Unlock Long-Term Memory with LangChain: Persistent Conversations Simplified

Long Term Memory

import { ChatOpenAI } from "@langchain/openai";
import { HumanMessage, AIMessage } from "@langchain/core/messages";
import * as dotenv from "dotenv";

dotenv.config();

async function main() {
  const chatModel = new ChatOpenAI({
    modelName: "gpt-3.5-turbo",
    temperature: 0.7,
    openAIApiKey: process.env.OPENAI_API_KEY!,
  });

  // Simple in-memory storage for chat history
  const memoryStore: { role: string; content: string }[] = [
    { role: "human", content: "Hi! What can you do?" },
    {
      role: "ai",
      content:
        "Hello! I can assist with a variety of tasks, such as answering questions, summarizing content, or helping with programming.",
    },
  ];

  // Function to add new messages to the memory store
  function addToMemory(role: string, content: string) {
    memoryStore.push({ role, content });
  }

  // New user input
  const userInput = "Can you remind me what you said earlier?";
  addToMemory("human", userInput);

  // Combine memory store into a format compatible with the model
  const conversationHistory = memoryStore.map((msg) =>
    msg.role === "human" ? new HumanMessage(msg.content) : new AIMessage(msg.content)
  );

  // Generate AI response
  const response = await chatModel.call(conversationHistory);

  // Add the AI response to memory
  addToMemory("ai", response.text || "");

  // Output the full conversation
  console.log("Conversation History:");
  memoryStore.forEach((msg) => {
    console.log(`${msg.role.toUpperCase()}: ${msg.content}`);
  });

  console.log("\nAI Response:");
  console.log(response.text || response);
}

main().catch(console.error);

This example demonstrates how to implement long-term conversation memory using LangChain's ChatOpenAI model. The script stores conversation history in a simple in-memory data structure, allowing AI to retain context across multiple interactions. By keeping track of previous exchanges, the function enables more dynamic, context-aware responses. Whether you're building chatbots, virtual assistants, or interactive AI tools, this implementation showcases how to create a seamless, memory-enabled conversational experience.

Conclusion

...