Vector Search Deployments

Vector Search Deployments¶

Before you work with vector search, you need to ensure that the vector search feature is enabled for your cluster. You can enable vector search on new and existing clusters.

Note

In the beta release, vector search can only be enabled via API. A UI will be added in future releases.
Before you use the ScyllaDB Cloud API, you need to generate a personal API token for authenticating requests to the API endpoints. See Create a Personal Token for Authentication for details.

Creating a New Cluster with Vector Search Enabled¶

Get your account ID (ACCOUNT_ID):

curl -X GET "https://api.cloud.scylladb.com/account/default" \
   -H "Authorization: Bearer YOUR_API_TOKEN"

Response looks like:

{
  "error": "",
  "data": {
     "accountId": 12345,
     "name": "my-account",
     "userId": "12345"
  }
}

Here 12345 is your ACCOUNT_ID.

Create a new cluster that includes the ``vectorSearch`` field in the API request body. Make sure to replace ACCOUNT_ID and YOUR_API_TOKEN with actual values in the example below.

curl -X POST "https://api.cloud.scylladb.com/account/{ACCOUNT_ID}/cluster" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "clusterName": "my-vector-cluster",
    "cloudProviderId": 1,
    "regionId": 1,
    "scyllaVersion":"2025.4.0~rc0-0.20251001.6969918d3151",
    "numberOfNodes": 3,
    "instanceId": 62,
    "freeTier": true,
    "replicationFactor": 3,
    "vectorSearch": {
      "defaultNodes": 1,
      "defaultInstanceTypeId": 175
    }
  }'

This will deploy dedicated vector search nodes in the cluster.

Connect to the cluster with cqlsh.
1. Go to https://cloud.scylladb.com/, choose your cluster and go to the Connect tab.
2. Choose Cqlsh from the left menu and follow the instructions.

Enabling Vector Search on an Existing Cluster¶

Note

Prerequisites:

ScyllaDB version must be >= 2025.4.x in your cluster.

To enable vector search on an existing cluster, you must deploy new vector search nodes. Before doing that, you need to retrieve your account ID, cluster ID, and datacenter (DC) ID.

In the examples below, make sure to replace YOUR_API_TOKEN with your actual access token value.

Get your account ID (ACCOUNT_ID):

curl -X GET "https://api.cloud.scylladb.com/account/default" \
   -H "Authorization: Bearer YOUR_API_TOKEN"

Response looks like:

{
  "error": "",
  "data": {
     "accountId": 12345,
     "name": "my-account",
     "userId": "12345"
  }
}

Here 12345 is your ACCOUNT_ID.

List your clusters to get your cluster ID:

curl -X GET "https://api.cloud.scylladb.com/account/{ACCOUNT_ID}/clusters" \
   -H "Authorization: Bearer YOUR_API_TOKEN"

Response looks like:

{
  "data": {
    "clusters": [
       {
         "id": 6789,
         "name": "my-vector-cluster",
         "status": "ACTIVE"
       }
    ]
  }
 }

Here 6789 is your clusterId.

List the datacenters (DCs) for your cluster to get the DC ID.

curl -X GET "https://api.cloud.scylladb.com/account/{ACCOUNT_ID}/cluster/{CLUSTER_ID}/dcs" \
   -H "Authorization: Bearer YOUR_API_TOKEN"

Response looks like:

{
  "data": {
    "dataCenters": [
       {
         "id": 222,
         "name": "us-east-1a",
         "status": "ACTIVE"
       }
    ]
  }
}

Here 222 is the dcId you need for vector store operations.

Deploy vector search nodes.

curl -X POST "https://api.cloud.scylladb.com/account/{ACCOUNT_ID}/cluster/{CLUSTER_ID}/dc/{DC_ID}/vector-search" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
     "defaultNodes": 1,
     "defaultInstanceTypeId": 175
  }'

During the beta period, the supported instance types for vector search are:

175 - AWS t4g.small
176 - AWS t4g.medium
177 - AWS r7g.medium
178 - GCP e2-small
179 - GCP e2-medium
180 - GCP n4-highmem-2

Connect to the cluster with cqlsh.
1. Go to https://cloud.scylladb.com/, choose your cluster and go to the Connect tab.
2. Choose Cqlsh from the left menu and follow the instructions.

Deployment Limitations in Beta Release¶

Vector search nodes can only be created via ScyllaDB Cloud API. Vector search cannot be enabled for clusters created in the UI.
You can create one vector search node per Availability Zone (AZ).
Multi-DC deployments are not supported.
Vector search nodes have Time to Live (TTL) of 30 days.
ScyllaDB version should be 2025.4.X or higher.

Was this page helpful?