Why is memory not working?

[Elindo586]

It seems like memory doesn't remember the information I gave in the previous question.

I tell the bot my name is Jack, then in follow up question I ask him my name, and the bot says it doesn't have that information... How can I fix that?

Here is the code:

import { ChatOpenAI } from "langchain/chat_models/openai";
import { ConversationalRetrievalQAChain } from "langchain/chains";
import { BufferMemory } from "langchain/memory";

import { TextLoader } from "langchain/document_loaders/fs/text";
import { CharacterTextSplitter } from "langchain/text_splitter";
import { OpenAIEmbeddings } from "langchain/embeddings/openai";
import { FaissStore } from "langchain/vectorstores/faiss";

import { OpenAI } from "langchain/llms/openai";
import { PromptTemplate } from "langchain/prompts";
import {
  SimpleSequentialChain,
  LLMChain,
  RetrievalQAChain,
  loadQAStuffChain,
} from "langchain/chains";

let chain;
let result;

let loader;
let docs;
let splitter;
let documents;
let embeddings1;
let vectorstore;

let model1;

let embeddings;
let vectoreStore;
let vectorStoreRetriever;
let vectorChain;
// let overallChain;

const useStore = async (req, res) => {
  if (req.method === "POST") {
    loader = new TextLoader("./documents/restaurant.txt");
    docs = await loader.load();
    splitter = new CharacterTextSplitter({
      chunkSize: 200,
      chunkOverlap: 50,
    });
    documents = await splitter.splitDocuments(docs);
    embeddings1 = new OpenAIEmbeddings();
    vectorstore = await FaissStore.fromDocuments(documents, embeddings1);
    await vectorstore.save("./");

    const message = req.body.newText;
    const firstOne = req.body.firstMsg;

    console.log(message);
    if (firstOne) {
      model1 = new ChatOpenAI({
        modelName: "gpt-4",
        openAIApiKey: process.env.OPENAI_API_KEY,
        temperature: 0,
      });

      embeddings = new OpenAIEmbeddings();
      vectoreStore = await FaissStore.load("./", embeddings);
    }
    chain = ConversationalRetrievalQAChain.fromLLM(
      model1,
      vectoreStore.asRetriever(),
      {
        memory: new BufferMemory({
          memoryKey: "chat_history", // Must be set to "chat_history"
          inputKey: "question", // The key for the input to the chain
          outputKey: "text", // The key for the final conversational output of the chain
          returnMessages: true,
          // questionGeneratorChainOptions: {
          //   llm: fasterModel,
          // },
        }),
      }
    );
    let chatHistory = "";
    result = await chain.call({
      question: message,
      chat_history: chatHistory,
      // Add the new user message here
      // { role: 'user', content: message },
    });
    chatHistory = `${message}\n${result.text}`;

    const followUpRes = await chain.call({
      question: message,
      chat_history: chatHistory,
    });

    console.log(result);

    return res.status(200).json({ output: result });
  } else {
    res.status(405).json({ say: "Only POST is allowed" });
  }
};
export default useStore;

[dosubot[bot]]

🤖

Hello Jack,

The issue you're experiencing seems to be related to how the memory is being managed in your code. The BufferMemory in LangChainJS is not retaining the information from previous interactions because it's not being updated with the new interactions. After each interaction, you need to update the memory with the new conversation.

Here's how you can modify your code:

// ... rest of your code

let chatHistory = "";
result = await chain.call({
  question: message,
  chat_history: chatHistory,
});
chatHistory = `${message}\n${result.text}`;

const followUpRes = await chain.call({
  question: message,
  chat_history: chatHistory,
});

// ... rest of your code

In this updated code, after each interaction, the chatHistory is updated with the new conversation. This way, the BufferMemory will retain the information from previous interactions.

Also, please note that the memoryKey should be set to "chat_history" as per the BufferMemory class definition. You have correctly set this in your code.

This solution is based on the information provided in the BufferMemory class definition and a similar issue discussed in the LangChainJS repository (issue #2477).

Please try this solution and let me know if it resolves your issue. If you have any further questions, feel free to ask.

Best,
Dosu

Sources

• How can we add Memory to the dynamictool
• chat-conversational-react-description is not working
• ConversationalRetrievalQAChain with FirestoreChatMessageHistory: problem with chat_history
• examples/src/memory/buffer.ts
• langchain/src/memory/buffer_memory.ts
• examples/src/memory/buffer_window.ts

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.