Create a vector index

Create a vector index for dense vectors, sparse vectors or text, with an empty default namespace.

POST /v1/tenants/{tenant}/vector-indexes

Define a vector index before loading recordsCreating the index starts an empty default namespace.

Choose the representationsDefine dense vectors, sparse vectors or searchable text.
Create the indexSet its name and supported configuration.
Save the index IDAdd records through the record endpoints next.

Before you start

Use your database bearer token.

Choose a unique index name and the dimensions or text configuration your data needs. The example creates demo-search for three-dimensional vectors.

Path parameters

Field	Type	Required
`tenant`	`string`	Required

Headers

Field	Type	Required	Description
`x-oc-db-user`	`string`	Optional	Acting database user (role, grant and row-policy checks). Send with x-oc-db-key.
`x-oc-db-key`	`string`	Optional	API key of the x-oc-db-user user.

Request body

application/json

Limits and accepted values

name is 1-45 bytes of [a-z0-9-].
At least one of dimension, sparse: true or text_fields is required;
dimension 1-8192 needs metric (cosine, dot, l2, manhattan).
deletion_protection: enabled|disabled (default disabled);
identifier_profile: unicode|ascii (default unicode);
tags: string map, at most 20.
embedding is refused with 501 and metadata_publish with 400 (generated-embedding indexes are not available yet).
Unknown fields are refused with 400 unknown_request_field.

Field	Type	Required
`deletion_protection`	`string`	Optional
`dimension`	`integer`	Optional
`embedding`	`object`	Optional
`identifier_profile`	`string`	Optional
`metadata_publish`	`string`	Optional
`metric`	`string`	Optional
`name`	`string`	Required
`sparse`	`boolean`	Optional
`tags`	`object`	Optional
`text_fields`	`object[]`	Optional

Fields in text_fields

Field	Type	Required
`analyzer`	`string`	Required
`name`	`string`	Required

Field	Type	Required
`visibility_fields`	`string[]`	Optional

Fields in visibility_fields

Field	Type	Required
`visibility_fields`	`string`	Optional

Read the result

Save index_id; the search route uses it. The response records the fixed dimensions and metric, and the index starts with an empty default namespace. Creating an index does not insert vectors.

Response statuses

HTTP status reference

Status	What to do
201	Created
400	Correct the request before retrying.
401	Check the credential and Authorization header.
402	Check feature access or available credits.
403	Check tenant access, roles and permissions.
409	Resolve the conflict before retrying.
413	Split or reduce the request body.
415	Send the required Content-Type.
422	Correct the values or unsupported combination.
429	Honor Retry-After when present; back off.
500	Check the outcome before retrying a write.
501	Check deployment support for this operation.
503	Honor Retry-After when present; check write outcomes.

Request example

curl --include --request POST "${OC_BASE_URL}/v1/tenants/${OC_TENANT}/vector-indexes" \
  --header "Authorization: Bearer ${OC_TOKEN}" \
  --header "Content-Type: application/json" \
  --data-binary '{
  "name": "demo-search",
  "dimension": 3,
  "metric": "cosine",
  "deletion_protection": "disabled"
}'

Response example

Examples use synthetic values to show the response format.

Response status

{
  "index_id": "22222222-2222-4222-8222-222222222222",
  "name": "demo-search",
  "state": "active",
  "dimension": 3,
  "metric": "cosine",
  "score_direction": "higher_is_better",
  "sparse": false,
  "text_fields": [],
  "visibility_fields": [],
  "embedding": null,
  "deletion_protection": "disabled",
  "tags": {},
  "identifier_profile": "unicode",
  "compat_family": "vectors",
  "created_at": "2026-10-30T00:00:00.000Z"
}

{
  "error": {
    "code": "unknown_request_field",
    "message": "Unrecognized field in request.",
    "status": 400,
    "retryable": false
  }
}

Illustrative message; code and envelope follow the documented vector-index contract.

Correct the request before retrying.

Download the OpenAPI specification for the complete response schemas.

Before you startCopy Anchor Link

Path parametersCopy Anchor Link

HeadersCopy Anchor Link

Request bodyCopy Anchor Link