Crate ruvector_gnn_wasm 

WebAssembly bindings for RuVector GNN

This module provides high-performance browser bindings for Graph Neural Network operations on HNSW topology, including:

• GNN layer forward passes
• Tensor compression with adaptive level selection
• Differentiable search with soft attention
• Hierarchical forward propagation

Structs

JsRuvectorLayer

Graph Neural Network layer for HNSW topology

JsTensorCompress

Tensor compressor with adaptive level selection

SearchConfig

Query configuration for differentiable search

Functions

cosine_similarity

Compute cosine similarity between two vectors

differentiable_search

Differentiable search using soft attention mechanism

hierarchical_forward

Hierarchical forward pass through multiple GNN layers

init

Initialize panic hook for better error messages

version

Get version information