---
sidebar_class_name: node-only
---

# MongoDB Atlas

:::tip Compatibility
Only available on Node.js.
:::

Langchain supports MongoDB Atlas as a vector store.

## Setup

### Installation

First, add the Node MongoDB SDK to your project:

```bash npm2yarn
npm install -S mongodb
```

### Initial Cluster Configuration

Next, you'll need create a MongoDB Atlas cluster. Navigate to the [MongoDB Atlas website](https://www.mongodb.com/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 `Collections` and create either a blank collection or one from the provided sample data.

### Creating an Index

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

Go to the `Search` tab within your cluster, then select `Create Search Index`. Using the JSON editor option, add an index to the collection you wish to use.

```js
{
  "mappings": {
    "fields": {
      // Default value, should match the name of the field within your collection that contains embeddings
      "embedding": [
        {
          "dimensions": 1024,
          "similarity": "euclidean",
          "type": "knnVector"
        }
      ]
    }
  }
}
```

The `dimensions` property should match the dimensionality of the embeddings you are using. For example, Cohere embeddings have 1024 dimensions, and OpenAI embeddings have 1536.

**Note:** By default the vector store expects an index name of `default`, an indexed collection field name of `embedding`, and a raw text field name of `text`. You should initialize the vector store with field names matching your collection schema as shown below.

Finally, proceed to build the index.

## Usage

### Ingestion

import CodeBlock from "@theme/CodeBlock";
import Ingestion from "@examples/indexes/vector_stores/mongodb_atlas_fromTexts.ts";

<CodeBlock language="typescript">{Ingestion}</CodeBlock>

### Search

import Search from "@examples/indexes/vector_stores/mongodb_atlas_search.ts";

<CodeBlock language="typescript">{Search}</CodeBlock>