39 lines
929 B
Plaintext
39 lines
929 B
Plaintext
|
---
|
|||
|
|
title: 流式调用
|
|||
|
|
sidebarTitle: 流式调用
|
|||
|
|
description: SSE 流式输出接入说明
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# 流式调用
|
|||
|
|
|
|||
|
|
在请求体中设置 `"stream": true`，服务端以 SSE 形式返回增量内容。
|
|||
|
|
|
|||
|
|
## cURL
|
|||
|
|
|
|||
|
|
```bash
|
|||
|
|
curl https://api.haiyushuke.com/v1/chat/completions \
|
|||
|
|
-H "Authorization: Bearer YOUR_API_KEY" \
|
|||
|
|
-H "Content-Type: application/json" \
|
|||
|
|
-d '{"model":"gpt-4o-mini","stream":true,"messages":[{"role":"user","content":"写一首四句诗"}]}'
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## OpenAI SDK（Node）
|
|||
|
|
|
|||
|
|
```ts
|
|||
|
|
const stream = await client.chat.completions.create({
|
|||
|
|
model: "gpt-4o-mini",
|
|||
|
|
stream: true,
|
|||
|
|
messages: [{ role: "user", content: "你好" }],
|
|||
|
|
});
|
|||
|
|
|
|||
|
|
for await (const chunk of stream) {
|
|||
|
|
const text = chunk.choices[0]?.delta?.content;
|
|||
|
|
if (text) process.stdout.write(text);
|
|||
|
|
}
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## 注意
|
|||
|
|
|
|||
|
|
- 客户端需正确处理连接中断与超时重试
|
|||
|
|
- 流式场景下计费通常按 **输出 token** 累计，以账单规则为准
|