Claude 2e4eafead0 feat: Add ruvector-gnn crate with GNN, compression, WASM and Node.js bindings ... Major additions: - ruvector-gnn: Complete GNN implementation with RuvectorLayer, multi-head attention, GRU cell - Tensor compression: 5-tier adaptive compression (f32→f16→PQ8→PQ4→Binary, 2-32x) - Differentiable search: Soft attention k-NN with gradient flow - Training: InfoNCE contrastive loss, SGD optimizer - Query API: RuvectorQuery, QueryResult, SubGraph types - MmapManager: Memory-mapped embeddings with gradient accumulation - Tensor operations: Full tensor math library Bindings: - ruvector-gnn-wasm: Full WASM bindings for browser - ruvector-gnn-node: napi-rs bindings for Node.js Fixes: - WASM compatibility for ruvector-graph (conditional compilation) - Feature flags for storage/hnsw modules Updated README with GNN architecture overview and tutorials		2025-11-26 04:50:36 +00:00
..
benches	perf: Add benchmarks and optimize new capabilities	2025-11-26 03:19:08 +00:00
examples	fix: Resolve compilation errors in ruvector-graph crate	2025-11-25 23:42:29 +00:00
src	feat: Add ruvector-gnn crate with GNN, compression, WASM and Node.js bindings	2025-11-26 04:50:36 +00:00
tests	feat: Implement all previously ignored features	2025-11-26 01:07:57 +00:00
ARCHITECTURE.md	feat: Add Neo4j-compatible hypergraph database package (ruvector-graph)	2025-11-25 23:11:54 +00:00
Cargo.toml	feat: Add ruvector-gnn crate with GNN, compression, WASM and Node.js bindings	2025-11-26 04:50:36 +00:00