Query Vectors

vectorize.indexes.query(, ) -> IndexQueryResponse

POST/accounts/{account_id}/vectorize/v2/indexes/{index_name}/query

Finds vectors closest to a given vector in an index.

Security

API Token

The preferred authorization scheme for interacting with the Cloudflare API. Create a token.

Example:Authorization: Bearer Sn3lZJTBX6kkg7OdcBUAxOO963GEIyGQqnFTOFYY

API Email + API Key

The previous authorization scheme for interacting with the Cloudflare API, used in conjunction with a Global API key.

Example:X-Auth-Email: user@example.com

The previous authorization scheme for interacting with the Cloudflare API. When possible, use API tokens instead of Global API keys.

Example:X-Auth-Key: 144c9defac04969c7bfad8efaa8ea194

Accepted Permissions (at least one required)

Vectorize WriteVectorize Read

ParametersExpand Collapse

account_id: str

Identifier

maxLength32

index_name: str

vector: Iterable[float]

The search vector that will be used to find the nearest neighbors.

filter: Optional[object]

A metadata filter expression used to limit nearest neighbor results.

return_metadata: Optional[Literal["none", "indexed", "all"]]

Whether to return no metadata, indexed metadata or all metadata associated with the closest vectors.

One of the following:

"none"

"indexed"

"all"

return_values: Optional[bool]

Whether to return the values associated with the closest vectors.

top_k: Optional[float]

The number of nearest neighbors to find.

ReturnsExpand Collapse

class IndexQueryResponse: …

count: Optional[int]

Specifies the count of vectors returned by the search

matches: Optional[List[Match]]

Array of vectors matched by the search

id: Optional[str]

Identifier for a Vector

maxLength64

metadata: Optional[object]

namespace: Optional[str]

score: Optional[float]

The score of the vector according to the index's distance metric

values: Optional[List[float]]

Query Vectors

import os
from cloudflare import Cloudflare

client = Cloudflare(
    api_token=os.environ.get("CLOUDFLARE_API_TOKEN"),  # This is the default and can be omitted
)
response = client.vectorize.indexes.query(
    index_name="example-index",
    account_id="023e105f4ecef8ad9ca31a8372d0c353",
    vector=[0.5, 0.5, 0.5],
)
print(response.count)

{
  "errors": [
    {
      "code": 1000,
      "message": "message",
      "documentation_url": "documentation_url",
      "source": {
        "pointer": "pointer"
      }
    }
  ],
  "messages": [
    {
      "code": 1000,
      "message": "message",
      "documentation_url": "documentation_url",
      "source": {
        "pointer": "pointer"
      }
    }
  ],
  "result": {
    "count": 0,
    "matches": [
      {
        "id": "some-vector-id-023e105f4ecef8ad9ca31a8372d0c353",
        "metadata": {},
        "namespace": "namespace",
        "score": 0,
        "values": [
          0
        ]
      }
    ]
  },
  "success": true
}

Returns Examples

{
  "errors": [
    {
      "code": 1000,
      "message": "message",
      "documentation_url": "documentation_url",
      "source": {
        "pointer": "pointer"
      }
    }
  ],
  "messages": [
    {
      "code": 1000,
      "message": "message",
      "documentation_url": "documentation_url",
      "source": {
        "pointer": "pointer"
      }
    }
  ],
  "result": {
    "count": 0,
    "matches": [
      {
        "id": "some-vector-id-023e105f4ecef8ad9ca31a8372d0c353",
        "metadata": {},
        "namespace": "namespace",
        "score": 0,
        "values": [
          0
        ]
      }
    ]
  },
  "success": true
}