Using Buffer Memory with Chat Models

This example covers how to use chat-specific memory classes with chat models. The key thing to notice is that setting returnMessages: true makes the memory return a list of chat messages instead of a string.

tip

See this section for general instructions on installing integration packages.

npm

npm install @langchain/openai

Yarn

yarn add @langchain/openai

pnpm

pnpm add @langchain/openai

import { ConversationChain } from "langchain/chains";
import { ChatOpenAI } from "@langchain/openai";
import {
  ChatPromptTemplate,
  MessagesPlaceholder,
} from "@langchain/core/prompts";
import { BufferMemory } from "langchain/memory";

const chat = new ChatOpenAI({ temperature: 0 });

const chatPrompt = ChatPromptTemplate.fromMessages([
  [
    "system",
    "The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.",
  ],
  new MessagesPlaceholder("history"),
  ["human", "{input}"],
]);

const chain = new ConversationChain({
  memory: new BufferMemory({ returnMessages: true, memoryKey: "history" }),
  prompt: chatPrompt,
  llm: chat,
});

const response = await chain.invoke({
  input: "hi! whats up?",
});

console.log(response);

API Reference:

• ConversationChain from langchain/chains
• ChatOpenAI from @langchain/openai
• ChatPromptTemplate from @langchain/core/prompts
• MessagesPlaceholder from @langchain/core/prompts
• BufferMemory from langchain/memory