63 lines
1.4 KiB
Plaintext
63 lines
1.4 KiB
Plaintext
|
---
|
|||
|
|
title: OpenAI 接入
|
|||
|
|
sidebarTitle: OpenAI
|
|||
|
|
description: 通过 OpenAI 兼容协议接入 GPT 系列模型
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# OpenAI 兼容接入
|
|||
|
|
|
|||
|
|
海宇数科对 OpenAI 官方 SDK 及 HTTP API 提供兼容层，便于现有应用零改造迁移。
|
|||
|
|
|
|||
|
|
## 端点
|
|||
|
|
|
|||
|
|
| 项目 | 值 |
|
|||
|
|
| --- | --- |
|
|||
|
|
| Base URL | `https://api.haiyushuke.com/v1` |
|
|||
|
|
| Chat Completions | `POST /chat/completions` |
|
|||
|
|
| 鉴权 | `Authorization: Bearer <API_KEY>` |
|
|||
|
|
|
|||
|
|
## Node.js（官方 SDK）
|
|||
|
|
|
|||
|
|
```ts
|
|||
|
|
import OpenAI from "openai";
|
|||
|
|
|
|||
|
|
const client = new OpenAI({
|
|||
|
|
apiKey: process.env.HAIYUSHUKE_API_KEY,
|
|||
|
|
baseURL: "https://api.haiyushuke.com/v1",
|
|||
|
|
});
|
|||
|
|
|
|||
|
|
const completion = await client.chat.completions.create({
|
|||
|
|
model: "gpt-4o-mini",
|
|||
|
|
messages: [{ role: "user", content: "Hello" }],
|
|||
|
|
});
|
|||
|
|
|
|||
|
|
console.log(completion.choices[0]?.message?.content);
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## Python
|
|||
|
|
|
|||
|
|
```python
|
|||
|
|
from openai import OpenAI
|
|||
|
|
|
|||
|
|
client = OpenAI(
|
|||
|
|
api_key="YOUR_API_KEY",
|
|||
|
|
base_url="https://api.haiyushuke.com/v1",
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
resp = client.chat.completions.create(
|
|||
|
|
model="gpt-4o-mini",
|
|||
|
|
messages=[{"role": "user", "content": "Hello"}],
|
|||
|
|
)
|
|||
|
|
print(resp.choices[0].message.content)
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## 常用参数
|
|||
|
|
|
|||
|
|
- `temperature`：0–2，控制随机性
|
|||
|
|
- `max_tokens`：最大生成 token
|
|||
|
|
- `stream: true`：开启流式，见 [流式调用](/docs/guides/streaming)
|
|||
|
|
|
|||
|
|
## 模型 ID
|
|||
|
|
|
|||
|
|
请在控制台 **模型广场** 查看当前可用 ID；名称可能随供应商更新，以控制台为准。
|