docs: consolidate and archive redundant documentation

- Archived 13 API design iterations to docs/api-design-archive/
- Consolidated augmentation docs to docs/augmentations-archive/
- Maintained ONE definitive API doc at docs/api/README.md
- Cleaned up documentation structure for 2.0 release
- Preserved all historical documents for reference
This commit is contained in:
David Snelling 2025-08-25 10:15:38 -07:00
parent ef8f35ec2a
commit 994276f09f
35 changed files with 444 additions and 239 deletions

View file

@ -60,11 +60,11 @@ await brain.searchWithinNouns(ids[], query) // Search within specific nouns
### Triple Intelligence 🧠
```typescript
await brain.find(query) // Unified Vector + Graph + Field search
await brain.find(query) // Unified Vector + Graph + Metadata search
// Examples:
await brain.find('documents about AI') // Natural language
await brain.find({ like: 'sample-id' }) // Similar to ID
await brain.find({ where: { type: 'doc' }}) // Field filter
await brain.find({ where: { type: 'doc' }}) // Metadata filter
await brain.find({ connected: { to: id }}) // Graph traversal
```

View file

@ -47,14 +47,14 @@ deleteVerbs(ids[]) // Delete multiple verbs
// Core Search
search(query, k?, options?) // Primary vector search
searchText(text, k?, options?) // Natural language search
find(query) // Triple Intelligence (Vector+Graph+Field) 🧠
find(query) // Triple Intelligence (Vector+Graph+Metadata) 🧠
findSimilar(id, k?, options?) // Find similar to existing noun
// Advanced Search
searchByNounTypes(types[], query, k?) // Filter by noun types
searchWithinItems(query, ids[], k?) // Search within specific nouns
searchWithCursor(query, cursor) // Paginated search
searchByStandardField(field, value, k?) // Field-based search
searchByStandardField(field, value, k?) // Metadata-based search
// Graph Search
searchVerbs(query, options?) // Search relationships
@ -206,7 +206,7 @@ These are now private (use new methods above):
- `addItem()`, `addToBoth()`, `addBatch()`, `getBatch()`
### ✅ Triple Intelligence
- New `find()` method unifies Vector + Graph + Field search
- New `find()` method unifies Vector + Graph + Metadata search
- Most powerful search capability in one simple method
### ✅ Zero-Configuration

View file

@ -48,7 +48,7 @@ find({
// Vector search
like: 'text' | vector | {id: 'noun-id'},
// Field filtering with BRAINY OPERATORS (NOT MongoDB!)
// Metadata filtering with BRAINY OPERATORS (NOT MongoDB!)
where: {
// Direct equality
field: value,
@ -261,7 +261,7 @@ brain.generateRandomGraph(nodes, edges) // Test data
3. **Simple neuralImport** - One method, smart detection
4. **Visualization exports** - For D3, Cytoscape, GraphML
5. **search() is just convenience** - Not a complete alias
6. **find() has Triple Intelligence** - Vector + Graph + Field
6. **find() has Triple Intelligence** - Vector + Graph + Metadata
7. **Proper operator names** - greaterThan not $gt
8. **Complete clustering API** - Fast, large, streaming options
9. **Synapses and Conduits** - External and internal sync

View file

@ -126,7 +126,7 @@ Simple vector similarity search (convenience wrapper)
// Vector similarity
like?: string | number[] | {id: string}, // Text, vector, or noun ID
// Field filtering
// Metadata filtering
where?: {
field: value, // Exact match
field: {$in: [values]}, // In array

View file

@ -242,7 +242,7 @@ mode // Current mode (readonly)
**Neural Import** - Smart AI-powered data import
**Clustering** - Automatic and manual clustering
**Triple Intelligence** - Vector + Graph + Field combined
**Triple Intelligence** - Vector + Graph + Metadata combined
**Verb Scoring** - Intelligent relationship scoring
**Synapses** - External platform connectors
**Conduits** - Brainy-to-Brainy sync

View file

@ -48,7 +48,7 @@ Just TWO methods - simple and powerful:
```typescript
search(query, k?) // Convenience: same as find({like: query, limit: k})
find(query) // TRIPLE INTELLIGENCE: Vector + Graph + Field
find(query) // TRIPLE INTELLIGENCE: Vector + Graph + Metadata
```
### Find Query (with CORRECT Brainy Operators):
@ -229,7 +229,7 @@ BrainyData.warmup() // Warmup
1. **Zero-Config** - Works instantly, no setup
2. **Auto-Embedding** - Text automatically becomes vectors
3. **Triple Intelligence** - Vector + Graph + Field combined
3. **Triple Intelligence** - Vector + Graph + Metadata combined
4. **Brainy Operators** - Clean, legal, no MongoDB style
5. **Complete Neural API** - All clustering/viz features
6. **Simple Import** - One method, auto-detects everything

