# OpenAI

Kamiya API与OpenAI官方API完全兼容，您可以将该接口作为中继直接用于像 [BetterChatGPT](https://github.com/ztjhz/BetterChatGPT) 这样为OpenAI API开发的应用程序。

## Chat Completion

```http
POST https://p0.kamiya.dev/api/openai/chat/completions
```

Stream调用示例(SSE)

```json
{
    "messages": [
        {
          "role":"system",
          "content":"You are ChatGPT, a large language model trained by OpenAI.\nCarefully heed the user's instructions. \nRespond using Markdown."
        },
        {
          "role":"user",
          "content":"你好"
        }
    ],
    "model":"openai:gpt-3.5-turbo",
    "max_tokens":null,
    "temperature":1,
    "presence_penalty":0,
    "top_p":1,
    "frequency_penalty":0,
    "stream":true
}
```

阻塞式调用示例(非SSE)

```json
{
    "messages": [
        {
          "role":"user",
          "content":"Generate a title in less than 6 words for the following message (language: zh-CN):\n\"\"\"\nUser: 你好\nAssistant: 你好！请问有什么我能帮到你的吗？\n\"\"\""
        }
    ],
    "model":"openai:gpt-3.5-turbo",
    "max_tokens":null,
    "temperature":1,
    "presence_penalty":0,
    "top_p":1,
    "frequency_penalty":0
}
```

如需以非Stream(SSE)方式调用，仅支持调用`gpt-3.5-turbo`模型，其余模型均以Stream(SSE)方式提供。

如果您具有相应权限，也可以调用`anthropic:claude-1`等由Anthropic提供的模型，在该API端点下这些模型的响应都被格式化为OpenAI兼容(SSE)。

## 经简化的Chat API

Kamiya同时提供经过简化的Chat API，可按实际需求调用。该API由服务器维护上下文(Context)，Redis缓存时间为48H。

```http
POST https://p0.kamiya.dev/api/openai/chatgpt/conversation
```

请求示例

```json
{
    "content":"你好",
    "conversationId": "e282d7a0-b183-4c7c-ba9c-3559e2af751f" //首次请求（第一条消息）无需携带，后续消息需携带
}
```

Stream(SSE)响应

响应格式与OpenAI Chat Completion一致，在`[DONE]`发送后还会追加一段由Kamiya提供的`kamiyaInfo`，其中包含

```json
{
    "id": "kamiyaInfo",
    "conversationId": "e282d7a0-b183-4c7c-ba9c-3559e2af751f", // 后续消息中需包含的conversationId
    "message": "[DONE]",
    "fullContent": "请问你想要我帮助你什么方面的问题呢？" // 产生计费的完整回复
}
```

使用该API时无需维护上下文，上下文裁剪与窗口控制均有Kamiya完成。


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.kamiya.dev/kamiya-api/openai.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.