Create an index

Create a vector index. Provide a `dimension` + `metric` for raw vectors, or an `embed` model for server-side (integrated) embedding — not both.

Create a vector index. Provide a dimension + metric for raw vectors, or an embed model for server-side (integrated) embedding — not both.

Authorization

TokenAuth

Authorization<token>

Project API key as Token lb-sk_...

In: header

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

name*string

1–45 chars: lowercase letters, numbers, hyphens.

vector_type?string

hybrid adds a sparse full-text space (Postgres FTS) beside the dense vectors, queryable with mode: sparse|hybrid.

Default"dense"

Value in

"dense"
"hybrid"

dimension?integer

Vector dimension (omit when using embed).

metric?string

Default"cosine"

Value in

"cosine"
"euclidean"
"dotproduct"

sparse?

Hybrid only: where the sparse space reads text — "text" (default) or "metadata:".

embed?

Integrated embedding configuration.

Response Body

`application/json`

curl -X POST "https://example.com/v1/indexes" \  -H "Content-Type: application/json" \  -d '{    "name": "products",    "dimension": 384,    "metric": "cosine"  }'

{  "name": "string",  "dimension": 0,  "metric": "string",  "embed_model": "string",  "managed": true,  "created_at": "2019-08-24T14:15:22Z"}

{  "detail": "string"}

Create an index

Authorization

Request Body

Response Body

201application/json

401application/json

`application/json`

`application/json`