diff --git a/README.en-US.md b/README.en-US.md index 5a49e0a..0616fd2 100644 --- a/README.en-US.md +++ b/README.en-US.md @@ -2,27 +2,35 @@ [English](./README.en-US.md) | Simplified Chinese -An Azure OpenAI API proxy tool that can convert OpenAI API requests into Azure OpenAI API requests, allowing applications that only support OpenAI to seamlessly use Azure Open AI. +Azure OpenAI Proxy is a tool that transforms OpenAI API requests into Azure OpenAI API requests. This allows applications that are compatible only with OpenAI to use Azure Open AI seamlessly. -## Usage Requirements +## Prerequisites -You must have an Azure OpenAI account to use the Azure OpenAI Proxy. +To use Azure OpenAI Proxy, you need an Azure OpenAI account. -## Deploy to Azure +## Azure Deployment [![Deploy to Azure](https://aka.ms/deploytoazurebutton)](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2Fscalaone%2Fazure-openai-proxy%2Fmain%2Fdeploy%2Fazure-deploy.json) ## Docker Deployment +Run the following command to deploy using Docker: + `docker run -d -p 3000:3000 scalaone/azure-openai-proxy` -## Local Running and Testing, Command Line Method +## Local Execution and Testing (Command Line) + +Follow the steps below: 1. Install NodeJS 18. -2. Clone the code in the command line window. -3. Run `npm install` to install dependencies. +2. Clone the repository in the command line window. +3. Run `npm install` to install the dependencies. 4. Run `npm start` to start the application. -5. Run the script below for testing, replacing `AZURE_RESOURCE_ID`, `AZURE_MODEL_DEPLOYMENT`, and `AZURE_API_KEY` before running it, `AZURE_API_VERSION` is optional and the default value is `2023-03-15-preview`. +5. Use the script below for testing. Replace `AZURE_RESOURCE_ID`, `AZURE_MODEL_DEPLOYMENT`, and `AZURE_API_KEY` before executing. `AZURE_API_VERSION` is optional, its default value is `2023-05-15`. + +
+Test script + ```bash curl -X "POST" "http://localhost:3000/v1/chat/completions" \ -H 'Authorization: AZURE_RESOURCE_ID:AZURE_MODEL_DEPLOYMENT:AZURE_API_KEY:AZURE_API_VERSION' \ @@ -44,45 +52,51 @@ curl -X "POST" "http://localhost:3000/v1/chat/completions" \ }' ``` -## App has been tested +
+ +## Tested Applications -The following apps have been tested and confirmed to work with the azure-openai-proxy: +The azure-openai-proxy has been tested and confirmed to work with the following applications: -| App Name | E2E Docker-compose file | -|------------------|-------------------------| +| Application Name | Docker-compose File | +|------------------|---------------------| | [chatbot-ui](https://github.com/mckaywrigley/chatbot-ui) | [docker-compose.yml](./e2e/chatbot-ui/docker-compose.yml) | | [chatgpt-next-web](https://github.com/Yidadaa/ChatGPT-Next-Web) | [docker-compose.yml](./e2e/chatgpt-next-web/docker-compose.yml) | | [chatgpt-web](https://github.com/Chanzhaoyu/chatgpt-web) | [docker-compose.yml](./e2e/chatgpt-web/docker-compose.yml) | | [chatgpt-lite](https://github.com/blrchen/chatgpt-lite) | [docker-compose.yml](./e2e/chatgpt-lite/docker-compose.yml) | | [chatgpt-mininal](https://github.com/blrchen/chatgpt-mininal) | [docker-compose.yml](./e2e/chatgpt-mininal/docker-compose.yml) | -To run a test locally, please follow these steps: +To test locally, follow these steps: -1. Clone the code in a command-line window. -2. Update the environment variable `OPENAPI_API_KEY` with `AZURE_RESOURCE_ID:AZURE_MODEL_DEPLOYMENT:AZURE_API_KEY`. Alternatively, you can update the OPENAPI_API_KEY value directly in the docker-compose.yml file. -3. Navigate to the directory containing the `docker-compose.yml` file for the app you want to test. -4. Execute the build command: `docker-compose build`. +1. Clone the repository in a command-line window. +2. Update the `OPENAPI_API_KEY` environment variable with `AZURE_RESOURCE_ID:AZURE_MODEL_DEPLOYMENT:AZURE_API_KEY`. Alternatively, update the OPENAPI_API_KEY value directly in the docker-compose.yml file. +3. Navigate to the directory containing the `docker-compose.yml` file for the application you want to test. +4. Run the build command: `docker-compose build`. 5. Start the service: `docker-compose up -d`. -6. Based on the exposed port defined in the docker-compose.yml file, launch the app to test it locally. For example, visit http://localhost:3000. +6. Launch the application locally using the exposed port defined in the docker-compose.yml file. For example, visit http://localhost:3000. -## Frequently Asked Questions +## FAQs -Q: What is `AZURE_RESOURCE_ID`,`AZURE_MODEL_DEPLOYMENT`,`AZURE_API_KEY`? +
