{"library":"ruvector","title":"RuVector","description":"RuVector is a self-learning vector database for Node.js built in Rust, offering sub-millisecond hybrid search, Graph RAG, FlashAttention-3, HNSW, and DiskANN, with over 50 attention mechanisms. Current stable version is 2.2.0, with frequent releases (weekly to monthly). Key differentiators: single npm package, no external services required, native Node.js performance via Rust native bindings with WASM fallback, TypeScript-first API, and built-in self-learning capabilities. It integrates deeply with the Claude Code ecosystem and provides enterprise-grade features like ONNX embeddings, AST analysis, and security scanning.","language":"javascript","status":"active","last_verified":"Sat Apr 25","install":{"commands":["npm install ruvector"],"cli":null},"imports":["import RuVector from '@ruvector/attention'","import { HybridSearch } from '@ruvector/attention'","import { HNSWIndex } from '@ruvector/attention'"],"auth":{"required":false,"env_vars":[]},"quickstart":{"code":"import RuVector, { HNSWIndex, HybridSearch, FlashAttention } from '@ruvector/attention'\n\n// Create a new vector database instance\nconst db = new RuVector({ dimension: 384, metric: 'cosine' })\n\n// Add vectors with metadata\nconst id1 = await db.add([0.1, 0.2, 0.3, /* ... 384-d vector */], { label: 'doc1' })\nconst id2 = await db.add([0.4, 0.5, 0.6, /* ... */], { label: 'doc2' })\n\n// Perform hybrid search (sparse + dense fusion)\nconst hybrid = new HybridSearch(db, { alpha: 0.5 })\nconst results = await hybrid.search([0.1, 0.2, 0.3], { topK: 5, rerank: true })\nconsole.log('Hybrid results:', results)\n\n// Use FlashAttention-3 for exact nearest neighbor\nconst attn = new FlashAttention({ heads: 8, headDim: 64 })\nconst scores = await attn.compute(queryVectors, keyVectors)\n\n// Build HNSW index for fast approximate search\nconst index = new HNSWIndex({ dimension: 384, M: 16, efConstruction: 200 })\nawait index.build(vectors)\nconst neighbors = await index.search(query, 10)\nconsole.log('ANN neighbors:', neighbors)\n\n// Persist to disk using DiskANN\nawait db.save('./my_index.ruv')","lang":"typescript","description":"Demonstrates core operations: creating a vector database, adding vectors, hybrid search, FlashAttention-3, and HNSW indexing.","tag":null,"tag_description":null,"last_tested":null,"results":[]},"compatibility":null}