Qdrant · Schema
SparseIndexParams
Configuration for sparse inverted index.
AIArtificial IntelligenceVector Databases
Properties
| Name | Type | Description |
|---|---|---|
| full_scan_threshold | integer | We prefer a full scan search upto (excluding) this number of vectors. Note: this is number of vectors, not KiloBytes. |
| on_disk | boolean | Store index on disk. If set to false, the index will be stored in RAM. Default: false |
| datatype | object | Defines which datatype should be used for the index. Choosing different datatypes allows to optimize memory usage and performance vs accuracy. - For `float32` datatype - vectors are stored as single-p |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "#/components/schemas/SparseIndexParams",
"title": "SparseIndexParams",
"description": "Configuration for sparse inverted index.",
"type": "object",
"properties": {
"full_scan_threshold": {
"description": "We prefer a full scan search upto (excluding) this number of vectors.\n\nNote: this is number of vectors, not KiloBytes.",
"type": "integer",
"format": "uint",
"minimum": 0,
"nullable": true
},
"on_disk": {
"description": "Store index on disk. If set to false, the index will be stored in RAM. Default: false",
"type": "boolean",
"nullable": true
},
"datatype": {
"description": "Defines which datatype should be used for the index. 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 quantized to unsigned 8-bit integers, 1 byte. Quantization to fit byte range `[0, 255]` happens during indexing automatically, so the actual vector data does not need to conform to this range.",
"anyOf": [
{
"$ref": "#/components/schemas/Datatype"
},
{
"nullable": true
}
]
}
}
}