Fetch

The Fetch operation looks up and returns vectors, by ID, from a single namespace. The returned vectors include the vector data and/or metadata.

cURL

curl --request GET \
     --url https://index_name-project_id.svc.environment.pinecone.io/vectors/fetch \
     --header 'accept: application/json'

Authorizations

Api-Key

string

header

required

An API Key is required to call Pinecone APIs. Get yours at https://app.pinecone.io/.

Query Parameters

ids

string[]

required

The vector IDs to fetch. Does not accept values containing spaces. Limited to 1000 IDs.

namespace

string

Response

200

application/json

A successful response.

The response for the Fetch operation.

vectors

object

The fetched vectors, in the form of a map between the fetched ids and the fetched vectors

Show child attributes

vectors.{key}

object

Show child attributes

vectors.{key}.id

string

required

This is the vector's unique id.

Required string length: 1 - 512

Example:

"example-vector-1"

vectors.{key}.values

number[]

required

This is the vector data included in the request.

Example:

[0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8]

vectors.{key}.sparseValues

object

Vector sparse data. Represented as a list of indices and a list of corresponded values, which must be the same length.

Show child attributes

vectors.{key}.sparseValues.indices

integer[]

required

The indices of the sparse data.

Example:

[1, 312, 822, 14, 980]

vectors.{key}.sparseValues.values

number[]

required

The corresponding values of the sparse data, which must be the same length as the indices.

Example:

[0.1, 0.2, 0.3, 0.4, 0.5]

vectors.{key}.metadata

object

This is the metadata included in the request.

Example:

{ "genre": "documentary", "year": 2019 }

namespace

string

The <a href='https://docs.pinecone.io/docs/namespaces'>namespace</a> of the vectors.

Example:

"example-namespace"