Struct RuvectorCapabilities 

pub struct RuvectorCapabilities {
    pub hnsw: bool,
    pub attention: bool,
    pub graph: bool,
    pub gnn: bool,
    pub sona: bool,
    pub simd: bool,
    pub parallel: bool,
    pub quantization_level: u8,
    pub max_efficient_dim: usize,
    pub estimated_ops_per_sec: u64,
}

Ruvector capabilities flags

Indicates which Ruvector features are available at runtime. Use detect() to get the current capabilities.

Fields

hnsw: bool

HNSW index is available for approximate nearest neighbor search

attention: bool

Flash Attention is available for efficient inference

graph: bool

Knowledge graph is available for relationship learning

gnn: bool

Graph neural networks are available for complex reasoning

sona: bool

SONA learning framework is available

simd: bool

SIMD acceleration is available

parallel: bool

Parallel processing is available

quantization_level: u8

Quantization support level (0=none, 1=scalar, 2=int4, 3=product)

max_efficient_dim: usize

Maximum embedding dimension supported efficiently

estimated_ops_per_sec: u64

Estimated ops/sec for 512-dim vectors

Implementations

impl RuvectorCapabilities

pub fn detect() -> Self

Detect available Ruvector capabilities

This function probes the system to determine which features are available. Results are cached for subsequent calls.

Example

use ruvllm::capabilities::RuvectorCapabilities;

let caps = RuvectorCapabilities::detect();
if caps.hnsw {
    println!("HNSW indexing available");
}
if caps.attention {
    println!("Flash Attention available");
}

pub fn cached() -> &'static Self

Get cached capabilities (same as detect but more explicit)

pub fn redetect() -> Self

Force re-detection of capabilities

Note: This is generally not needed as capabilities don’t change at runtime. This function creates a new detection but cannot update the cached value.

pub fn full_intelligence(&self) -> bool

Check if all intelligence features are available

pub fn graph_reasoning(&self) -> bool

Check if graph reasoning is available

pub fn summary(&self) -> String

Get feature summary string

pub fn recommended_batch_size(&self) -> usize

Get recommended batch size based on capabilities

pub fn recommended_hnsw_params(&self) -> (usize, usize, usize)

Get recommended HNSW parameters based on capabilities

Trait Implementations

impl Clone for RuvectorCapabilities

fn clone(&self) -> RuvectorCapabilities

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Copy for RuvectorCapabilities

impl Debug for RuvectorCapabilities

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for RuvectorCapabilities

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for RuvectorCapabilities

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for RuvectorCapabilities

impl PartialEq for RuvectorCapabilities

fn eq(&self, other: &RuvectorCapabilities) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for RuvectorCapabilities

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for RuvectorCapabilities