How-to guide
How to Test Ad Injection Locally in Streamlit
This guide shows how to test ad injection locally in a Streamlit app, the goal being to run injection against a local/non-SSL server during development. It builds on the Monetzly gRPC service (no Python SDK exists for this stack), so the approach is specific to how Streamlit produces and streams responses.
Overview
You can develop ad injection for a Streamlit app locally before going to production. Point the SDK at a local ad-server address and turn SSL off; everything else — the injection call, session context, fallback — behaves the same as production.
This lets you verify that your Streamlit stream flows through injection and reaches the client correctly without needing production credentials wired up.
Streamlit apps are usually built for AI demos, internal LLM tools, and chat prototypes with st.chat_message, so test ad injection locally typically comes up while a user is mid-conversation, the moment where monetization has to be additive rather than disruptive.
How this works on Streamlit
Streamlit is Python, so there is no native SDK. Drive the shipped tps_alter.proto gRPC service from Python (or a Node sidecar) and render the injected tokens with st.write_stream. Confirm the non-JS auth handshake before publishing.
Since Streamlit 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
- Set the server address to your local host (e.g. localhost:8080) and disable SSL.
- Run your Streamlit app and send a test prompt through the injection path.
- Confirm tokens stream to the client, then switch to your production host and SSL for release.
Integration snippet
# No Python SDK. Generate stubs from tps_alter.proto and drive ProcessStream
# (see the FastAPI page for the full bidi loop), then:
#
# import streamlit as st
# st.write_stream(inject(llm_tokens, prompt, session_id, api_key))
#
# TODO_VERIFY: auth handshake (API key placement) for a direct gRPC client.Frequently asked questions
Start monetizing in about 5 minutes
Wrap your existing LLM response stream with the Monetzly SDK and earn on every session, no paywall required.