ScyllaDB Docs ScyllaDB Cloud Vector Search Reference for Vector Search

Reference for Vector Search¶

This page is a technical reference for working with Vector Search in ScyllaDB. It includes a list of supported instance types, the CQL syntax needed to define and query vector data, and the API endpoints for working with Vector Search. Use it as a quick lookup when writing queries or building integrations.

Supported Instance Types¶

The following instance types are supported for Vector Search clusters.

On AWS¶

Instance Type	ID
t4g.medium	176
r7g.medium	177
r7g.large	204
r7g.xlarge	205
r7g.2xlarge	206
r7g.4xlarge	207
r7g.8xlarge	208
r7g.12xlarge	209
r7g.16xlarge	210
r7i.24xlarge	211
r7i.48xlarge	212

On GCP¶

Instance Type	ID
e2-medium	179
n4-highmem-2	180
n4-highmem-4	213
n4-highmem-8	214
n4-highmem-16	215
n4-highmem-32	216
n4-highmem-48	217
n4-highmem-64	218
n4-highmem-80	219
m4-megamem-28	220 (limited availability - contact us)
m4-ultramem-56	221 (limited availability - contact us)
m4-ultramem-112	222 (limited availability - contact us)
m4-ultramem-224	223 (limited availability - contact us)

CQL Reference¶

Create Vector Table¶

Syntax:

CREATE TABLE IF NOT EXISTS `keyspace.table` (
 column1 `type`,
 column2 `type`,
 column3 `type`,
 vector_column_name vector<float, n>,
);

Example:

CREATE TABLE IF NOT EXISTS mykeyspace.pictures (
 userid uuid,
 pictureid uuid,
 body text,
 posted_by text,
 picture_vector vector<float, 64>,
 PRIMARY KEY (userid, pictureid, posted_by)
);

Create Vector Index¶

Syntax:

CREATE CUSTOM INDEX [ IF NOT EXISTS ] `index_name`
ON `table_name` (`vector_column_name`)
USING 'vector_index'
[WITH OPTIONS = ];

Example:

CREATE CUSTOM INDEX vectorIndex
ON pictures (picture_vector)
USING 'vector_index'
WITH OPTIONS = {'similarity_function': 'COSINE', 'maximum_node_connections': '16'};

See Global Secondary Indexes - Vector Index in the ScyllaDB documentation for a list of available options.

Drop Vector Index¶

Syntax:

DROP INDEX [ IF EXISTS ] `index_name`

Example:

DROP INDEX [ IF EXISTS ] vectorIndex

Run Similarity Search¶

Syntax:

SELECT `column1`, `column2`, ...
FROM `keyspace.table`
ORDER BY `vector_column_name`
ANN OF `vector`
LIMIT `integer`;

Example:

SELECT pictureid
FROM mykeyspace.pictures
ORDER BY picture_vector ANN OF [
0.12,0.34,0.56,0.78,0.91,0.15,0.62,0.48,0.22,0.31,
0.40,0.67,0.53,0.84,0.19,0.72,0.63,0.54,0.26,0.33,
0.11,0.09,0.27,0.41,0.69,0.82,0.57,0.38,0.71,0.46,
0.55,0.64,0.17,0.81,0.23,0.95,0.66,0.35,0.44,0.59,
0.02,0.75,0.28,0.16,0.92,0.88,0.47,0.13,0.99,0.21,
0.32,0.83,0.45,0.04,0.86,0.25,0.36,0.73,0.07,0.61,
0.52,0.14,0.68,0.05
]
LIMIT 3;

API Reference¶

Create a Vector Search Cluster¶

Create a new cluster with Vector Search enabled:

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
    }
  }'

Deploy Vector Search Nodes¶

Deploy Vector Search nodes in the specified datacenter (DC):

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
  }'

Delete Vector Search Nodes¶

Delete Vector Search nodes from the specified datacenter (DC):

curl -X DELETE "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" \

Get Vector Search Nodes¶

Get information about Vector Search nodes in the specified datacenter (DC):

curl -X GET "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" \

Example response:

{
  "data": {
    "availabilityZones": [
      {
        "azid": "use1-az4",
        "nodes": [
          {
            "id": 337,
            "instanceTypeId": 175,
            "status": "ACTIVE"
          }
        ]
      },
      {
        "azid": "use1-az5",
        "nodes": [
          {
            "id": 338,
            "instanceTypeId": 175,
            "status": "ACTIVE"
          }
        ]
      },
      {
        "azid": "use1-az2",
        "nodes": [
          {
            "id": 339,
            "instanceTypeId": 175,
            "status": "ACTIVE"
          }
        ]
      }
    ]
  }
}

Get Your Account ID¶

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

Response:

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

Get Your Cluster ID¶

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

Get Your DC ID¶

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

Was this page helpful?