How to beginner · 3 min read

LangChain chatbot with message history

Q: LangChain chatbot with message history

Use LangChain with the ChatOpenAI class to build a chatbot that maintains message history by storing and passing previous messages in a ConversationBufferMemory. This enables context-aware conversations with models like gpt-4o.

Quick answer

Use LangChain with the ChatOpenAI class to build a chatbot that maintains message history by storing and passing previous messages in a ConversationBufferMemory. This enables context-aware conversations with models like gpt-4o.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install langchain_openai langchain_community

Setup

Install the required packages and set your OpenAI API key as an environment variable.

Install LangChain OpenAI and community packages:

bash

pip install langchain_openai langchain_community

Step by step

This example shows how to create a LangChain chatbot with message history using ConversationBufferMemory to keep track of the conversation context.

python

import os
from langchain_openai import ChatOpenAI
from langchain_community.memory import ConversationBufferMemory
from langchain_core.chains import ConversationChain

# Initialize the chat model
chat = ChatOpenAI(model="gpt-4o", temperature=0.7, api_key=os.environ["OPENAI_API_KEY"])

# Set up memory to store conversation history
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)

# Create the conversation chain with memory
conversation = ConversationChain(llm=chat, memory=memory)

# Simulate a chat session
print("User: Hello, who won the world series in 2023?")
response1 = conversation.invoke({"input": "Hello, who won the world series in 2023?"})
print("Bot:", response1["response"])

print("User: Where was it played?")
response2 = conversation.invoke({"input": "Where was it played?"})
print("Bot:", response2["response"])

output

User: Hello, who won the world series in 2023?
Bot: The Texas Rangers won the 2023 World Series.
User: Where was it played?
Bot: The 2023 World Series was played at Globe Life Field in Arlington, Texas.

Common variations

You can customize your chatbot by:

Using ChatAnthropic for Anthropic Claude models.
Switching to async calls with conversation.invoke_async().
Using different memory types like ConversationSummaryMemory for summarizing long chats.
Changing the model to gpt-4o-mini for faster, cheaper responses.

python

from langchain_anthropic import ChatAnthropic
import asyncio

# Async example with Anthropic Claude
async def async_chat():
    chat = ChatAnthropic(model="claude-3-5-sonnet-20241022", api_key=os.environ["ANTHROPIC_API_KEY"])
    memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
    conversation = ConversationChain(llm=chat, memory=memory)
    response = await conversation.invoke_async({"input": "Hello!"})
    print(response["response"])

asyncio.run(async_chat())

output

Hello! How can I assist you today?

Troubleshooting

If you get an authentication error, verify your OPENAI_API_KEY environment variable is set correctly.
If the chatbot forgets context, ensure ConversationBufferMemory is properly passed to the ConversationChain.
For rate limits, reduce max_tokens or switch to a smaller model like gpt-4o-mini.

✅

Key Takeaways

Use ConversationBufferMemory in LangChain to maintain chat history for context.
Pass the memory object to ConversationChain to enable stateful conversations.
You can switch models or SDKs easily while keeping the same memory pattern.
Async invocation is supported for scalable chatbot applications.
Always set your API key securely via environment variables.

Verified 2026-04 · gpt-4o, gpt-4o-mini, claude-3-5-sonnet-20241022

Verify ↗