Add docker compose file and update README (#6)

README.en-US.md

@@ -0,0 +1,70 @@
+# Azure OpenAI Proxy
+
+[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.
+
+## Usage Requirements
+
+You must have an Azure OpenAI account to use the Azure OpenAI Proxy.
+
+## Docker Deployment
+`docker run -d -p 3080:3080 scalaone/azure-openai-proxy`
+
+## Local Running and Testing, Command Line Method
+
+1. Install NodeJS 18.
+2. Clone the code in the command line window.
+3. Run `npm install` to install dependencies.
+4. Run `npm start` to start the application.
+5. Run the script below for testing, replacing `YOUR_RESOURCE_ID`, `YOUR_MODEL_DEPLOYMENT`, and `YOUR_API_KEY` before running it.
+```bash
+curl -X "POST" "http://localhost:3000/v1/chat/completions" \
+-H 'Authorization: YOUR_RESOURCE_ID:YOUR_MODEL_DEPLOYMENT:YOUR_API_KEY' \
+-H 'Content-Type: application/json; charset=utf-8' \
+-d $'{
+  "messages": [
+    {
+      "role": "system",
+      "content": "You are an AI assistant that helps people find information."
+    },
+    {
+      "role": "user",
+      "content": "hi."
+    }
+  ],
+  "temperature": 1,
+  "model": "gpt-3.5-turbo",
+  "stream": false
+}'
+```
+
+## Local Running and Testing, Using WebChat for Streaming Test
+
+1. Clone code in command line window
+2. Update environment variable of OPENAPI_API_KEY on line nine of docker-compose.yml file with `YOUR_RESOURCE_ID:YOUR_MODEL_DEPLOYMENT:YOUR_API_KEY`
+3. Execute build：run docker-compose build
+4. Start service：run docker-compose up -d
+5. Launch `http://localhost:3000`
+
+Frequently Asked Questions
+
+Q：What is `YOUR_RESOURCE_ID`,`YOUR_MODEL_DEPLOYMENT`,`YOUR_API_KEY`?
+
+A：It can be found in azure management portal，see image below for details：
+
+![resource-and-model](./resource-and-model.jpg)
+
+Q：How do I support GPT-4？
+
+A ：To use GPT-4 , please use key format as follows:
+
+`YOUR_RESOURCE_ID:gpt-3.5-turbo|YOUR_MODEL_DEPLOYMENT,gpt-4|YOUR_MODEL_DEPLOYMENT,gpt-4-32k|YOUR_MODEL_DEPLOYMENT:YOUR_API_KEY`
+
+# How To Contribute Code?
+
+Welcome to submit various PRs.
+
+# Disclaimer
+
+This code is for demonstration and testing purposes only.

README.md

@@ -1,54 +1,36 @@
-# Azure-OpenAI-Proxy
+# Azure OpenAI Proxy
 
-Azure-OpenAI-Proxy is an application that serves as a proxy for OpenAI's API. It enables users to request AI-generated text completions for specific prompts, using different models and parameters. The proxy supports GPT-4 models in addition to other available models. It simplifies the interaction with the OpenAI API and helps manage multiple deployments with ease for your AI-based text generation applications.
+[English](./README.en-US.md) | 简体中文
 
-## Installation
+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。
 
-Follow these steps to set up Azure-OpenAI-Proxy:
+## 使用要求
 
-1. Clone the repository:
+必须拥有Azure OpenAI帐户才能使用 Azure OpenAI Proxy。
 
-```
-git clone https://github.com/scalaone/azure-openai-proxy.git
-```
-
-2. Navigate to the project directory:
-
-```
-cd azure-openai-proxy
-```
-
-3. Install the required dependencies:
-
-```
-npm install
-```
+## Docker部署
+`docker run -d -p 3080:3080 scalaone/azure-openai-proxy`
 
-4. Replace the placeholder values in the example request as mentioned in the [Usage section](#usage) with your actual resource ID, deployment IDs, model names, and API key.
+## 本地运行和测试，命令行方式
 
