Streaming - OpenModex

Overview

Streaming allows you to receive response tokens as they’re generated, rather than waiting for the complete response. This dramatically improves perceived latency for your users.

When to Use Streaming

Chat interfaces — show typing indicators and real-time text
Long responses — don’t make users wait for the full response
Code generation — display code as it’s written

How It Works

Set stream: true in your request
OpenModex opens an SSE (Server-Sent Events) connection
Tokens are sent as data: events as they’re generated
The stream ends with data: [DONE]

Examples

const stream = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Tell me a story.' }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Tell me a story."}],
    stream=True,
)

for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

stream, _ := client.Chat.Completions.CreateStream(ctx, &openmodex.ChatCompletionParams{
    Model:    "gpt-4o",
    Messages: []openmodex.ChatMessage{{Role: "user", Content: "Tell me a story."}},
})

for chunk, err := range stream.Iter() {
    if err != nil { break }
    fmt.Print(chunk.Choices[0].Delta.Content)
}

import { useChat } from '@openmodex/react';

function Chat() {
  const { messages, input, setInput, sendMessage, isLoading } = useChat({
    apiKey: 'omx_sk_...',
    model: 'gpt-4o',
  });

  return (
    <div>
      {messages.map((m) => (
        <div key={m.id}>{m.role}: {m.content}</div>
      ))}
      <input value={input} onChange={(e) => setInput(e.target.value)} />
      <button onClick={() => sendMessage()}>Send</button>
    </div>
  );
}

Streaming + Fallbacks

Streaming works seamlessly with fallbacks. If the primary model fails before streaming starts, OpenModex automatically retries with the fallback model:

const stream = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }],
  stream: true,
  routing: {
    fallback: ['claude-3.5-sonnet'],
  },
});