- Introduced a new WebAssembly binary file `rvlite_bg.wasm` for the rvlite project.
- Added TypeScript definitions in `rvlite_bg.wasm.d.ts` to expose various functions and memory management for the WebAssembly module.
This commit addresses GitHub issue #17 by implementing comprehensive
forgetting mitigation for continual learning in the GNN module.
## New Features
### Optimizer Implementation (training.rs)
- Full Adam optimizer with bias-corrected first and second moments
- SGD with momentum support
- Lazy initialization of state buffers for efficiency
### Replay Buffer (replay.rs)
- Experience replay with reservoir sampling for uniform distribution
- Distribution shift detection with statistical tracking
- Configurable capacity and batch sampling
### Elastic Weight Consolidation (ewc.rs)
- Fisher information diagonal computation
- Anchor weight consolidation for task boundaries
- EWC penalty and gradient computation
### Learning Rate Scheduling (scheduler.rs)
- Constant, StepDecay, Exponential schedulers
- CosineAnnealing with warm restarts
- WarmupLinear for pre-training warmup
- ReduceOnPlateau for adaptive learning
## Deployment Infrastructure
### GitHub Actions Release Pipeline (.github/workflows/release.yml)
- 8-stage CI/CD pipeline for complete releases
- Validates, builds crates, WASM, and native modules
- Publishes to crates.io and npmjs.com
- Creates GitHub releases with artifacts
### Deployment Script (scripts/deploy.sh)
- Comprehensive deployment orchestration
- Version synchronization across Cargo.toml and package.json
- Dry-run mode for testing
- Cross-platform native builds support
## Test Coverage
- 177 tests passing in ruvector-gnn
- Comprehensive tests for all new modules
- Convergence tests for optimizers
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
New features exposed to Node.js:
- CollectionManager: Multi-collection support with aliases
- getMetrics(): Prometheus metrics endpoint
- getHealth(): Health status with uptime tracking
- Filter: Metadata-based search filtering
Updates:
- Rebuilt Linux x64 and ARM64 binaries with new features
- Updated all package versions to 0.1.15
- Enhanced TypeScript definitions with new interfaces
- Added commit-binaries job to CI workflow
- Fixed macos-15-intel -> macos-13 in CI matrix
- Added build scripts in scripts/build/
Note: macOS and Windows binaries will be built by CI
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major new package implementing a distributed hypergraph database with:
## Core Components (crates/ruvector-graph/)
- Cypher-compatible query parser with lexer, AST, optimizer
- Query execution engine with SIMD optimization and parallel execution
- ACID transaction support with MVCC isolation levels
- Distributed consensus and federation layer
- Vector-graph hybrid queries for AI/RAG workloads
- Performance optimizations (100x faster than Neo4j target)
## Bindings
- WASM bindings (crates/ruvector-graph-wasm/)
- NAPI-RS Node.js bindings (crates/ruvector-graph-node/)
- NPM packages for both targets
## CLI Integration
- 8 new graph commands: create, query, shell, import, export, info, benchmark, serve
## CI/CD
- Updated build-native.yml for graph packages
- New graph-ci.yml for testing and benchmarks
- New graph-release.yml for automated publishing
## Data Generation
- OpenRouter/Kimi K2 integration (packages/graph-data-generator/)
- Agentic-synth benchmark suite integration
## Tests & Benchmarks
- 11 test files covering all components
- Criterion benchmarks for performance validation
- Neo4j compatibility test suite
## Architecture Highlights
- CSR graph layout for cache-friendly access
- SIMD-vectorized query operators
- Roaring bitmaps for label indexes
- Bloom filters for fast negative lookups
- Adaptive radix tree for property indexes
Note: This is a comprehensive implementation created by 15 parallel agents.
Some integration fixes may be needed to resolve cross-module dependencies.
Co-authored-by: Claude AI Swarm <swarm@claude.ai>