-5. Run the application:
-
-```
-npm run start
-```
-
-The Azure-OpenAI-Proxy will be running on your server and listening for incoming requests.
-
-## Usage
-
-To send a request, use a `curl` command to POST the input data to the application's URL. Replace the placeholder values with your actual resource ID, deployment IDs, model names, and API key.
-
-Example request:
-
-```
-curl -X "POST" "https://openaiproxy2.azurewebsites.net/v1/chat/completions" \
-     -H 'Authorization: Bearer YOUR_RESOURCE_ID:YOUR_MODEL_NAME_IDENTIFIERS:YOUR_API_KEY' \
-     -H 'Content-Type: application/json; charset=utf-8' \
-     -d $'{
+1. 安装 NodeJS 18。
+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`YOUR_RESOURCE_ID`，`YOUR_MODEL_DEPLOYMENT`，`YOUR_API_KEY`替换。
+```bash
+curl -X "POST" "http://localhost:3000/v1/chat/completions" \
+-H 'Authorization: YOUR_RESOURCE_ID:YOUR_MODEL_DEPLOYMENT:YOUR_API_KEY' \
+-H 'Content-Type: application/json; charset=utf-8' \
+-d $'{
   "messages": [
     {
-      "content": "hi",
-      "role": "user"
+      "role": "system",
+      "content": "You are an AI assistant that helps people find information."
+    },
+    {
+      "role": "user",
+      "content": "hi."
     }
   ],
   "temperature": 1,
@@ -57,35 +39,32 @@ curl -X "POST" "https://openaiproxy2.azurewebsites.net/v1/chat/completions" \
 }'
 ```
 
-Replace the following placeholder values:
+## 本地运行和测试，使用WebChat测试streaming
 
-- `YOUR_RESOURCE_ID` with the actual resource ID (e.g., `hai`).
-- `YOUR_MODEL_NAME_IDENTIFIERS` with the actual model and deployment ID mappings (e.g., `gpt-3.5-turbo|gpt-35-turbo,gpt-4|gpt-4,gpt-4-32k|gpt-4-32k`).
-- `YOUR_API_KEY` with your actual API key (e.g., `xxxxxx`).
+1. 克隆代码到命令行窗口
+2. 更新 `docker-compose.yml` 文件中第九行的 `OPENAI_API_KEY` 环境变量为`YOUR_RESOURCE_ID:YOUR_MODEL_DEPLOYMENT:YOUR_API_KEY`
+3. 执行构建：运行 `docker-compose build`
+4. 启动服务：运行 `docker-compose up -d`
+5. 运行`http://localhost:3000`
 
-## Parameters
+常见问题
 
-The request body contains the following parameters:
+Q：什么是`YOUR_RESOURCE_ID`,`YOUR_MODEL_DEPLOYMENT`,`YOUR_API_KEY`
 
-- `messages`: An array of message objects containing `content` and `role` properties. The `content` represents the text input, and the `role` can be one of the following options: `'system'`, `'user'`, or `'assistant'`.
-- `temperature`: Controls the randomness of generated completions. Higher values (e.g., 1) result in more random responses, while lower values (e.g., 0.1) produce more focused and deterministic responses.
-- `model`: Specifies the AI model to be used for generating completions. In the example, it is set to `'gpt-3.5-turbo'`.
-- `stream`: A boolean value indicating whether the response should be streamed.
+A: 可以在Azure的管理门户里查找，具体见下图标注
 
-## License
+![resource-and-model](./resource-and-model.jpg)
 
-This project is licensed under the MIT License. See the [LICENSE](https://choosealicense.com/licenses/mit/) file for details.
+Q: 如何支持GPT-4
 
-## Contributing
+A: 要使用GPT-4, 请使用下列格式的key: 
 
-Contributions to Azure-OpenAI-Proxy are greatly appreciated. To contribute, follow these steps:
+`YOUR_RESOURCE_ID:gpt-3.5-turbo|YOUR_MODEL_DEPLOYMENT,gpt-4|YOUR_MODEL_DEPLOYMENT,gpt-4-32k|YOUR_MODEL_DEPLOYMENT:YOUR_API_KEY`
 
-1. Fork the repository and create your branch.
-2. Make changes or additions to the code.
-3. Commit your changes and raise a Pull Request.
+# 贡献代码方式
 
-Please make sure to follow the project's coding standards and update documentation accordingly.
+欢迎提交各种PR。
 
-For further information, check the [OpenAI API documentation](https://platform.openai.com/docs/api-reference/completions/create).
+# 免责声明
 
-Thank you for your interest in contributing to Azure-OpenAI-Proxy. Your efforts will help improve the project and benefit the community.
+此代码仅供演示和测试目的。

docker-compose.yml

@@ -0,0 +1,25 @@
+version: '3.8'
+
+services:
+  gptlite:
+    image: blrchen/gptlite:main
+    ports:
+      - 3000:3000
+    environment:
+      OPENAI_API_KEY: ${OPENAI_API_KEY}
+      OPENAI_API_BASE_URL: http://azure-openai:3000
+    depends_on:
+      - azure-openai
+    networks:
+      - network
+
+  azure-openai:
+    build:
+      context: .
+    networks:
+      - network
+    restart: unless-stopped
+
+networks:
+  network:
+    driver: bridge