mirror of
https://github.com/ruvnet/RuVector.git
synced 2026-05-25 23:24:03 +00:00
* feat(ospipe): implement OSpipe screenpipe integration with WASM + TypeScript SDK Adds the OSpipe crate providing a quantum-enhanced screenpipe integration layer: - Rust core library (7 modules): capture, storage, search, pipeline, safety, config, wasm - WASM bindings via wasm-bindgen for browser deployment - TypeScript SDK (@ruvector/ospipe) with SSE streaming and hybrid search - Frame deduplication, PII safety gate, query routing, cosine similarity search - 56 tests passing (24 unit + 32 integration), builds for native + wasm32 - Comprehensive ADR with Windows/macOS/Linux/WASM integration plans - CI stub for cross-platform matrix builds (Linux, Windows, macOS, WASM) Co-Authored-By: claude-flow <ruv@ruv.net> * chore(ospipe): add README, fix clippy warnings, optimize dedup and pipeline - Add comprehensive README.md with features, comparison tables, quick start guides, collapsed configuration reference, and API docs - Fix all default clippy warnings (auto-fix + manual) - Replace Vec with VecDeque in FrameDeduplicator for O(1) eviction - Remove redundant frame.clone() in ingestion pipeline (move instead) - Add is_empty() to WASM OsPipeWasm type - Fix broken intra-doc link for cfg-gated bindings module - Remove unused imports in integration tests (FrameContent, SearchConfig) Co-Authored-By: claude-flow <ruv@ruv.net> * feat(ospipe): integrate graph, attention, GNN, and quantum crates (Phase 2-4) Add four new OSpipe modules integrating RuVector crates: - graph: KnowledgeGraph wrapping ruvector-graph with heuristic entity extraction (URLs, emails, @mentions, capitalized phrases), entity/ relationship CRUD, and frame entity ingestion - search/reranker: AttentionReranker using ruvector-attention scaled dot-product attention for result re-ranking (0.6*attention + 0.4*cosine) - learning: SearchLearner with EWC (ruvector-gnn) for continual learning without catastrophic forgetting, ReplayBuffer for feedback, and EmbeddingQuantizer for age-based vector compression - quantum: QuantumSearch using ruqu-algorithms QAOA for diversity selection, Grover-inspired amplitude boosting, and optimal iteration estimation All modules use cfg-gated dual implementations (native + WASM stub). 60 tests passing (59 integration + 1 doc-test), native + WASM builds clean. Co-Authored-By: claude-flow <ruv@ruv.net> * feat(ospipe): complete all 15 gap items — HNSW, persistence, REST API, MMR, safety fixes Implements all remaining OSpipe features from the gap analysis: High — Core functionality: - HNSW indexing via ruvector-core with O(log n) ANN search (HnswVectorStore) - EmbeddingModel trait + RuvectorEmbeddingModel for pluggable embedding backends - JSON-file persistence layer (PersistenceLayer) for frames and config - Axum REST API server matching TypeScript SDK endpoints (/search, /graph, /health, /stats, /route) - Enhanced search pipeline wired into ingestion (router -> rerank -> quantum diversity) Medium — Correctness: - WASM/native routing consistency (aligned keyword sets and priority order) - WASM/native safety consistency (email detection, deny keywords, CC/SSN patterns) - MMR (Maximal Marginal Relevance) reranker for diversity vs relevance tradeoff - Delete and update_metadata APIs on VectorStore and HnswVectorStore - Email redaction preserves surrounding whitespace (tabs, newlines, multi-space) Lower — Polish: - TypeScript SDK: fetchWithRetry with exponential backoff, timeout, AbortSignal - console_error_panic_hook init in WASM module - WASM test scaffold (tests/wasm.rs) - Quantization tiers in config (None -> Scalar -> Product -> Binary by age) - All clippy warnings resolved (0 warnings) 82 tests passing, 1 doc-test passing, 0 clippy warnings. Co-Authored-By: claude-flow <ruv@ruv.net> * chore: update Cargo.lock after OSpipe dependency changes Co-Authored-By: claude-flow <ruv@ruv.net> * feat(ospipe): add server binary, WASM build, version-pin deps for publishing - Add ospipe-server binary with CLI args (--port, --data-dir, --help, --version) - Add tracing-subscriber for structured logging - Version-pin all 9 path dependencies for crates.io readiness - Fix ref -> ref mut for KnowledgeGraph mutable borrow in pipeline - Fix redundant rustdoc link in embedding.rs - Update ospipe-wasm package.json to match wasm-pack output filenames - WASM build produces 145KB binary with full browser API Build artifacts (not committed, in dist/): - ospipe-server-linux-x86_64 (1.8MB) - ospipe-server-linux-arm64 (1.6MB) - ospipe-server-windows-x86_64.exe (3.9MB) - ospipe_bg.wasm (145KB) - @ruvector/ospipe npm tarball (13.9KB) Co-Authored-By: claude-flow <ruv@ruv.net> * docs: add OSpipe to root README, publish ospipe + deps to crates.io Add OSpipe personal AI memory section to root README with features, comparison table, install commands, and Rust quickstart. Published to registries: - ospipe v0.1.0 (crates.io) - ruvector-delta-core v0.1.0 (crates.io) - ruvector-cluster v2.0.2 (crates.io) - ruvector-router-core v2.0.2 (crates.io) - @ruvector/ospipe v0.1.0 (npm) - @ruvector/ospipe-wasm v0.1.0 (npm) Co-Authored-By: claude-flow <ruv@ruv.net> * fix: add uuid dev-dep for tests, bump rvlite to 0.2.1 - Add uuid to OSpipe dev-dependencies to fix version mismatch in integration tests - Bump rvlite npm package to 0.2.1 (0.2.0 blocked by npm) Co-Authored-By: claude-flow <ruv@ruv.net> |
||
|---|---|---|
| .. | ||
| agentic-jujutsu | ||
| apify | ||
| benchmarks | ||
| data | ||
| delta-behavior | ||
| dna | ||
| docs | ||
| edge | ||
| edge-full/pkg | ||
| edge-net | ||
| exo-ai-2025 | ||
| google-cloud | ||
| graph | ||
| meta-cognition-spiking-neural-network | ||
| mincut | ||
| neural-trader | ||
| nodejs | ||
| onnx-embeddings | ||
| onnx-embeddings-wasm | ||
| OSpipe | ||
| prime-radiant | ||
| refrag-pipeline | ||
| rust | ||
| ruvLLM | ||
| scipix | ||
| spiking-network | ||
| subpolynomial-time | ||
| ultra-low-latency-sim | ||
| vibecast-7sense | ||
| vwm-viewer | ||
| wasm/ios | ||
| wasm-react | ||
| wasm-vanilla | ||
| bounded_instance_demo.rs | ||
| README.md | ||
RuVector Examples
Comprehensive examples demonstrating RuVector's capabilities across multiple platforms and use cases.
Directory Structure
examples/
├── rust/ # Rust SDK examples
├── nodejs/ # Node.js SDK examples
├── graph/ # Graph database features
├── wasm-react/ # React + WebAssembly integration
├── wasm-vanilla/ # Vanilla JS + WebAssembly
├── agentic-jujutsu/ # AI agent version control
├── exo-ai-2025/ # Advanced cognitive substrate
├── refrag-pipeline/ # Document processing pipeline
└── docs/ # Additional documentation
Quick Start by Platform
Rust
cd rust
cargo run --example basic_usage
cargo run --example advanced_features
cargo run --example agenticdb_demo
Node.js
cd nodejs
npm install
node basic_usage.js
node semantic_search.js
WebAssembly (React)
cd wasm-react
npm install
npm run dev
WebAssembly (Vanilla)
cd wasm-vanilla
# Open index.html in browser
Example Categories
| Category | Directory | Description |
|---|---|---|
| Core API | rust/basic_usage.rs |
Vector DB fundamentals |
| Batch Ops | rust/batch_operations.rs |
High-throughput ingestion |
| RAG Pipeline | rust/rag_pipeline.rs |
Retrieval-Augmented Generation |
| Advanced | rust/advanced_features.rs |
Hypergraphs, neural hashing |
| AgenticDB | rust/agenticdb_demo.rs |
AI agent memory system |
| GNN | rust/gnn_example.rs |
Graph Neural Networks |
| Graph | graph/ |
Cypher queries, clustering |
| Node.js | nodejs/ |
JavaScript integration |
| WASM React | wasm-react/ |
Modern React apps |
| WASM Vanilla | wasm-vanilla/ |
Browser without framework |
| Agentic Jujutsu | agentic-jujutsu/ |
Multi-agent version control |
| EXO-AI 2025 | exo-ai-2025/ |
Cognitive substrate research |
| Refrag | refrag-pipeline/ |
Document fragmentation |
Feature Highlights
Vector Database Core
- High-performance similarity search
- Multiple distance metrics (Cosine, Euclidean, Dot Product)
- Metadata filtering
- Batch operations
Advanced Features
- Hypergraph Index: Multi-entity relationships
- Temporal Hypergraph: Time-aware relationships
- Causal Memory: Cause-effect chains
- Learned Index: ML-optimized indexing
- Neural Hash: Locality-sensitive hashing
- Topological Analysis: Persistent homology
AgenticDB
- Reflexion episodes (self-critique)
- Skill library (consolidated patterns)
- Causal memory (hypergraph relationships)
- Learning sessions (RL training data)
- Vector embeddings (core storage)
EXO-AI Cognitive Substrate
- exo-core: IIT consciousness, thermodynamics
- exo-temporal: Causal memory coordination
- exo-hypergraph: Topological structures
- exo-manifold: Continuous deformation
- exo-exotic: 10 cutting-edge experiments
- exo-wasm: Browser deployment
- exo-federation: Distributed consensus
- exo-node: Native bindings
- exo-backend-classical: Classical compute
Running Benchmarks
# Rust benchmarks
cargo bench --example advanced_features
# Refrag pipeline benchmarks
cd refrag-pipeline
cargo bench
# EXO-AI benchmarks
cd exo-ai-2025
cargo bench
Related Documentation
License
MIT OR Apache-2.0