Qdrant · Schema

QuantizationSearchParams

Additional parameters of the search

AIArtificial IntelligenceVector Databases

Properties

Name Type Description
ignore boolean If true, quantized vectors are ignored. Default is false.
rescore boolean If true, use original vectors to re-score top-k results. Might require more time in case if original vectors are stored on disk. If not set, qdrant decides automatically apply rescoring or not.
oversampling number Oversampling factor for quantization. Default is 1.0. Defines how many extra vectors should be preselected using quantized index, and then re-scored using original vectors. For example, if `oversampli
View JSON Schema on GitHub

JSON Schema

qdrant-quantizationsearchparams-schema.json Raw ↑ 
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/QuantizationSearchParams",
  "title": "QuantizationSearchParams",
  "description": "Additional parameters of the search",
  "type": "object",
  "properties": {
    "ignore": {
      "description": "If true, quantized vectors are ignored. Default is false.",
      "default": false,
      "type": "boolean"
    },
    "rescore": {
      "description": "If true, use original vectors to re-score top-k results. Might require more time in case if original vectors are stored on disk. If not set, qdrant decides automatically apply rescoring or not.",
      "type": "boolean",
      "nullable": true
    },
    "oversampling": {
      "description": "Oversampling factor for quantization. Default is 1.0.\n\nDefines how many extra vectors should be preselected using quantized index, and then re-scored using original vectors.\n\nFor example, if `oversampling` is 2.4 and `limit` is 100, then 240 vectors will be preselected using quantized index, and then top-100 will be returned after re-scoring.",
      "type": "number",
      "format": "double",
      "minimum": 1,
      "nullable": true
    }
  }
}