# go-llm-proxy

**Repository Path**: ppnt/go-llm-proxy

## Basic Information

- **Project Name**: go-llm-proxy
- **Description**: 大模型代理服务
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 1
- **Created**: 2024-05-15
- **Last Updated**: 2024-11-23

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# go-llm-proxy

## 简介

`go-llm-proxy` 是一个用于代理 OpenAI 请求的服务。它接收客户端发起的 OpenAI API 请求，并将其转发至 OpenAI 官方服务器。本项目仅作为代理转发，不进行任何数据存储。

**注意**：您需要自行申请 OpenAI 的 API 密钥。

## 快速上手

以下是部署后的示例地址：`https://llm.maxkb.ai`

使用 `curl` 发送请求示例：

```shell
curl --location --request POST 'https://llm.maxkb.ai/openai/v1/chat/completions' \
--header 'Authorization: Bearer YOUR_OPENAI_API_KEY' \
--header 'Content-Type: application/json' \
--data-raw '{
    "messages": [
        {
            "role": "system",
            "content": "Just say hi"
        }
    ],
    "model": "gpt-4o-mini",
    "stream": true
}'
```

**注意**：请将 `YOUR_OPENAI_API_KEY` 替换为您的实际 API 密钥。

## 构建

使用 Go 语言编译本项目：

```sh
go build
```

## 运行

编译后，运行生成的可执行文件：

```sh
./go-llm-proxy
```

## 测试

使用 `curl` 测试代理服务是否能正确转发请求并显示返回数据：

```sh
curl --location --request POST 'http://127.0.0.1:8888/openai/v1/chat/completions' \
--header 'Authorization: Bearer YOUR_OPENAI_API_KEY' \
--header 'Content-Type: application/json' \
--data-raw '{
    "messages": [
        {
            "role": "system",
            "content": "Just say hi"
        }
    ],
    "model": "gpt-3.5-turbo",
    "stream": true
}'
```

**示例响应**：

```shell
data:{"id":"chatcmpl-9P3fvvyk4IuCprCnvMytoKN8UtskC","object":"chat.completion.chunk","created":1715759355,"model":"gpt-3.5-turbo-0125","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}

data:{"id":"chatcmpl-9P3fvvyk4IuCprCnvMytoKN8UtskC","object":"chat.completion.chunk","created":1715759355,"model":"gpt-3.5-turbo-0125","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Hi"},"logprobs":null,"finish_reason":null}]}

data:{"id":"chatcmpl-9P3fvvyk4IuCprCnvMytoKN8UtskC","object":"chat.completion.chunk","created":1715759355,"model":"gpt-3.5-turbo-0125","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}]}

data:{"id":"chatcmpl-9P3fvvyk4IuCprCnvMytoKN8UtskC","object":"chat.completion.chunk","created":1715759355,"model":"gpt-3.5-turbo-0125","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" How"},"logprobs":null,"finish_reason":null}]}

data:{"id":"chatcmpl-9P3fvvyk4IuCprCnvMytoKN8UtskC","object":"chat.completion.chunk","created":1715759355,"model":"gpt-3.5-turbo-0125","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" can"},"logprobs":null,"finish_reason":null}]}

data:{"id":"chatcmpl-9P3fvvyk4IuCprCnvMytoKN8UtskC","object":"chat.completion.chunk","created":1715759355,"model":"gpt-3.5-turbo-0125","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" I"},"logprobs":null,"finish_reason":null}]}

data:{"id":"chatcmpl-9P3fvvyk4IuCprCnvMytoKN8UtskC","object":"chat.completion.chunk","created":1715759355,"model":"gpt-3.5-turbo-0125","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" assist"},"logprobs":null,"finish_reason":null}]}

data:{"id":"chatcmpl-9P3fvvyk4IuCprCnvMytoKN8UtskC","object":"chat.completion.chunk","created":1715759355,"model":"gpt-3.5-turbo-0125","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" you"},"logprobs":null,"finish_reason":null}]}

data:{"id":"chatcmpl-9P3fvvyk4IuCprCnvMytoKN8UtskC","object":"chat.completion.chunk","created":1715759355,"model":"gpt-3.5-turbo-0125","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" today"},"logprobs":null,"finish_reason":null}]}

data:{"id":"chatcmpl-9P3fvvyk4IuCprCnvMytoKN8UtskC","object":"chat.completion.chunk","created":1715759355,"model":"gpt-3.5-turbo-0125","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"?"},"logprobs":null,"finish_reason":null}]}

data:{"id":"chatcmpl-9P3fvvyk4IuCprCnvMytoKN8UtskC","object":"chat.completion.chunk","created":1715759355,"model":"gpt-3.5-turbo-0125","system_fingerprint":null,"choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}

data:[DONE]
```

## 支持的模型

目前支持的模型包括：[OpenAI 模型列表](https://platform.openai.com/docs/models)

请根据需要配置代理连接的具体模型。

## 贡献

欢迎社区开发者贡献代码，增加新功能或改进现有功能。请提交 Pull Requests 至我们的 GitHub 仓库。

## 许可证

本项目采用 MIT 许可证，详见 [`LICENSE`](LICENSE) 文件。

## 安全提示

请勿在公开场合（如 GitHub 仓库）暴露您的 OpenAI API 密钥。确保妥善保管您的密钥，以防止滥用。