pub struct HybridQuery<'a> {
pub anchor_node: &'a str,
pub embedding: &'a [f32],
pub collection: &'a str,
pub graph_depth: usize,
pub top_k: usize,
pub alpha: f64,
pub filter: Option<Value>,
}Expand description
Parameters for a hybrid graph + vector query.
Fields§
§anchor_node: &'a strThe memory-graph node to start traversal from.
embedding: &'a [f32]Query embedding to rank against the vector collection.
collection: &'a strName of the vector collection to search.
graph_depth: usizeMaximum graph traversal depth from anchor_node.
top_k: usizeMaximum number of results to return after blending.
alpha: f64Interpolation factor between vector similarity and graph proximity.
0.0 = pure graph weight, 1.0 = pure vector similarity.
filter: Option<Value>Optional metadata filter applied before vector scoring.
Auto Trait Implementations§
impl<'a> Freeze for HybridQuery<'a>
impl<'a> RefUnwindSafe for HybridQuery<'a>
impl<'a> Send for HybridQuery<'a>
impl<'a> Sync for HybridQuery<'a>
impl<'a> Unpin for HybridQuery<'a>
impl<'a> UnsafeUnpin for HybridQuery<'a>
impl<'a> UnwindSafe for HybridQuery<'a>
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more