Streaming Responses
Handle streaming responses for real-time chat output
Streaming Responses
Streaming allows you to receive chat responses token-by-token as they're generated, providing a better user experience for real-time applications.
Basic Streaming
from openai import OpenAI
client = OpenAI(
api_key="sk_your_api_key",
base_url="https://www.novakit.ai/api/v1"
)
stream = client.chat.completions.create(
model="openai/gpt-4o-mini",
messages=[{"role": "user", "content": "Tell me a story"}],
stream=True
)
for chunk in stream:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)import OpenAI from "openai";
const client = new OpenAI({
apiKey: "sk_your_api_key",
baseURL: "https://www.novakit.ai/api/v1",
});
const stream = await client.chat.completions.create({
model: "openai/gpt-4o-mini",
messages: [{ role: "user", content: "Tell me a story" }],
stream: true,
});
for await (const chunk of stream) {
const content = chunk.choices[0]?.delta?.content || "";
process.stdout.write(content);
}curl -N https://www.novakit.ai/api/v1/chat/completions \
-H "Authorization: Bearer sk_your_api_key" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-4o-mini",
"messages": [{"role": "user", "content": "Tell me a story"}],
"stream": true
}'React/Next.js Integration
Using the Vercel AI SDK:
// app/api/chat/route.ts
import { streamText } from "ai";
import { createOpenAI } from "@ai-sdk/openai";
const novakit = createOpenAI({
apiKey: process.env.NOVAKIT_API_KEY,
baseURL: "https://www.novakit.ai/api/v1",
});
export async function POST(req: Request) {
const { messages } = await req.json();
const result = await streamText({
model: novakit("openai/gpt-4o-mini"),
messages,
});
return result.toDataStreamResponse();
}// components/chat.tsx
"use client";
import { useChat } from "ai/react";
export function Chat() {
const { messages, input, handleInputChange, handleSubmit } = useChat();
return (
<div>
{messages.map((m) => (
<div key={m.id}>
{m.role}: {m.content}
</div>
))}
<form onSubmit={handleSubmit}>
<input value={input} onChange={handleInputChange} />
<button type="submit">Send</button>
</form>
</div>
);
}SSE Event Format
The stream consists of Server-Sent Events (SSE):
data: {"id":"chatcmpl-123","choices":[{"delta":{"content":"Hello"}}]}
data: {"id":"chatcmpl-123","choices":[{"delta":{"content":" there"}}]}
data: {"id":"chatcmpl-123","choices":[{"delta":{"content":"!"}}]}
data: [DONE]Handling Stream Completion
from openai import OpenAI
client = OpenAI(
api_key="sk_your_api_key",
base_url="https://www.novakit.ai/api/v1"
)
full_response = ""
stream = client.chat.completions.create(
model="openai/gpt-4o-mini",
messages=[{"role": "user", "content": "Write a haiku"}],
stream=True
)
for chunk in stream:
content = chunk.choices[0].delta.content or ""
full_response += content
print(content, end="", flush=True)
print(f"\n\nFull response: {full_response}")