Weaviate · Schema

BM25Config

Tuning parameters for the BM25 algorithm.

Vector DatabaseAIMachine LearningSemantic SearchOpen SourceGraphQLKubernetes

Properties

Name Type Description
k1 number Calibrates term-weight scaling based on the term frequency within a document (default: 1.2).
b number Calibrates term-weight scaling based on the document length (default: 0.75).
View JSON Schema on GitHub

JSON Schema

weaviate-bm25-config-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://api-evangelist.github.io/weaviate/json-schema/weaviate-bm25-config-schema.json",
  "title": "BM25Config",
  "description": "Tuning parameters for the BM25 algorithm.",
  "type": "object",
  "properties": {
    "k1": {
      "type": "number",
      "format": "float",
      "description": "Calibrates term-weight scaling based on the term frequency within a document (default: 1.2)."
    },
    "b": {
      "type": "number",
      "format": "float",
      "description": "Calibrates term-weight scaling based on the document length (default: 0.75)."
    }
  }
}