Skip to main content


Streamlit is an open-source Python library that makes it easy to create and share beautiful, custom web apps for machine learning and data science.

This notebook goes over how to store and use chat message history in a Streamlit app. StreamlitChatMessageHistory will store messages in Streamlit session state at the specified key=. The default key is "langchain_messages".

The integration lives in the langchain-community package, so we need to install that. We also need to install streamlit.

pip install -U langchain-community streamlit

You can see the full app example running here, and more examples in

from langchain_community.chat_message_histories import (

history = StreamlitChatMessageHistory(key="chat_messages")

history.add_ai_message("whats up?")

We can easily combine this message history class with LCEL Runnables.

The history will be persisted across re-runs of the Streamlit app within a given user session. A given StreamlitChatMessageHistory will NOT be persisted or shared across user sessions.

# Optionally, specify your own session_state key for storing messages
msgs = StreamlitChatMessageHistory(key="special_app_key")

if len(msgs.messages) == 0:
msgs.add_ai_message("How can I help you?")
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_core.runnables.history import RunnableWithMessageHistory
from langchain_openai import ChatOpenAI

prompt = ChatPromptTemplate.from_messages(
("system", "You are an AI chatbot having a conversation with a human."),
("human", "{question}"),

chain = prompt | ChatOpenAI()
chain_with_history = RunnableWithMessageHistory(
lambda session_id: msgs, # Always return the instance created earlier

Conversational Streamlit apps will often re-draw each previous chat message on every re-run. This is easy to do by iterating through StreamlitChatMessageHistory.messages:

import streamlit as st

for msg in msgs.messages:

if prompt := st.chat_input():

# As usual, new messages are added to StreamlitChatMessageHistory when the Chain is called.
config = {"configurable": {"session_id": "any"}}
response = chain_with_history.invoke({"question": prompt}, config)

View the final app.

Was this page helpful?

You can also leave detailed feedback on GitHub.