MongoDB Atlas

This guide provides a quick overview for getting started with MongoDB Atlas [vector stores](/oss/javascript/integrations/vectorstores). For detailed documentation of all `MongoDBAtlasVectorSearch` features and configurations head to the [API reference](https://api.js.langchain.com/classes/langchain_mongodb.MongoDBAtlasVectorSearch.html).

## Overview

### Integration details

| Class | Package | [PY support](https://python.langchain.ac.cn/docs/integrations/vectorstores/mongodb_atlas/) |  Version |
| :--- | :--- | :---: | :---: |
| [`MongoDBAtlasVectorSearch`](https://api.js.langchain.com/classes/langchain_mongodb.MongoDBAtlasVectorSearch.html) | [`@langchain/mongodb`](https://npmjs.net.cn/package/@langchain/mongodb) | ✅ | ![NPM - Version](https://img.shields.io/npm/v/@langchain/mongodb?style=flat-square&label=%20&) |

## Setup

To use MongoDB Atlas vector stores, you'll need to configure a MongoDB Atlas cluster and install the `@langchain/mongodb` integration package.

### Initial Cluster Configuration

To create a MongoDB Atlas cluster, navigate to the [MongoDB Atlas website](https://mongodb.ac.cn/products/platform/atlas-database) and create an account if you don't already have one.

Create and name a cluster when prompted, then find it under `Database`. Select `Browse Collections` and create either a blank collection or one from the provided sample data.

**Note:** The cluster created must be MongoDB 7.0 or higher.

### Creating an Index

After configuring your cluster, you'll need to create an index on the collection field you want to search over.

Switch to the `Atlas Search` tab and click `Create Search Index`. From there, make sure you select `Atlas Vector Search - JSON Editor`, then select the appropriate database and collection and paste the following into the textbox:

```json
{
  "fields": [
    {
      "numDimensions": 1536,
      "path": "embedding",
      "similarity": "euclidean",
      "type": "vector"
    }
  ]
}

process.env.MONGODB_ATLAS_URI = "your-atlas-url";
process.env.MONGODB_ATLAS_COLLECTION_NAME = "your-atlas-db-name";
process.env.MONGODB_ATLAS_DB_NAME = "your-atlas-db-name";

process.env.OPENAI_API_KEY = "YOUR_API_KEY";

// process.env.LANGSMITH_TRACING="true"
// process.env.LANGSMITH_API_KEY="your-api-key"

import { MongoDBAtlasVectorSearch } from "@langchain/mongodb";
import { OpenAIEmbeddings } from "@langchain/openai";
import { MongoClient } from "mongodb";

const client = new MongoClient(process.env.MONGODB_ATLAS_URI || "");
const collection = client.db(process.env.MONGODB_ATLAS_DB_NAME)
  .collection(process.env.MONGODB_ATLAS_COLLECTION_NAME);

const embeddings = new OpenAIEmbeddings({
  model: "text-embedding-3-small",
});

const vectorStore = new MongoDBAtlasVectorSearch(embeddings, {
  collection: collection,
  indexName: "vector_index", // The name of the Atlas search index. Defaults to "default"
  textKey: "text", // The name of the collection field containing the raw content. Defaults to "text"
  embeddingKey: "embedding", // The name of the collection field containing the embedded text. Defaults to "embedding"
});

import type { Document } from "@langchain/core/documents";

const document1: Document = {
  pageContent: "The powerhouse of the cell is the mitochondria",
  metadata: { source: "https://example.com" }
};

const document2: Document = {
  pageContent: "Buildings are made out of brick",
  metadata: { source: "https://example.com" }
};

const document3: Document = {
  pageContent: "Mitochondria are made out of lipids",
  metadata: { source: "https://example.com" }
};

const document4: Document = {
  pageContent: "The 2024 Olympics are in Paris",
  metadata: { source: "https://example.com" }
}

const documents = [document1, document2, document3, document4];

await vectorStore.addDocuments(documents, { ids: ["1", "2", "3", "4"] });

[ '1', '2', '3', '4' ]

await vectorStore.delete({ ids: ["4"] });

const similaritySearchResults = await vectorStore.similaritySearch("biology", 2);

for (const doc of similaritySearchResults) {
  console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
}

* The powerhouse of the cell is the mitochondria [{"_id":"1","source":"https://example.com"}]
* Mitochondria are made out of lipids [{"_id":"3","source":"https://example.com"}]

{
  "fields": [
    {
      "numDimensions": 1024,
      "path": "embedding",
      "similarity": "euclidean",
      "type": "vector"
    },
    {
      "path": "source",
      "type": "filter"
    }
  ]
}

const filter = {
  preFilter: {
    source: {
      $eq: "https://example.com",
    },
  },
}

const filteredResults = await vectorStore.similaritySearch("biology", 2, filter);

for (const doc of filteredResults) {
  console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
}

* The powerhouse of the cell is the mitochondria [{"_id":"1","source":"https://example.com"}]
* Mitochondria are made out of lipids [{"_id":"3","source":"https://example.com"}]

const similaritySearchWithScoreResults = await vectorStore.similaritySearchWithScore("biology", 2, filter)

for (const [doc, score] of similaritySearchWithScoreResults) {
  console.log(`* [SIM=${score.toFixed(3)}] ${doc.pageContent} [${JSON.stringify(doc.metadata)}]`);
}

* [SIM=0.374] The powerhouse of the cell is the mitochondria [{"_id":"1","source":"https://example.com"}]
* [SIM=0.370] Mitochondria are made out of lipids [{"_id":"3","source":"https://example.com"}]

const retriever = vectorStore.asRetriever({
  // Optional filter
  filter: filter,
  k: 2,
});
await retriever.invoke("biology");

[
  Document {
    pageContent: 'The powerhouse of the cell is the mitochondria',
    metadata: { _id: '1', source: 'https://example.com' },
    id: undefined
  },
  Document {
    pageContent: 'Mitochondria are made out of lipids',
    metadata: { _id: '3', source: 'https://example.com' },
    id: undefined
  }
]

await client.close();