What session id should I use in Streamlit?

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

Is passing the prompt required for Streamlit?

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 Streamlit

This guide shows how to pass session context to ads in a Streamlit app, the goal being to supply session id, prompt, and metadata so injected ads are relevant. 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

Ad relevance in a Streamlit 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.

Streamlit apps are usually built for AI demos, internal LLM tools, and chat prototypes with st.chat_message, 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 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

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

Integration snippet

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

# 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.