In this tutorial, we’ll walk through the steps to create a Chainlit application integrated with LangChain.

Preview of what you will build

​
Prerequisites

Before getting started, make sure you have the following:
  • A working installation of Chainlit
  • The LangChain package installed
  • An OpenAI API key
  • Basic understanding of Python programming

​
Step 1: Create a Python file

Create a new Python file named app.py in your project directory. This file will contain the main logic for your LLM application.

​
Step 2: Write the Application Logic

In app.py, import the necessary packages and define one function to handle a new chat session and another function to handle messages incoming from the UI.

​
With LangChain

Let’s go through a small example.
If your agent/chain does not have an async implementation, fallback to the sync implementation.
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
from langchain.schema import StrOutputParser
from langchain.schema.runnable import Runnable
from langchain.schema.runnable.config import RunnableConfig
from typing import cast

import chainlit as cl


@cl.on_chat_start
async def on_chat_start():
    model = ChatOpenAI(streaming=True)
    prompt = ChatPromptTemplate.from_messages(
        [
            (
                "system",
                "You're a very knowledgeable historian who provides accurate and eloquent answers to historical questions.",
            ),
            ("human", "{question}"),
        ]
    )
    runnable = prompt | model | StrOutputParser()
    cl.user_session.set("runnable", runnable)


@cl.on_message
async def on_message(message: cl.Message):
    runnable = cast(Runnable, cl.user_session.get("runnable"))  # type: Runnable

    msg = cl.Message(content="")

    async for chunk in runnable.astream(
        {"question": message.content},
        config=RunnableConfig(callbacks=[cl.LangchainCallbackHandler()]),
    ):
        await msg.stream_token(chunk)

    await msg.send()
This code sets up an instance of Runnable with a custom ChatPromptTemplate for each chat session. The Runnable is invoked everytime a user sends a message to generate the response. The callback handler is responsible for listening to the chain’s intermediate steps and sending them to the UI.

​
With LangGraph

from typing import Literal
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import ToolNode
from langchain.schema.runnable.config import RunnableConfig
from langchain_core.messages import HumanMessage

import chainlit as cl

@tool
def get_weather(city: Literal["nyc", "sf"]):
    """Use this to get weather information."""
    if city == "nyc":
        return "It might be cloudy in nyc"
    elif city == "sf":
        return "It's always sunny in sf"
    else:
        raise AssertionError("Unknown city")


tools = [get_weather]
model = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)
final_model = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)

model = model.bind_tools(tools)
# NOTE: this is where we're adding a tag that we'll can use later to filter the model stream events to only the model called in the final node.
# This is not necessary if you call a single LLM but might be important in case you call multiple models within the node and want to filter events
# from only one of them.
final_model = final_model.with_config(tags=["final_node"])
tool_node = ToolNode(tools=tools)

from typing import Annotated
from typing_extensions import TypedDict

from langgraph.graph import END, StateGraph, START
from langgraph.graph.message import MessagesState
from langchain_core.messages import BaseMessage, SystemMessage, HumanMessage


def should_continue(state: MessagesState) -> Literal["tools", "final"]:
    messages = state["messages"]
    last_message = messages[-1]
    # If the LLM makes a tool call, then we route to the "tools" node
    if last_message.tool_calls:
        return "tools"
    # Otherwise, we stop (reply to the user)
    return "final"


def call_model(state: MessagesState):
    messages = state["messages"]
    response = model.invoke(messages)
    # We return a list, because this will get added to the existing list
    return {"messages": [response]}


def call_final_model(state: MessagesState):
    messages = state["messages"]
    last_ai_message = messages[-1]
    response = final_model.invoke(
        [
            SystemMessage("Rewrite this in the voice of Al Roker"),
            HumanMessage(last_ai_message.content),
        ]
    )
    # overwrite the last AI message from the agent
    response.id = last_ai_message.id
    return {"messages": [response]}


builder = StateGraph(MessagesState)

builder.add_node("agent", call_model)
builder.add_node("tools", tool_node)
# add a separate final node
builder.add_node("final", call_final_model)

builder.add_edge(START, "agent")
builder.add_conditional_edges(
    "agent",
    should_continue,
)

builder.add_edge("tools", "agent")
builder.add_edge("final", END)

graph = builder.compile()

@cl.on_message
async def on_message(msg: cl.Message):
    config = {"configurable": {"thread_id": cl.context.session.id}}
    cb = cl.LangchainCallbackHandler()
    final_answer = cl.Message(content="")
    
    for msg, metadata in graph.stream({"messages": [HumanMessage(content=msg.content)]}, stream_mode="messages", config=RunnableConfig(callbacks=[cb], **config)):
        if (
            msg.content
            and not isinstance(msg, HumanMessage)
            and metadata["langgraph_node"] == "final"
        ):
            await final_answer.stream_token(msg.content)

    await final_answer.send()

​
Step 3: Run the Application

To start your app, open a terminal and navigate to the directory containing app.py. Then run the following command: 
chainlit run app.py -w
The -w flag tells Chainlit to enable auto-reloading, so you don’t need to restart the server every time you make changes to your application. Your chatbot UI should now be accessible at http://localhost:8000.
When using LangChain, prompts and completions are not cached by default. To enable the cache, set the cache=true in your chainlit config file.