What session id should I use in LlamaIndex.TS?

Any stable identifier for the conversation — reuse your existing LlamaIndex.TS session or thread id so turns are grouped correctly.

Is passing the prompt required for LlamaIndex.TS?

It is optional but strongly recommended: the prompt is what makes the injected ad contextually relevant to the current turn.

How-to guide

How to Pass Session Context to Ads in LlamaIndex.TS

This guide shows how to pass session context to ads in a LlamaIndex.TS app, the goal being to supply session id, prompt, and metadata so injected ads are relevant. It builds on the Monetzly server SDK, so the approach is specific to how LlamaIndex.TS produces and streams responses.

Overview

Ad relevance in a LlamaIndex.TS app comes from context. When you inject, you pass a session id, the live prompt, and optional metadata — that is what lets Monetzly match a recommendation to what the user is actually asking about in that turn.

The session id groups turns from the same conversation; the prompt drives per-turn relevance; metadata carries anything extra you want to target on. All are supplied per injection call.

LlamaIndex.TS apps are usually built for RAG over private docs, knowledge-base search, and structured data QA, so pass session context to ads 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

Choose a stable session id for the conversation (reuse your LlamaIndex.TS session or thread id).
Pass the current user prompt on each injection call.
Add optional metadata (topic, user type) to sharpen targeting.

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();