Does injecting ads change how my Flask model is called?

No. Your Flask 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 Flask?

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 Flask

This guide shows how to inject ads into a streaming response in a Flask app, the goal being to wrap the LLM token stream so contextual ads appear inside the assistant's reply. It builds on the Monetzly gRPC service (no Python SDK exists for this stack), so the approach is specific to how Flask produces and streams responses.

Overview

This is the core of monetizing a Flask 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 Flask 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.

Flask apps are usually built for simple LLM web apps, chat endpoints, and prototype APIs, 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 Flask

Same as FastAPI: no Python SDK, so integrate via the shipped tps_alter.proto gRPC service (generate stubs, drive ProcessStream) or a Node sidecar. In Flask, stream the injected tokens back with a generator response. Confirm the non-JS auth handshake before publishing.

Since Flask is a Python stack with no official SDK, this task runs through the shipped tps_alter.proto gRPC service (or a Node sidecar); the auth handshake for a direct client is still TODO_VERIFY.

Steps

Produce your Flask 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

TODO_VERIFY: Flask uses the gRPC proto path, confirm the auth handshake with Monetzly before relying on this in production.

# Generate stubs once from tps_alter.proto (shipped in @monetzly/server-sdk):
#   python -m grpc_tools.protoc -I. --python_out=. --grpc_python_out=. tps_alter.proto
# Then drive TPSAlterService.ProcessStream: StartRequest -> TokenRequest* -> StopRequest,
# reading back injected TokenResponses. See the FastAPI page for the full bidi loop.
# In Flask, yield the injected tokens from a streaming Response.
# TODO_VERIFY: auth handshake (API key placement) for a direct gRPC client.