Xata is a serverless data platform, based on PostgreSQL. It provides a type-safe TypeScript/JavaScript SDK for interacting with your database, and a UI for managing your data. With the XataChatMessageHistory class, you can use Xata databases for longer-term persistence of chat sessions. Because Xata works via a REST API and has a pure TypeScript SDK, you can use this with Vercel Edge, Cloudflare Workers and any other Serverless environment.

​
Setup

​
Install the Xata CLI

npm install @xata.io/cli -g

​
Create a database to be used as a vector store

In the Xata UI create a new database. You can name it whatever you want, but for this example we’ll use langchain. When executed for the first time, the Xata LangChain integration will create the table used for storing the chat messages. If a table with that name already exists, it will be left untouched.

​
Initialize the project

In your project, run: 
xata init
and then choose the database you created above. This will also generate a xata.ts or xata.js file that defines the client you can use to interact with the database. See the Xata getting started docs for more details on using the Xata JavaScript/TypeScript SDK.

​
Usage

Each chat history session stored in Xata database must have a unique id. In this example, the getXataClient() function is used to create a new Xata client based on the environment variables. However, we recommend using the code generated by the xata init command, in which case you only need to import the getXataClient() function from the generated xata.ts file.
See this section for general instructions on installing integration packages.
npm
npm install @langchain/openai @langchain/community @langchain/core

import { BufferMemory } from "langchain/memory";
import { ChatOpenAI } from "@langchain/openai";
import { ConversationChain } from "langchain/chains";
import { XataChatMessageHistory } from "@langchain/community/stores/message/xata";
import { BaseClient } from "@xata.io/client";

// if you use the generated client, you don't need this function.
// Just import getXataClient from the generated xata.ts instead.
const getXataClient = () => {
  if (!process.env.XATA_API_KEY) {
    throw new Error("XATA_API_KEY not set");
  }

  if (!process.env.XATA_DB_URL) {
    throw new Error("XATA_DB_URL not set");
  }
  const xata = new BaseClient({
    databaseURL: process.env.XATA_DB_URL,
    apiKey: process.env.XATA_API_KEY,
    branch: process.env.XATA_BRANCH || "main",
  });
  return xata;
};

const memory = new BufferMemory({
  chatHistory: new XataChatMessageHistory({
    table: "messages",
    sessionId: new Date().toISOString(), // Or some other unique identifier for the conversation
    client: getXataClient(),
    apiKey: process.env.XATA_API_KEY, // The API key is needed for creating the table.
  }),
});

const model = new ChatOpenAI({
  model: "gpt-4o-mini",
});
const chain = new ConversationChain({ llm: model, memory });

const res1 = await chain.invoke({ input: "Hi! I'm Jim." });
console.log({ res1 });
/*
{
  res1: {
    text: "Hello Jim! It's nice to meet you. My name is AI. How may I assist you today?"
  }
}
*/

const res2 = await chain.invoke({ input: "What did I just say my name was?" });
console.log({ res2 });

/*
{
  res1: {
    text: "You said your name was Jim."
  }
}
*/

​
With pre-created table

If you don’t want the code to always check if the table exists, you can create the table manually in the Xata UI and pass createTable: false to the constructor. The table must have the following columns:
  • sessionId of type String
  • type of type String
  • role of type String
  • content of type Text
  • name of type String
  • additionalKwargs of type Text
import { BufferMemory } from "langchain/memory";
import { ChatOpenAI } from "@langchain/openai";
import { ConversationChain } from "langchain/chains";
import { XataChatMessageHistory } from "@langchain/community/stores/message/xata";
import { BaseClient } from "@xata.io/client";

// Before running this example, see the docs at
// https://js.langchain.com/docs/modules/memory/integrations/xata

// if you use the generated client, you don't need this function.
// Just import getXataClient from the generated xata.ts instead.
const getXataClient = () => {
  if (!process.env.XATA_API_KEY) {
    throw new Error("XATA_API_KEY not set");
  }

  if (!process.env.XATA_DB_URL) {
    throw new Error("XATA_DB_URL not set");
  }
  const xata = new BaseClient({
    databaseURL: process.env.XATA_DB_URL,
    apiKey: process.env.XATA_API_KEY,
    branch: process.env.XATA_BRANCH || "main",
  });
  return xata;
};

const memory = new BufferMemory({
  chatHistory: new XataChatMessageHistory({
    table: "messages",
    sessionId: new Date().toISOString(), // Or some other unique identifier for the conversation
    client: getXataClient(),
    createTable: false, // Explicitly set to false if the table is already created
  }),
});

const model = new ChatOpenAI({
  model: "gpt-4o-mini",
});
const chain = new ConversationChain({ llm: model, memory });

const res1 = await chain.invoke({ input: "Hi! I'm Jim." });
console.log({ res1 });
/*
{
  res1: {
    text: "Hello Jim! It's nice to meet you. My name is AI. How may I assist you today?"
  }
}
*/

const res2 = await chain.invoke({ input: "What did I just say my name was?" });
console.log({ res2 });

/*
{
  res1: {
    text: "You said your name was Jim."
  }
}
*/