What happens to my Flowise response if Monetzly is down?

The SDK falls back to yielding your original token stream, so the user still receives a complete Flowise answer — just without ads for that request.

Do I need a manual fallback in Flowise?

The SDK handles fallback automatically, but wrapping the loop in your usual error handling is still good practice.

How-to guide

How to Handle Ad-Injection Errors in Flowise

This guide shows how to handle ad-injection errors in a Flowise app, the goal being to make sure the user still gets a reply if the ad service fails. It builds on the Monetzly server SDK, so the approach is specific to how Flowise produces and streams responses.

Overview

Monetization should never break your Flowise app. The Monetzly SDK is built for this: if the ad service connection fails or errors mid-stream, it falls back to yielding your original, un-injected token stream, so the user still gets a complete answer.

You should still wrap the injection loop in your normal error handling so a failure degrades to a plain Flowise response rather than a broken request.

Flowise apps are usually built for visual chatbot building, no-code RAG, and prototyping agent flows, so handle ad-injection errors typically comes up while a user is mid-conversation, the moment where monetization has to be additive rather than disruptive.

How this works on Flowise

Flowise runs on Node, so the Monetzly SDK can live in the layer that consumes a flow's prediction stream. Call the Flowise prediction API with streaming enabled, adapt its SSE token events to { content }, and pass them through sdk.inject() before relaying to your users. Confirm the streaming response shape for your Flowise version / deployment.

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

Steps

Wrap the injection loop in your standard Flowise error handling.
Rely on the SDK's automatic fallback to the original stream on ad-service failure.
Log injection failures so you can monitor fill and uptime separately from your model.

Integration snippet

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

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

// TODO_VERIFY: adapt to your Flowise streaming prediction response shape.
async function* flowiseChunks() {
  const res = await fetch(`${FLOWISE_URL}/api/v1/prediction/${flowId}`, {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ question, streaming: true }),
  });
  for await (const token of parseSSE(res.body!)) yield { content: token };
}

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