View file

@ -53,7 +53,7 @@ find('documents about AI')
// Similar to existing noun
find({ like: 'noun-id-123' })
// Field filtering
// Metadata filtering
find({ where: { type: 'article' }})
// Graph traversal
@ -62,7 +62,7 @@ find({ connected: { to: 'id', via: 'references' }})
// Combined queries (Triple Intelligence!)
find({
like: 'sample-doc', // Vector similarity
where: { status: 'published' }, // Field filter
where: { status: 'published' }, // Metadata filter
connected: { via: 'cites' }, // Graph relationships
limit: 10 // Pagination
})
@ -127,7 +127,7 @@ shutdown() // Cleanup
### Why So Simple?
1. **`addNoun()` handles everything** - Text? Auto-embeds. Vector? Uses directly.
2. **`find()` is the ultimate search** - Combines vector, graph, and field search
2. **`find()` is the ultimate search** - Combines vector, graph, and metadata search
3. **`search()` is just convenience** - Simple alias to `find()` for basic queries
4. **No duplicate methods** - One way to do each thing
@ -136,7 +136,7 @@ shutdown() // Cleanup
The `find()` method is your Swiss Army knife:
- Text search → Auto-embeds and searches
- Vector search → `{ like: 'id' }` or `{ like: vector }`
- Field search → `{ where: { field: value }}`
- Metadata search → `{ where: { field: value }}`
- Graph search → `{ connected: { to/from: 'id' }}`
- Combine them all → Triple Intelligence!

View file

@ -54,7 +54,7 @@ search(query, k?) // Simple vector search
// Equivalent to: find({like: query, limit: k})
find(query) // TRIPLE INTELLIGENCE 🧠
// Combines Vector + Graph + Field search
// Combines Vector + Graph + Metadata search
```
### Find Query Structure
@ -329,7 +329,7 @@ brain.initialized // Is initialized?
1. **Brainy Operators** - NOT MongoDB style ($gt, $lt)
2. **Neural API** - Complete with visualization export
3. **Simple Search** - Just `search()` and `find()`
4. **Triple Intelligence** - Vector + Graph + Field in `find()`
4. **Triple Intelligence** - Vector + Graph + Metadata in `find()`
5. **Auto-embedding** - `addNoun()` accepts text directly
6. **Unified Methods** - `getNouns()` handles all plural queries
7. **Clean Architecture** - Augmentation system for extensibility

View file

@ -60,7 +60,7 @@ searchByNounTypes(types[], query) // Filter by noun types
searchWithinItems(query, ids[], k?) // Search within specific nouns
searchVerbs(query) // Search relationships
searchNounsByVerbs(conditions) // Graph-based noun search
searchByStandardField(field, value) // Field-based search
searchByStandardField(field, value) // Metadata-based search
```
### Distributed Search

View file

@ -47,14 +47,14 @@ deleteVerbs(ids[]) // Delete multiple verbs
// Core Search
search(query, k?, options?) // Primary vector search
searchText(text, k?, options?) // Natural language search
find(query) // Triple Intelligence (Vector+Graph+Field) 🧠
find(query) // Triple Intelligence (Vector+Graph+Metadata) 🧠
findSimilar(id, k?, options?) // Find similar to existing noun
// Advanced Search
searchByNounTypes(types[], query, k?) // Filter by noun types
searchWithinItems(query, ids[], k?) // Search within specific nouns
searchWithCursor(query, cursor) // Paginated search
searchByStandardField(field, value, k?) // Field-based search
searchByStandardField(field, value, k?) // Metadata-based search
// Graph Search
searchVerbs(query, options?) // Search relationships
@ -206,5 +206,5 @@ These are now private (use new methods above):
- `addItem()`, `addToBoth()`, `addBatch()`, `getBatch()`
### ✅ Triple Intelligence
- New `find()` method unifies Vector + Graph + Field search
- New `find()` method unifies Vector + Graph + Metadata search
- Most powerful search capability in one simple method

