code with keith
HomeAboutBlogProjects
← PreviousNext →

Module 1 - Lesson 3e: Streaming Responses

Real-time output with streaming responses.

Published: 1/3/2026

Example 5: Streaming Responses

Streaming allows you to receive responses in real-time as the AI generates them, rather than waiting for the complete response.

What It Does

Enables streaming mode so you can display text as it's generated, creating a more interactive experience (like ChatGPT).

Code Snippet

Create src/stream-prompt.ts:

import OpenAI from "openai";
import dotenv from "dotenv";

dotenv.config();
const openai = new OpenAI();

async function streamPrompt(): Promise<void> {
  try {
    console.log("Testing OpenAI connection...");

    // Enable streaming with stream: true
    const response = await openai.responses.create({
      model: "gpt-5-nano",
      input: [
        {
          role: "system",
          content:
            "You are a helpful travel assistant. Provide detailed travel suggestions based on user preferences and give a guide to the destination and include distance from the airport.",
        },
        {
          role: "user",
          content:
            "Suggest a travel destination within Europe where there is a Christmas market that is famous but is not in a big city. I would like to go somewhere that is less than 2 hours from a major airport and has good public transport links.",
        },
      ],
      stream: true, // Enable streaming
    });

    // Variables to collect streaming data
    let finalResponse = "";
    let usageInfo = null;

    console.log("✅ Stream Prompt Success!");
    console.log("---------Streaming event data start-------");

    // Iterate over streaming events
    for await (const event of response) {
      console.log(event);

      // Capture the final text when done
      if (event.type === "response.output_text.done") {
        finalResponse = event.text;
      }

      // Capture usage info when completed
      if (event.type === "response.completed") {
        usageInfo = event.response.usage;
      }
    }

    console.log("---------Streaming event data end-------");
    console.log("Final Response:", finalResponse);
    console.log("Tokens used:");
    console.dir(usageInfo, { depth: null });
    console.log("✅ Stream Prompt Completed!");
  } catch (error) {
    if (error instanceof OpenAI.APIError) {
      console.log("❌ API Error:", error.status, error.message);
    } else if (error instanceof Error) {
      console.log("❌ Error:", error.message);
    }
  }
}

streamPrompt().catch(console.error);

Run It

pnpm tsx src/stream-prompt.ts

Key Points

  • Real-time output: See text as it's generated
  • Better UX: Users don't wait for complete response
  • Event-based: Process events as they arrive
  • Use case: Chat interfaces, long responses, interactive apps

Streaming Event Types

// Text chunk events
event.type === "response.output_text.delta"; // Partial text
event.type === "response.output_text.done"; // Complete text

// Completion events
event.type === "response.completed"; // Full response done
← PreviousNext →