aarondb/vec_index/types
Types
Construction and search limits for an HNSW index.
pub type HnswConfig {
HnswConfig(
max_neighbors: Int,
search_budget: Int,
level_source: LevelSource,
)
}Constructors
-
HnswConfig( max_neighbors: Int, search_budget: Int, level_source: LevelSource, )
A single layer in the Hierarchical Navigable Small-World graph.
pub type Layer {
Layer(edges: dict.Dict(fact.EntityId, List(fact.EntityId)))
}Constructors
-
Layer(edges: dict.Dict(fact.EntityId, List(fact.EntityId)))
The source used to choose HNSW insertion levels.
pub type LevelSource {
RandomLevels
DeterministicLevels(List(Int))
}Constructors
-
RandomLevels -
DeterministicLevels(List(Int))
An entity and its cosine-similarity score.
pub type SearchResult {
SearchResult(entity: fact.EntityId, score: Float)
}Constructors
-
SearchResult(entity: fact.EntityId, score: Float)
A Hierarchical Navigable Small-World graph for approximate nearest-neighbor search.
pub type VecIndex {
VecIndex(
nodes: dict.Dict(fact.EntityId, List(Float)),
layers: dict.Dict(Int, Layer),
dimensions: option.Option(Int),
config: HnswConfig,
entry_point: Result(fact.EntityId, Nil),
max_level: Int,
)
}Constructors
-
VecIndex( nodes: dict.Dict(fact.EntityId, List(Float)), layers: dict.Dict(Int, Layer), dimensions: option.Option(Int), config: HnswConfig, entry_point: Result(fact.EntityId, Nil), max_level: Int, )