How to Pass Session Context to Ads in Vercel AI SDK (Next.js)

Overview

Ad relevance in a Vercel AI SDK (Next.js) 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.

Vercel AI SDK (Next.js) apps are usually built for streaming chat UIs, Next.js AI apps, and edge/serverless LLM routes, 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 Vercel AI SDK (Next.js)

Vercel's streamText() exposes a textStream of plain strings. Wrap it in an async generator that yields { content: text } and pass that into sdk.inject(); then stream the injected tokens back in your Route Handler Response. Both APIs are documented, so this is a direct fit.

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

Steps

1. Choose a stable session id for the conversation (reuse your Vercel AI SDK (Next.js) session or thread id).
2. Pass the current user prompt on each injection call.
3. Add optional metadata (topic, user type) to sharpen targeting.

Integration snippet

import { streamText } from "ai";
import { google } from "@ai-sdk/google";
import { MonetzlySDK } from "@monetzly/server-sdk";

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

export async function POST(req: Request) {
  const { prompt } = await req.json();
  await sdk.connect();
  const { textStream } = streamText({ model: google("gemini-2.0-flash"), prompt });

  // Adapt Vercel's string stream to Monetzly's TokenChunk shape.
  async function* asChunks() {
    for await (const text of textStream) yield { content: text };
  }

  const enc = new TextEncoder();
  const body = new ReadableStream({
    async start(c) {
      for await (const t of sdk.inject(asChunks(), { prompt }))
        c.enqueue(enc.encode(t.content ?? ""));
      await sdk.disconnect();
      c.close();
    },
  });
  return new Response(body, { headers: { "Content-Type": "text/plain; charset=utf-8" } });
}

Frequently asked questions

Related