流式输出接口(Streaming)
POST https://ai.amaxsmp.com/v1/chat/completions流式输出复用对话补全接口,只需将 stream 参数设为 true。响应采用 SSE(Server-Sent Events)格式。
请求示例
cURL
curl https://ai.amaxsmp.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
-d '{
"model": "gpt-4o",
"messages": [
{"role": "user", "content": "写一首关于春天的诗"}
],
"stream": true
}'Python(OpenAI SDK)
from openai import OpenAI
client = OpenAI(
base_url="https://ai.amaxsmp.com/v1",
api_key="sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
)
stream = client.chat.completions.create(
model="gpt-4o",
messages=[
{"role": "user", "content": "写一首关于春天的诗"}
],
stream=True
)
for chunk in stream:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="")JavaScript
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://ai.amaxsmp.com/v1",
apiKey: "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
});
const stream = await client.chat.completions.create({
model: "gpt-4o",
messages: [
{ role: "user", content: "写一首关于春天的诗" },
],
stream: true,
});
for await (const chunk of stream) {
if (chunk.choices[0]?.delta?.content) {
process.stdout.write(chunk.choices[0].delta.content);
}
}SSE 数据格式
流式响应中每条数据以 data: 开头:
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1710000000,"model":"gpt-4o","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1710000000,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":"春"},"finish_reason":null}]}
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1710000000,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":"天"},"finish_reason":null}]}
...
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1710000000,"model":"gpt-4o","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
data: [DONE]| 字段 | 说明 |
|---|---|
choices[].delta.role | 仅第一个 chunk 包含,值为 assistant |
choices[].delta.content | 流式输出的文本片段 |
choices[].finish_reason | 最后一个 chunk 为 stop / length,其余为 null |
[DONE] | 流结束标记 |