+Q: What are `AZURE_RESOURCE_ID`,`AZURE_MODEL_DEPLOYMENT`, and `AZURE_API_KEY`? -A: It can be found in azure management portal, see image below for details: +A: You can find these in the Azure management portal. Refer to the image below for details: ![resource-and-model](./resource-and-model.jpg) +
-Q: How do I support GPT-4？ +
+Q: How can I use GPT-4? -A: To use GPT-4, please use key format as follows: +A: To use GPT-4, use the key format as follows: `AZURE_RESOURCE_ID:gpt-3.5-turbo|AZURE_MODEL_DEPLOYMENT,gpt-4|AZURE_MODEL_DEPLOYMENT,gpt-4-32k|AZURE_MODEL_DEPLOYMENT:AZURE_API_KEY:AZURE_API_VERSION` +
-# How To Contribute Code? +## Contributing -Welcome to submit various PRs. +We welcome various PR submissions. -# Disclaimer +## Disclaimer -This code is for demonstration and testing purposes only. \ No newline at end of file +This code is intended for demonstration and testing purposes only. \ No newline at end of file diff --git a/README.md b/README.md index 09bce04..cc90bd3 100644 --- a/README.md +++ b/README.md @@ -2,7 +2,7 @@ [English](./README.en-US.md) | 简体中文 -一个 Azure OpenAI API 代理工具，能将 OpenAI API 请求转换为 Azure OpenAI API 请求，使仅支持 OpenAI 的应用程序可以无缝地使用 Azure Open AI。 +Azure OpenAI Proxy是一个 OpenAI API 代理工具，它可以将OpenAI API请求转换为Azure OpenAI API请求，使仅支持OpenAI的应用程序可以无缝地使用Azure OpenAI。 ## 使用要求 @@ -14,7 +14,9 @@ ## Docker Deployment -`docker run -d -p 3000:3000 scalaone/azure-openai-proxy` +```bash +docker run -d -p 3000:3000 scalaone/azure-openai-proxy +``` ## 本地运行和测试，命令行方式 @@ -22,7 +24,11 @@ 2. 克隆代码到命令行窗口。 3. 运行 `npm install` 安装依赖项。 4. 运行 `npm start` 启动应用程序。 -5. 运行下面脚本测试，运行前需要把`AZURE_RESOURCE_ID`，`AZURE_MODEL_DEPLOYMENT`，`AZURE_API_KEY`, `AZURE_API_VERSION`替换，`AZURE_API_VERSION`参数可选，目前默认是`2023-03-15-preview`。 +5. 运行下面脚本测试，运行前需要把`AZURE_RESOURCE_ID`，`AZURE_MODEL_DEPLOYMENT`，`AZURE_API_KEY`, `AZURE_API_VERSION`替换，`AZURE_API_VERSION`参数可选，目前默认是`2023-05-15`。 + +
+测试脚本 + ```bash curl -X "POST" "http://localhost:3000/v1/chat/completions" \ -H 'Authorization: AZURE_RESOURCE_ID:AZURE_MODEL_DEPLOYMENT:AZURE_API_KEY:AZURE_API_VERSION' \ @@ -44,6 +50,8 @@ curl -X "POST" "http://localhost:3000/v1/chat/completions" \ }' ``` +
+ ## 已测试应用 以下应用已经过测试，确认可以与 azure-openai-proxy 一起工作： @@ -61,23 +69,25 @@ curl -X "POST" "http://localhost:3000/v1/chat/completions" \ 1. 在命令行窗口中克隆代码。 2. 更新环境变量`OPENAPI_API_KEY`的值为`AZURE_RESOURCE_ID:AZURE_MODEL_DEPLOYMENT:AZURE_API_KEY`。或者，直接在`docker-compose.yml`文件中更新`OPENAPI_API_KEY`值。 3. 导航到包含要测试的应用程序的`docker-compose.yml`文件所在的目录。 -3. 执行构建命令：`docker-compose build`。 -4. 启动服务：`docker-compose up -d`。 -5. 根据`docker-compose.yml`文件中定义的公开端口，启动应用以在本地进行测试。例如，访问 http://localhost:3000。 +4. 执行构建命令：`docker-compose build`。 +5. 启动服务：`docker-compose up -d`。 +6. 根据`docker-compose.yml`文件中定义的公开端口，启动应用以在本地进行测试。例如，访问 http://localhost:3000。 ## 常见问题 -Q：什么是`AZURE_RESOURCE_ID`，`AZURE_MODEL_DEPLOYMENT`，`AZURE_API_KEY` - +
+Q：什么是`AZURE_RESOURCE_ID`，`AZURE_MODEL_DEPLOYMENT`，`AZURE_API_KEY` A: 可以在Azure的管理门户里查找，具体见下图标注 ![resource-and-model](./resource-and-model.jpg) +
-Q: 如何支持GPT-4 - +
+Q: 如何支持GPT-4 A: 要使用GPT-4，请使用下列格式的key: `AZURE_RESOURCE_ID:gpt-3.5-turbo|AZURE_MODEL_DEPLOYMENT,gpt-4|AZURE_MODEL_DEPLOYMENT,gpt-4-32k|AZURE_MODEL_DEPLOYMENT:AZURE_API_KEY:AZURE_API_VERSION` +
# 贡献代码方式 diff --git a/src/pages/api/chat/completions.ts b/src/pages/api/chat/completions.ts index 065cd56..16f1206 100644 --- a/src/pages/api/chat/completions.ts +++ b/src/pages/api/chat/completions.ts @@ -7,7 +7,7 @@ logger.add(new logger.transports.Console({ format: logger.format.simple() })); -const DEFAULT_API_VERSION = '2023-03-15-preview' +const DEFAULT_API_VERSION = '2023-05-15' const handler = async (req: NextApiRequest, res: NextApiResponse) => { if (req.method !== 'POST') {