass-green)  

A reverse proxy of https://api.openai.com that supports token load-balance and avoids token leakage

openai api reference

`https://platform.openai.com/docs/api-reference`

## Feature

- simple, clean but efficent code

- providing an authorization without openai token leakage

- supproting token load-balance

- avoiding the limitation of single openai token

- removing invalid token automatically

## 本地开发

```nashorn js

cd code

mv config.example.yaml config.yaml

```

```

OPENAI_KEY: sk-xxx,sk-xx

AUTH_TOKEN: xxxxxxx

PORT: 9000

TARGET: https://api.openai.com

```

```

go run main.go

```

## 部署上线

```

cd ..

s deploy

```

Use by cURL

```

curl --location 'http://localhost:8080/v1/chat/completions' \

--header 'Authorization: Bearer YOUR_AUTHORIZATION' \

--header 'Content-Type: application/json' \

--data '{

    "max_tokens": 250,

    "model": "gpt-3.5-turbo",

    "messages": [

        {

            "role": "user",

            "content": "Hello!"

        }

    ]

}'

```