cogrow-protean-streamlit 0.0.1

The official Protean Streamlit library

Protean SDK Streamlit

The CoGrow Protean Streamlit library provides functionality that simplifies integration of Streamlit applications with Protean platform.

Installation

# install from PyPI
pip install cogrow-protean-streamlit

Protean Authenticator

ProteanAuthenticator allows Streamlit applications to leverage Protean platform authentication using OAuth2 Resource Server pattern.

Usage

Using ProteanAuthenticator is as simple as importing the module, initializing an instance with the OAuth2 issuer URI and calling authenticate to verify logged-in user's credentials:

import streamlit as st

from protean_streamlit import ProteanAuthenticator

protean_authenticator = ProteanAuthenticator("https://keycloak.cogrow.tech/realms/cogrow")
protean_authenticator.authenticate()
if protean_authenticator.is_logged_in:
    st.title("Protean Streamlit App")

You could use Protean bearer token to authenticate and access all Protean platform APIs:

import streamlit as st
from openai import OpenAI

from protean import Protean
from protean_streamlit import ProteanAuthenticator

protean_authenticator = ProteanAuthenticator("https://keycloak.cogrow.tech/realms/cogrow")
protean_authenticator.authenticate()

if protean_authenticator.is_logged_in:
    st.title("💬 Chatbot")

    # Use Protean APIs to fetch the user profile details
    protean_client = Protean(base_url=st.context.headers.get('Origin'), api_key=protean_authenticator.bearer_token)
    user_profile = protean_client.user.get_user_profile()
    with st.sidebar:
        st.markdown(f"### 👤 Logged in as: [{user_profile.fullname}](mailto:{user_profile.email})")

    if "messages" not in st.session_state:
        st.session_state["messages"] = [{"role": "assistant", "content": "How can I help you?"}]

    for msg in st.session_state.messages:
        st.chat_message(msg["role"]).write(msg["content"])

    if prompt := st.chat_input():
        client = OpenAI(api_key=protean_authenticator.bearer_token, base_url=f"{st.context.headers.get('Origin')}/api/inference/text")
        st.session_state.messages.append({"role": "user", "content": prompt})
        st.chat_message("user").write(prompt)
        response = client.chat.completions.create(model="llama-3.2-1b-instruct", messages=st.session_state.messages)
        msg = response.choices[0].message.content
        st.session_state.messages.append({"role": "assistant", "content": msg})
        st.chat_message("assistant").write(msg)