v1

latestOpenAPI 3.0.3Apache 2.02026-07-1372170520.1 KB

Vector Operations

Get index stats

Return statistics about the contents of an index, including the vector count per namespace, the number of dimensions, and the index fullness.

Serverless indexes scale automatically as needed, so index fullness is relevant only for pod-based indexes.

post/describe_index_stats

Headers

X-Pinecone-Api-Versionstring required

Required date-based version header

Request body

filterobject

If this parameter is present, the operation only returns statistics for vectors that satisfy the filter. See Understanding metadata.

Serverless indexes do not support filtering describe_index_stats by metadata.

Response

A successful response.

namespacesobject

A mapping for each namespace in the index from the namespace name to a summary of its contents. If a metadata filter expression is present, the summary will reflect only vectors matching that expression.

dimensioninteger

The dimension of the indexed vectors. Not specified if sparse index.

indexFullnessnumber float

The fullness of the index, regardless of whether a metadata filter expression was passed. The granularity of this metric is 10%.

Serverless indexes scale automatically as needed, so index fullness is relevant only for pod-based indexes.

The index fullness result may be inaccurate during pod resizing; to get the status of a pod resizing process, use describe_index.

totalVectorCountinteger

The total number of vectors in the index, regardless of whether a metadata filter expression was passed

metricstring

The metric used to measure similarity.

vectorTypestring

The type of vectors stored in the index.

memory_fullnessnumber float

The amount of memory used by a dedicated index

storage_fullnessnumber float

The amount of storage used by a dedicated index

Example response

{
  "dimension": 1024,
  "index_fullness": 0.4,
  "namespaces": {
    "": {
      "vectorCount": 50000
    },
    "example-namespace-2": {
      "vectorCount": 30000
    }
  },
  "totalVectorCount": 80000
}