# swoole-ai

**Repository Path**: cffycls/swoole-ai

## Basic Information

- **Project Name**: swoole-ai
- **Description**: swoole ai调用服务
- **Primary Language**: PHP
- **License**: MulanPSL-2.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2023-10-18
- **Last Updated**: 2024-05-26

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# swoole-ai服务

文档地址: [https://doc.swoole.com/@swoole-ai/chat.html](https://doc.swoole.com/@swoole-ai/chat.html)

>下文使用结果：为代码在linux（WSL）上执行返回，win下无返回和报错。

## 1. api返回测试
- demo/demo.php

```shell
# $messages[] = ["role" => "user", "content" => "你是谁呀"];
$chunk = 
{
    "data": {
        "id": "chatcmpl-8ArnSGCQ6gLWXOoPu9D2UDCuCq2AL",
        "object": "chat.completion",
        "created": 1697600766,
        "model": "gpt-3.5-turbo-0613",
        "choices": [
            {
                "index": 0,
                "message": {
                    "role": "assistant",
                    "content": "我是一个AI助手，被设计用来提供帮助和回答问题。请问有什么我可以帮助你的吗？"
                },
                "finish_reason": "stop"
            }
        ],
        "usage": {
            "prompt_tokens": 13,
            "completion_tokens": 42,
            "total_tokens": 55
        }
    },
    "code": 0,
    "message": ""
}

$res = $chunk['data']['choices'];
$data = array_column($res, 'message');
// AI返回`message`格式，如果是多个、可以点击“换一个”
[
    {
        "role": "assistant",
        "content": "我是一个AI助手，被设计用来提供帮助和回答问题。请问有什么我可以帮助你的吗？"
    }
]
```

## 2. 获取可用的模型列表
- demo/apis.php

[模型列表](demo/model-list.json)