Where do I put my Monetzly API key in a OpenAI Assistants API app?

In an environment variable (e.g. MONETZLY_API_KEY) read at runtime — never hard-coded in source or shipped to the client.

Do I open a new connection per request in OpenAI Assistants API?

Open a connection when a request begins and close it when the response stream finishes. The SDK manages reconnection internally.

How-to guide

How to Set Up the Monetzly SDK in OpenAI Assistants API

This guide shows how to set up the Monetzly SDK in a OpenAI Assistants API app, the goal being to get the SDK configured and connected before injecting any ads. It builds on the Monetzly server SDK, so the approach is specific to how OpenAI Assistants API produces and streams responses.

Overview

Before you can monetize a OpenAI Assistants API app, the Monetzly client needs configuring and connecting. This is a one-time setup: an API key, the ad-server address, and SSL settings, then a connection you open when a request starts and close when it ends.

Keep the API key in an environment variable, never in source. Use a non-SSL localhost address in development and your real ad-server host in production.

OpenAI Assistants API apps are usually built for hosted chat assistants, file-search agents, and tool-calling assistants, so set up the Monetzly SDK typically comes up while a user is mid-conversation, the moment where monetization has to be additive rather than disruptive.

How this works on OpenAI Assistants API

The Node OpenAI SDK streams run/completion events. Map each text delta event to { content: delta } and feed the generator into sdk.inject(). The Monetzly side is standard; the only framework detail to confirm is the exact delta event field for your chosen mode (Assistants run stream vs Chat Completions).

Because Monetzly's inject() accepts any async token stream, the OpenAI Assistants API side of this task is just mapping your output to it, no rewrite of your OpenAI Assistants API model call.

Steps

Install the SDK (or, for a Python OpenAI Assistants API stack, generate gRPC stubs from the shipped tps_alter.proto).
Create a config with your API key, server address, and SSL flag.
Open a connection at the start of a request and close it when the response finishes.

Integration snippet

import OpenAI from "openai";
import { MonetzlySDK } from "@monetzly/server-sdk";

const openai = new OpenAI();
const sdk = new MonetzlySDK({
  apiKey: process.env.MONETZLY_API_KEY!,
  serverAddress: process.env.MONETZLY_SERVER_ADDRESS!,
});
await sdk.connect();

const stream = await openai.chat.completions.create({
  model: "gpt-4o-mini", messages, stream: true,
});

async function* asChunks() {
  // TODO_VERIFY: for the Assistants run stream, read the text delta from the
  // run event instead of choices[0].delta.content.
  for await (const ev of stream) yield { content: ev.choices[0]?.delta?.content ?? "" };
}

for await (const t of sdk.inject(asChunks(), { prompt })) send(t.content ?? "");
await sdk.disconnect();