Qdrant · Schema

BinaryQuantizationConfig

AIArtificial IntelligenceVector Databases

Properties

Name Type Description
always_ram boolean
encoding object
query_encoding object Asymmetric quantization configuration allows a query to have different quantization than stored vectors. It can increase the accuracy of search at the cost of performance.
View JSON Schema on GitHub

JSON Schema

qdrant-binaryquantizationconfig-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/BinaryQuantizationConfig",
  "title": "BinaryQuantizationConfig",
  "type": "object",
  "properties": {
    "always_ram": {
      "type": "boolean",
      "nullable": true
    },
    "encoding": {
      "anyOf": [
        {
          "$ref": "#/components/schemas/BinaryQuantizationEncoding"
        },
        {
          "nullable": true
        }
      ]
    },
    "query_encoding": {
      "description": "Asymmetric quantization configuration allows a query to have different quantization than stored vectors. It can increase the accuracy of search at the cost of performance.",
      "anyOf": [
        {
          "$ref": "#/components/schemas/BinaryQuantizationQueryEncoding"
        },
        {
          "nullable": true
        }
      ]
    }
  }
}