Skip to main content

HNSWLib

Compatibility

Only available on Node.js.

HNSWLib is an in-memory vectorstore that can be saved to a file. It uses HNSWLib.

Setup​

caution

On Windows, you might need to install Visual Studio first in order to properly build the hnswlib-node package.

You can install it with

npm install hnswlib-node
tip

See this section for general instructions on installing integration packages.

npm install @langchain/openai @langchain/community

Usage​

Create a new index from texts​

import { HNSWLib } from "@langchain/community/vectorstores/hnswlib";
import { OpenAIEmbeddings } from "@langchain/openai";

const vectorStore = await HNSWLib.fromTexts(
  ["Hello world", "Bye bye", "hello nice world"],
  [{ id: 2 }, { id: 1 }, { id: 3 }],
  new OpenAIEmbeddings()
);

const resultOne = await vectorStore.similaritySearch("hello world", 1);
console.log(resultOne);

API Reference:

Create a new index from a loader​

import { HNSWLib } from "@langchain/community/vectorstores/hnswlib";
import { OpenAIEmbeddings } from "@langchain/openai";
import { TextLoader } from "langchain/document_loaders/fs/text";

// Create docs with a loader
const loader = new TextLoader("src/document_loaders/example_data/example.txt");
const docs = await loader.load();

// Load the docs into the vector store
const vectorStore = await HNSWLib.fromDocuments(docs, new OpenAIEmbeddings());

// Search for the most similar document
const result = await vectorStore.similaritySearch("hello world", 1);
console.log(result);

API Reference:

Save an index to a file and load it again​

import { HNSWLib } from "@langchain/community/vectorstores/hnswlib";
import { OpenAIEmbeddings } from "@langchain/openai";

// Create a vector store through any method, here from texts as an example
const vectorStore = await HNSWLib.fromTexts(
  ["Hello world", "Bye bye", "hello nice world"],
  [{ id: 2 }, { id: 1 }, { id: 3 }],
  new OpenAIEmbeddings()
);

// Save the vector store to a directory
const directory = "your/directory/here";
await vectorStore.save(directory);

// Load the vector store from the same directory
const loadedVectorStore = await HNSWLib.load(directory, new OpenAIEmbeddings());

// vectorStore and loadedVectorStore are identical

const result = await loadedVectorStore.similaritySearch("hello world", 1);
console.log(result);

API Reference:

Filter documents​

import { HNSWLib } from "@langchain/community/vectorstores/hnswlib";
import { OpenAIEmbeddings } from "@langchain/openai";

const vectorStore = await HNSWLib.fromTexts(
  ["Hello world", "Bye bye", "hello nice world"],
  [{ id: 2 }, { id: 1 }, { id: 3 }],
  new OpenAIEmbeddings()
);

const result = await vectorStore.similaritySearch(
  "hello world",
  10,
  (document) => document.metadata.id === 3
);

// only "hello nice world" will be returned
console.log(result);

API Reference:

Delete index​

import { HNSWLib } from "@langchain/community/vectorstores/hnswlib";
import { OpenAIEmbeddings } from "@langchain/openai";

// Save the vector store to a directory
const directory = "your/directory/here";

// Load the vector store from the same directory
const loadedVectorStore = await HNSWLib.load(directory, new OpenAIEmbeddings());

await loadedVectorStore.delete({ directory });

API Reference:

Help us out by providing feedback on this documentation page: