To enable vector search in a generic PostgreSQL database, LangChain.js supports using TypeORM with the pgvector Postgres extension.

​
Setup

To work with TypeORM, you need to install the typeorm and pg packages:
npm
npm install typeorm
npm
npm install pg
See this section for general instructions on installing LangChain packages.
npm
npm install @langchain/openai @langchain/community @langchain/core

​
Setup a pgvector self hosted instance with docker-compose

pgvector provides a prebuilt Docker image that can be used to quickly setup a self-hosted Postgres instance. Create a file below named docker-compose.yml:
docker-compose.yml
services:
  db:
    image: ankane/pgvector
    ports:
      - 5432:5432
    volumes:
      - ./data:/var/lib/postgresql/data
    environment:
      - POSTGRES_PASSWORD=ChangeMe
      - POSTGRES_USER=myuser
      - POSTGRES_DB=api
And then in the same directory, run docker compose up to start the container. You can find more information on how to setup pgvector in the official repository.

​
Usage

One complete example of using TypeORMVectorStore is the following: 
import { DataSourceOptions } from "typeorm";
import { OpenAIEmbeddings } from "@langchain/openai";
import { TypeORMVectorStore } from "@langchain/community/vectorstores/typeorm";

// First, follow set-up instructions at
// https://js.langchain.com/docs/modules/indexes/vector_stores/integrations/typeorm

export const run = async () => {
  const args = {
    postgresConnectionOptions: {
      type: "postgres",
      host: "localhost",
      port: 5432,
      username: "myuser",
      password: "ChangeMe",
      database: "api",
    } as DataSourceOptions,
  };

  const typeormVectorStore = await TypeORMVectorStore.fromDataSource(
    new OpenAIEmbeddings(),
    args
  );

  await typeormVectorStore.ensureTableInDatabase();

  await typeormVectorStore.addDocuments([
    { pageContent: "what's this", metadata: { a: 2 } },
    { pageContent: "Cat drinks milk", metadata: { a: 1 } },
  ]);

  const results = await typeormVectorStore.similaritySearch("hello", 2);

  console.log(results);
};