What do I need to change from code below to make this ConversationalRetreivalQAChain work?

[Elindo586]

I am using Next.js and apparently the code is not finding my question?

What do I need to change or add to make this code work?

Error:

"Hello how are you doing today? "
 ⨯ Error: Question key question not found.
    at ConversationalRetrievalQAChain._call (file:///C:/Users/Edgar/Desktop/Stuff/Acode/nextprojectd/node_modules/langchain/dist/chains/conversational_retrieval_chain.js:116:19)
    at ConversationalRetrievalQAChain.call (file:///C:/Users/Edgar/Desktop/Stuff/Acode/nextprojectd/node_modules/langchain/dist/chains/base.js:110:24)
    at async useStore (webpack-internal:///(api)/./pages/api/usestore2.js:71:24) {
  page: '/api/usestore2'
}
 ✓ Compiled /_error in 282ms (516 modules)

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 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
          }),
        }
      );
    }

    const result = await chain.call({
      message,
    });

    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,

The error message you're seeing is indicating that the ConversationalRetrievalQAChain is not finding the question key in the input object you're passing to the call method.

In your code, you're passing an object with a message key to the call method:

const result = await chain.call({
  message,
});

However, the ConversationalRetrievalQAChain is expecting an object with a question key. You should change the message key to question like so:

const result = await chain.call({
  question: message,
});

This should resolve the error you're seeing.

Also, please note that the ConversationalRetrievalQAChain expects a chat_history key in the input object for the call method. If you want to maintain a conversation history, you should pass the history as an array of message objects to the call method. Each message object should have a role key (which can be 'system', 'user', or 'assistant') and a content key. Here's an example:

const result = await chain.call({
  question: message,
  chat_history: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Who won the world series in 2020?' },
    { role: 'assistant', content: 'The Los Angeles Dodgers won the World Series in 2020.' },
    // Add the new user message here
    { role: 'user', content: message },
  ],
});

I hope this helps! Let me know if you have any other questions.

Sources

• examples/src/chains/conversational_qa.ts
• langchain/src/chains/tests/conversational_retrieval_chain.int.test.ts
• langchain/src/chains/conversational_retrieval_chain.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.