1.请求地址：https://gpt.bcwhkj.cn/api/v2.Gptliu/search   

2.请求方式: POST  

3.body格式：json

4.请求内容（sse 流式请求，输出效果较好，响应速度快）（非流式请求，可不加stream这一行）：

{
       "messages" : [{"role":"user","content":"你是谁?"}],
       "model": "gpt-3.5-turbo",
       "stream":true //非SSE流式请求，这一行可不加
}

5.请求头

{
    "Content-Type": application/json,
    "Authorization": "Bearer 这段中文换成你自己的TOKEN（注意前面有个英文空格需保留）"
}

token获取方式：访问公众号《冰橙文化科技》进入菜单冰橙GPT后，访问右上角 / 个人（首次访问免费赠送10000字符，可通过充值增加字符数）可查看 token

SSE流式请求与非流式请求的区别：
    流式POST请求：内容将进行逐家响应和返回，响应速度快。
    普通POST请求：将等待OPENAI的CHATGPT官方接口全部内容都响应完成后，服务器这边才会将内容将通过接口回复给前端，速度较慢。

也可通过微信扫以下图片进入：

5.响应体格式：json

6.响应内容（非流式请求时的响应内容）：

{
    "id": "chatcmpl-77dQj73rIl0GJyTpAH4QlcSnhOFKp",
    "object": "chat.completion",
    "created": 1682054221,
    "model": "gpt-3.5-turbo-0301",
    "usage": {
        "prompt_tokens": 13,
        "completion_tokens": 30,
        "total_tokens": 43
    },
    "choices": [
        {
            "message": {
                "role": "assistant",
                "content": "我是一个人工智能语言模型，可以根据用户提供的输入进行回答和交流。"
            },
            "finish_reason": "stop",
            "index": 0
        }
    ]
}

6.响应内容（流式请求时的响应内容）：

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"role":"assistant"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"我"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"是"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"一个"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"AI"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"语"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"言"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"模"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"型"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"，"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"专"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"门"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"用"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"来"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"回"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"答"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"问题"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"和"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"提"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"供"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"帮"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"助"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"的"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{"content":"。"},"index":0,"finish_reason":null}]}

data: {"id":"chatcmpl-783jPdq1a1ZG6KQc9pq98FDRSqNmp","object":"chat.completion.chunk","created":1682155323,"model":"gpt-3.5-turbo-0301","choices":[{"delta":{},"index":0,"finish_reason":"stop"}]}

data: [DONE]

特别说明【连续对话功能】：

如果需要有上下文语境，请把之前问的问题和答案一起通过Q参数传过来，其中问题和答案前面分别加上“ Q:” 和 “ A:”参数 ，Q和A前面有空格，举例：

Q = "你好！"

A : 你好，有什么可以帮助你的。

Q: "今天天气怎么样？"

那么第二次提交带上之前的问题和答案，请求体里面的Q就是：

keyword = " Q:你好！ A:你好，有什么可以帮助你的。 Q:今天天气怎么样？"

JS方法如下：

keyword='';                
that.list={ 　　
    wen:'老婆和妈妈同时掉水里，我要先救谁？', 　　
    da:'这种情况下，是理所当然应该先救妈妈的。救人的原则是先救生命危险的人，有可能先救老婆，这取决于老婆和妈妈的实际情况，而且也要考虑到逃生的可能性。假如老婆游泳能力很强，可能先救老婆，能在短时间内将她救出水面，否则，先救妈妈也是明智之举。 '
};        

//新问题
newQ:'我不同意？';        

//将之前的所有问答列表进行循环
that.list.forEach((v,k)=>{　　
    //将问和答案组合，<|endoftext|>是用于给OPENAI官方接口进行分段识别的　　
    keyword=keyword+' Q: '+v.wen + ' A: '+v.da+'。 <|endoftext|> ';
})        

//将新的问题组合　　        
keyword=keyword+'Q: '+newQ + 'A: ';

这样获取的答案就是支持上下文语境了哈～