Qdrant · Schema

VectorParams

Params of single vector data storage

AIArtificial IntelligenceVector Databases

Properties

Name Type Description
size integer Size of a vectors used
distance object
hnsw_config object Custom params for HNSW index. If none - values from collection configuration are used.
quantization_config object Custom params for quantization. If none - values from collection configuration are used.
on_disk boolean If true, vectors are served from disk, improving RAM usage at the cost of latency Default: false
datatype object Defines which datatype should be used to represent vectors in the storage. Choosing different datatypes allows to optimize memory usage and performance vs accuracy. - For `float32` datatype - vectors
multivector_config object
View JSON Schema on GitHub

JSON Schema

qdrant-vectorparams-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/VectorParams",
  "title": "VectorParams",
  "description": "Params of single vector data storage",
  "type": "object",
  "required": [
    "distance",
    "size"
  ],
  "properties": {
    "size": {
      "description": "Size of a vectors used",
      "type": "integer",
      "format": "uint64",
      "minimum": 1
    },
    "distance": {
      "$ref": "#/components/schemas/Distance"
    },
    "hnsw_config": {
      "description": "Custom params for HNSW index. If none - values from collection configuration are used.",
      "anyOf": [
        {
          "$ref": "#/components/schemas/HnswConfigDiff"
        },
        {
          "nullable": true
        }
      ]
    },
    "quantization_config": {
      "description": "Custom params for quantization. If none - values from collection configuration are used.",
      "anyOf": [
        {
          "$ref": "#/components/schemas/QuantizationConfig"
        },
        {
          "nullable": true
        }
      ]
    },
    "on_disk": {
      "description": "If true, vectors are served from disk, improving RAM usage at the cost of latency Default: false",
      "type": "boolean",
      "nullable": true
    },
    "datatype": {
      "description": "Defines which datatype should be used to represent vectors in the storage. Choosing different datatypes allows to optimize memory usage and performance vs accuracy.\n\n- For `float32` datatype - vectors are stored as single-precision floating point numbers, 4 bytes. - For `float16` datatype - vectors are stored as half-precision floating point numbers, 2 bytes. - For `uint8` datatype - vectors are stored as unsigned 8-bit integers, 1 byte. It expects vector elements to be in range `[0, 255]`.",
      "anyOf": [
        {
          "$ref": "#/components/schemas/Datatype"
        },
        {
          "nullable": true
        }
      ]
    },
    "multivector_config": {
      "anyOf": [
        {
          "$ref": "#/components/schemas/MultiVectorConfig"
        },
        {
          "nullable": true
        }
      ]
    }
  }
}