[−][src]Crate hnsw
Re-exports
pub use candidates::*; |
pub use generic_array::typenum; |
Modules
candidates |
Structs
Euclidean | Any list, vector, etc of floats wrapped in |
GenericArray | Struct representing a generic array - |
HNSW | This provides a HNSW implementation for any distance function. |
Hamming | Treats each bit contained in this struct as its own dimension and distance is computed as hamming distance. |
Params | |
Searcher | Contains all the state used when searching the HNSW |
Traits
ArrayLength | Trait making |
Distance | This is the primary trait used by the HNSW. This is also implemented for |
FloatingDistance | Implement this trait when your features have a floating point distance between them. You will take no performance
penalty for doing so. Please ensure your distance satisfies the conditions on |
Type Definitions
f32x2 | A 64-bit vector with 2 |
f32x4 | A 128-bit vector with 4 |
f32x8 | A 256-bit vector with 8 |
f32x16 | A 512-bit vector with 16 |
u128x2 | A 256-bit vector with 2 |
u128x4 | A 512-bit vector with 4 |