Nearest Neighbors By Embedding

POST 
/v1/dataset/data/get/nearest_neighbors/by_embedding

⚠️ WARNING

This endpoint is unstable & not officially supported. It may be deprecated and removed in future API versions.

Nearest Neighbors By Embedding

Request

application/json

Body

required

atlas_index_id Atlas Index Id (string)required

Unique atlas index id

queries

object

required

A set of embeddings to query. Where n is the number of vectors to search and d is the vector dimensionality, this can be either an nxd numpy array encoded to base64, OR a list of n lists with d numbers per list.

anyOf

MOD1

string

MOD2

Array [

items number

type

]

k K (integer)

Default value: 4

The number of neighbors to return

Responses

200

Successful Response

application/json

Schema

Schema

neighbors array[]required

nested list of nearest neighbors

distances array[]required

distances of the neighbors to queries

Example (from schema)

{
  "neighbors": [
    [
      "string"
    ]
  ],
  "distances": [
    [
      0
    ]
  ]
}

422

Validation Error

application/json

Schema

Schema

detail

object[]

Array [

loc

object[]

required

Array [

anyOf

MOD1

string

MOD2

integer

]

msg Message (string)required

type Error Type (string)required

]

Example (from schema)

{
  "detail": [
    {
      "loc": [
        "string",
        0
      ],
      "msg": "string",
      "type": "string"
    }
  ]
}

Loading...