Function differentiable_search 

pub fn differentiable_search(
    query: Float32Array,
    candidate_embeddings: Vec<Float32Array>,
    k: u32,
    temperature: f64,
) -> Result<SearchResult>

Differentiable search using soft attention mechanism

Arguments

• query - The query vector (Float32Array)
• candidate_embeddings - List of candidate embedding vectors (Array of Float32Array)
• k - Number of top results to return
• temperature - Temperature for softmax (lower = sharper, higher = smoother)

Returns

Search result with indices and soft weights

Example

const query = new Float32Array([1.0, 0.0, 0.0]);
const candidates = [new Float32Array([1.0, 0.0, 0.0]), new Float32Array([0.9, 0.1, 0.0]), new Float32Array([0.0, 1.0, 0.0])];
const result = differentiableSearch(query, candidates, 2, 1.0);
console.log(result.indices); // [0, 1]
console.log(result.weights); // [0.x, 0.y]