Does injecting ads change how my LlamaIndex.TS model is called?

No. Your LlamaIndex.TS model call is unchanged; you only wrap the resulting stream, so ad injection is additive rather than a rewrite.

Will the response still stream token by token in LlamaIndex.TS?

Yes. Injection preserves streaming — ads are placed inside the token stream, so the client still receives a live, incremental response.

How-to guide

How to Inject Ads Into a Streaming Response in LlamaIndex.TS

This guide shows how to inject ads into a streaming response in a LlamaIndex.TS app, the goal being to wrap the LLM token stream so contextual ads appear inside the assistant's reply. It builds on the Monetzly server SDK, so the approach is specific to how LlamaIndex.TS produces and streams responses.

Overview

This is the core of monetizing a LlamaIndex.TS app: instead of returning the raw model stream, you pass it through Monetzly, which injects contextual, labelled ads into the token stream and hands you back the enhanced stream to forward to the client.

You keep your existing LlamaIndex.TS model call untouched. Injection is additive — a wrapper around the stream you already produce, keyed on the session and the live prompt so the ad matches what the user is asking about.

LlamaIndex.TS apps are usually built for RAG over private docs, knowledge-base search, and structured data QA, so inject ads into a streaming response typically comes up while a user is mid-conversation, the moment where monetization has to be additive rather than disruptive.

How this works on LlamaIndex.TS

Use the TypeScript edition (LlamaIndex.TS) so you stay in the Node runtime the SDK requires. A streaming chat/query engine yields response chunks; map each chunk's text to { content } and pass into sdk.inject(). Confirm the chunk field name against your LlamaIndex.TS version.

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

Steps

Produce your LlamaIndex.TS response as a token stream as you already do.
Pass that stream into the Monetzly injection call with the session id and prompt.
Forward the enhanced tokens to the client (SSE, WebSocket, or your existing transport).

Integration snippet

import { MonetzlySDK } from "@monetzly/server-sdk";
// import a streaming chat engine from "llamaindex"

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

const stream = await chatEngine.chat({ message, stream: true });

async function* asChunks() {
  // TODO_VERIFY: confirm the text field (e.g. .response / .delta) for your version.
  for await (const chunk of stream) yield { content: chunk.response ?? chunk.delta ?? "" };
}

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