## New Documentation: ### docs/FIND_SYSTEM.md (Complete Find Guide): - Triple Intelligence architecture (vector + metadata + graph) - All query types: NLP, structured, proximity, graph traversal - Detailed index usage: HNSW, HashMap, Sorted arrays, Adjacency maps - Type-aware NLP processing with dynamic field discovery - Query execution flow with parallel search and fusion scoring - Performance characteristics and scalability metrics - Real-world query examples with execution plans ### docs/PERFORMANCE.md (Updated): - Added type-aware NLP performance metrics - Updated metadata index to show incremental sorted indices - Added type embeddings and field affinity memory usage - Corrected sorted index behavior (no more lazy loading) - New performance table with type detection and field matching ## Key Features Documented: ✅ Zero hardcoded fields (only 30+ noun, 40+ verb types) ✅ Dynamic field discovery from real data patterns ✅ Type-field affinity tracking and optimization ✅ Semantic field matching: 'by' → 'author' (87% confidence) ✅ Field-type validation with intelligent suggestions ✅ O(1) graph queries, O(log n) range queries, O(1) exact matches ✅ Sub-millisecond performance at scale with measured benchmarks This documents the most advanced query system in any vector database. |
||
|---|---|---|
| .. | ||
| api | ||
| architecture | ||
| augmentations | ||
| deployment | ||
| features | ||
| guides | ||
| API_REFERENCE.md | ||
| CREATING-AUGMENTATIONS.md | ||
| EXTENDING_STORAGE.md | ||
| FIND_SYSTEM.md | ||
| METADATA_CONTRACT_IMPLEMENTATION.md | ||
| MODEL_LOADING_QUICK_REFERENCE.md | ||
| PERFORMANCE.md | ||
| QUICK-START.md | ||
| README.md | ||
| RELEASE-GUIDE.md | ||
| SCALING.md | ||
| troubleshooting.md | ||
| universal-display-augmentation.md | ||
| ZERO_CONFIG.md | ||
Brainy Documentation
Welcome to the comprehensive documentation for Brainy, the multi-dimensional AI database with Triple Intelligence Engine.
📊 Implementation Status
- ✅ Production Ready: Core features working today
- 🚧 In Development: Features coming soon
- 📅 Roadmap: See ROADMAP.md
Quick Links
Getting Started
- Quick Start Guide - Get up and running in minutes
- Enterprise for Everyone - No limits, no tiers, everything free
- Natural Language Queries - Query with plain English
Core Concepts
- Zero Configuration - Auto-adapts to any environment
- Noun-Verb Taxonomy - Revolutionary data model
- Triple Intelligence - Unified query system
- Architecture Overview - System design
API Documentation
- API Reference - Complete API documentation
- TypeScript Types - Type definitions
Advanced Topics
- Augmentations System - Enterprise plugins & neural import
- Storage Architecture - Storage adapter system
- Performance Tuning - Optimization guide
- Migration Guide - Upgrading from 1.x
What is Brainy?
Brainy is a next-generation AI database that combines:
- Vector Search: Semantic similarity using HNSW indexing
- Graph Relationships: Complex relationship mapping and traversal
- Field Filtering: Precise metadata filtering with O(1) lookups
- Natural Language: Query in plain English
Key Features
🧠 Triple Intelligence Engine
All three intelligence types (vector, graph, field) work together in every query for optimal results.
📝 Noun-Verb Taxonomy
Model your data naturally as entities (nouns) and relationships (verbs) - no complex schemas needed.
🌍 Natural Language Queries
Ask questions in plain English and Brainy understands your intent:
await brain.find("recent articles about AI with high ratings")
⚡ Production Ready
- Universal storage (FileSystem, S3, OPFS, Memory)
- Zero configuration with intelligent defaults
- Full TypeScript support
- Cross-platform compatibility
Quick Example
import { BrainyData } from 'brainy'
// Initialize
const brain = new BrainyData()
await brain.init()
// Add entities (nouns)
const articleId = await brain.addNoun("Revolutionary AI Breakthrough", {
type: "article",
category: "technology",
rating: 4.8
})
const authorId = await brain.addNoun("Dr. Sarah Chen", {
type: "person",
role: "researcher"
})
// Create relationships (verbs)
await brain.addVerb(authorId, articleId, "authored", {
date: "2024-01-15",
contribution: "primary"
})
// Query naturally
const results = await brain.find("highly rated technology articles by researchers")
Documentation Structure
docs/
├── README.md # This file
├── guides/ # User guides
│ ├── getting-started.md # Quick start guide
│ ├── natural-language.md # NLP query guide
│ └── performance.md # Performance tuning
├── architecture/ # Technical architecture
│ ├── overview.md # System overview
│ ├── noun-verb-taxonomy.md # Data model
│ ├── triple-intelligence.md # Query system
│ └── storage.md # Storage layer
└── api/ # API documentation
├── README.md # API overview
├── brainy-data.md # Main class
└── types.md # TypeScript types
Community
- GitHub: github.com/brainy-org/brainy
- Issues: Report bugs or request features
- Discussions: Join the conversation
License
Brainy is MIT licensed. See LICENSE for details.