View file

@ -0,0 +1,28 @@
# API Design Archive
This directory contains historical API design documents from the Brainy 2.0 development process.
## Purpose
These documents represent the iterative refinement of the Brainy 2.0 API during development. They are preserved here for historical reference and to document the design decisions made along the way.
## Current API Documentation
The definitive API documentation is now located at:
- **`/docs/api/README.md`** - The ONE official API reference
## Archived Documents
These documents show the evolution of the API design:
- Various iterations of API structure
- Exploration of different naming conventions
- Refinement of the Triple Intelligence concept
- Transition from MongoDB operators to Brainy operators
- Evolution of the Neural API
## Key Decisions Made
1. **Terminology**: Vector + Graph + Metadata (not Field)
2. **Operators**: Brainy operators (greaterThan, lessThan) not MongoDB ($gt, $lt)
3. **Methods**: Specific noun/verb naming (addNoun, getNoun)
4. **Unification**: Single getNouns() method instead of multiple variants
5. **Neural API**: Complete clustering and visualization features
## Note
These documents are archived, not deleted, to preserve the development history and rationale behind API decisions.

View file

@ -1,236 +1,395 @@
# API Reference
# 🧠 Brainy 2.0 API Reference
Complete API documentation for Brainy's multi-dimensional AI database.
> **The definitive API documentation for Brainy 2.0**
> Clean • Powerful • Zero-Configuration
## Core APIs
## Quick Start
### [BrainyData](./brainy-data.md)
The main entry point for all operations.
### [Triple Intelligence](./triple-intelligence.md)
Unified query system for vector, graph, and field search.
### [Storage](./storage.md)
Storage adapter interfaces and implementations.
### [Entity Registry](./entity-registry.md)
High-performance entity deduplication system.
### [Neural API](./neural-api.md)
Natural language processing and similarity operations.
## Quick Reference
### Initialization
```typescript
import { BrainyData } from 'brainy'
const brain = new BrainyData({
storage: { type: 'filesystem', path: './data' },
vectors: { dimensions: 384 }
})
import { BrainyData } from '@soulcraft/brainy'
const brain = new BrainyData() // Zero config!
await brain.init()
```
### Basic Operations
// Add data (text auto-embeds!)
await brain.addNoun('The future of AI is here')
#### Add Entities (Nouns) and Relationships (Verbs)
```typescript
// Add entities (nouns) with automatic embedding
const id = await brain.addNoun("Machine learning is fascinating", {
category: "technology",
timestamp: Date.now()
})
// Add relationships (verbs) between entities
const sourceId = await brain.addNoun("Research Paper")
const targetId = await brain.addNoun("Neural Networks")
await brain.addVerb(sourceId, targetId, "discusses", {
confidence: 0.95,
section: "methodology"
})
// Batch operations
const entities = ["Entity 1", "Entity 2", "Entity 3"]
for (const entity of entities) {
await brain.addNoun(entity, { type: "batch" })
}
```
#### Search and Find
```typescript
// Simple semantic search
const results = await brain.search("AI and machine learning")
// Natural language queries with find()
const nlpResults = await brain.find("research papers about neural networks from 2024")
// Automatically interprets: document type, topic, and time range
// Advanced triple intelligence search with structured query
const structured = await brain.find({
like: "neural networks",
where: { category: "research" },
connected: { to: "team-id", depth: 2 },
limit: 20
})
// Complex natural language with multiple conditions
const complex = await brain.find("highly cited papers on deep learning with over 100 citations published in Nature")
// Automatically extracts: citation count, topic, publication venue
```
#### Get and Update
```typescript
// Get noun by ID
const noun = await brain.getNoun("noun-id")
// Get verb (relationship) by ID
const verb = await brain.getVerb("verb-id")
// Update noun metadata
await brain.updateNounMetadata("noun-id", {
verified: true,
lastModified: Date.now()
})
// Delete noun (soft delete by default)
await brain.deleteNoun("noun-id")
// Delete verb (relationship)
await brain.deleteVerb("verb-id")
```
## Advanced Features
### Augmentations
```typescript
import {
WALAugmentation,
EntityRegistryAugmentation,
BatchProcessingAugmentation
} from 'brainy'
const brain = new BrainyData({
augmentations: [
new WALAugmentation(),
new EntityRegistryAugmentation({ maxCacheSize: 100000 }),
new BatchProcessingAugmentation({ batchSize: 100 })
]
// Search with Triple Intelligence
const results = await brain.find({
like: 'artificial intelligence',
where: { year: { greaterThan: 2020 } },
connected: { via: 'references' }
})
```
### Event System
## Core Concepts
### 🧬 Nouns
Vectors with metadata - the fundamental data unit in Brainy.
### 🔗 Verbs
Relationships between nouns - the connections that create knowledge graphs.
### 🧠 Triple Intelligence
Vector search + Graph traversal + Metadata filtering in one unified query.
---
## API Reference
### Data Operations
#### Nouns (Vectors with Metadata)
##### `addNoun(dataOrVector, metadata?)`
Add a single noun to the database.
- **dataOrVector**: `string | number[]` - Text (auto-embeds) or pre-computed vector
- **metadata**: `object` - Associated metadata
- **Returns**: `Promise<string>` - The noun's ID
##### `getNoun(id)`
Retrieve a noun by ID.
- **id**: `string` - The noun's ID
- **Returns**: `Promise<VectorDocument | null>`
##### `updateNoun(id, dataOrVector?, metadata?)`
Update an existing noun.
- **id**: `string` - The noun's ID
- **dataOrVector**: `string | number[]` - New data/vector (optional)
- **metadata**: `object` - New metadata (optional)
- **Returns**: `Promise<void>`
##### `deleteNoun(id)`
Delete a noun.
- **id**: `string` - The noun's ID
- **Returns**: `Promise<boolean>`
##### `getNouns(options)`
Get multiple nouns (unified method).
- **options**: Can be:
- `string[]` - Array of IDs
- `{filter: object}` - Metadata filter
- `{limit: number, offset: number}` - Pagination
- **Returns**: `Promise<VectorDocument[]>`
#### Verbs (Relationships)
##### `addVerb(source, target, type, metadata?)`
Create a relationship between nouns.
- **source**: `string` - Source noun ID
- **target**: `string` - Target noun ID
- **type**: `string` - Relationship type
- **metadata**: `object` - Relationship metadata (optional)
- **Returns**: `Promise<string>` - The verb's ID
##### `getVerbsBySource(sourceId)`
Get all outgoing relationships.
- **sourceId**: `string` - Source noun ID
- **Returns**: `Promise<Verb[]>`
##### `getVerbsByTarget(targetId)`
Get all incoming relationships.
- **targetId**: `string` - Target noun ID
- **Returns**: `Promise<Verb[]>`
---
### Search Operations
#### `search(query, k?)`
Simple vector similarity search.
- **query**: `string | number[]` - Text or vector
- **k**: `number` - Number of results (default: 10)
- **Returns**: `Promise<SearchResult[]>`
> 💡 This is equivalent to: `find({like: query, limit: k})`
#### `find(query)` - Triple Intelligence 🧠
The ultimate search method combining vector, graph, and metadata search.
```typescript
brain.on('addNoun', (noun) => {
console.log('Noun added:', noun.id)
})
brain.on('addVerb', (verb) => {
console.log('Relationship created:', verb.type)
})
brain.on('search', (query, results) => {
console.log(`Search for "${query}" returned ${results.length} results`)
})
brain.on('error', (error) => {
console.error('Error occurred:', error)
find({
// Vector similarity
like: 'text query' | vector | {id: 'noun-id'},
// Metadata filtering (Brainy operators)
where: {
field: value, // Exact match
field: {
equals: value,
greaterThan: value,
lessThan: value,
greaterEqual: value,
lessEqual: value,
oneOf: [val1, val2], // In array
notOneOf: [val1, val2], // Not in array
contains: value, // Array/string contains
startsWith: value,
endsWith: value,
matches: /pattern/, // Pattern match
between: [min, max]
}
},
// Graph traversal
connected: {
to: 'noun-id', // Target noun
from: 'noun-id', // Source noun
via: 'relationship-type', // Relationship type
depth: 2 // Traversal depth
},
// Control
limit: 10, // Max results
offset: 0, // Skip results
explain: false // Include explanation
})
```
### Statistics
---
### Neural API
Access advanced AI features via `brain.neural`:
#### `brain.neural.similar(a, b)`
Calculate semantic similarity between two items.
- **Returns**: `Promise<number>` - Similarity score (0-1)
#### `brain.neural.clusters(options?)`
Automatically cluster nouns.
- **Returns**: `Promise<Cluster[]>` - Generated clusters
#### `brain.neural.hierarchy(id)`
Build semantic hierarchy from a noun.
- **Returns**: `Promise<HierarchyTree>` - Hierarchy structure
#### `brain.neural.neighbors(id, k?)`
Find k-nearest neighbors.
- **Returns**: `Promise<Noun[]>` - Nearest neighbors
#### `brain.neural.outliers(threshold?)`
Detect outlier nouns.
- **Returns**: `Promise<string[]>` - Outlier IDs
#### `brain.neural.visualize(options?)`
Generate visualization data for external tools.
```typescript
const stats = await brain.statistics()
console.log(`
Total items: ${stats.totalItems}
Index size: ${stats.indexSize}
Average query time: ${stats.avgQueryTime}ms
`)
visualize({
maxNodes: 100,
dimensions: 2 | 3,
algorithm: 'force' | 'hierarchical' | 'radial',
includeEdges: true
})
// Returns format for D3, Cytoscape, or GraphML
```
## Type Definitions
---
### Core Types
```typescript
interface SearchResult {
id: string
score: number
content?: string
metadata?: Record<string, any>
}
### Import & Export
interface TripleQuery {
like?: string | Vector | any
where?: Record<string, any>
connected?: ConnectionQuery
limit?: number
threshold?: number
}
#### `neuralImport(data, options?)`
AI-powered smart import that auto-detects format.
- **data**: `any` - Data to import
- **options**: Import configuration
- `confidenceThreshold`: Minimum confidence (0-1)
- `autoApply`: Automatically add to database
- `skipDuplicates`: Skip existing entities
- **Returns**: Detected entities and relationships
interface Vector {
values: number[]
dimensions: number
}
```
#### `backup()`
Create a full backup.
- **Returns**: `Promise<BackupData>`
## Error Handling
#### `restore(backup)`
Restore from backup.
- **backup**: `BackupData` - Previous backup
- **Returns**: `Promise<void>`
All methods follow consistent error handling:
---
```typescript
try {
await brain.addNoun("content", metadata)
} catch (error) {
if (error.code === 'STORAGE_ERROR') {
// Handle storage issues
} else if (error.code === 'VALIDATION_ERROR') {
// Handle validation issues
}
}
```
### Intelligence Features
## Performance Guidelines
#### Verb Scoring
Train the relationship scoring model:
- `provideFeedbackForVerbScoring(feedback)` - Train model
- `getVerbScoringStats()` - Get statistics
- `exportVerbScoringLearningData()` - Export training
- `importVerbScoringLearningData(data)` - Import training
### Batching
Always use batch operations for bulk data:
```typescript
// Good - efficient batch processing
const items = ["item1", "item2", "item3"]
for (const item of items) {
await brain.addNoun(item, { batch: true })
}
#### Embeddings
- `embed(text)` - Generate embedding vector
- `calculateSimilarity(a, b, metric?)` - Calculate similarity
// For relationships
const relationships = [
{ source: id1, target: id2, type: "related" },
{ source: id2, target: id3, type: "similar" }
]
for (const rel of relationships) {
await brain.addVerb(rel.source, rel.target, rel.type)
}
```
---
### Caching
Configure caching for your use case:
### Configuration & Management
#### Operational Modes
- `setReadOnly(bool)` - Toggle read-only mode
- `setWriteOnly(bool)` - Toggle write-only mode
- `setFrozen(bool)` - Freeze all modifications
#### Cache & Performance
- `getCacheStats()` - Get cache statistics
- `clearCache()` - Clear search cache
- `size()` - Get total noun count
- `getStatistics()` - Get full statistics
#### Data Management
- `clear(options?)` - Clear all data
- `clearNouns()` - Clear nouns only
- `clearVerbs()` - Clear verbs only
- `rebuildMetadataIndex()` - Rebuild index
---
### Lifecycle
#### Initialization
```typescript
const brain = new BrainyData({
cache: {
search: { maxSize: 100, ttl: 60000 },
metadata: { maxSize: 1000, ttl: 300000 }
}
storage: 'auto', // auto | memory | filesystem | s3
dimensions: 384, // Vector dimensions
cache: true, // Enable caching
index: true // Enable indexing
})
await brain.init() // Required before use!
```
### Indexing
Ensure fields used in queries are indexed:
#### Cleanup
```typescript
// Configure indexed fields
const brain = new BrainyData({
indexedFields: ['category', 'author', 'timestamp']
await brain.shutdown() // Graceful shutdown
```
#### Static Methods
- `BrainyData.preloadModel()` - Preload ML model
- `BrainyData.warmup()` - Warmup system
---
## Query Operators Reference
Brainy uses its own clean, readable operators:
| Brainy Operator | Description | Example |
|-----------------|-------------|---------|
| `equals` | Exact match | `{age: {equals: 25}}` |
| `greaterThan` | Greater than | `{age: {greaterThan: 18}}` |
| `lessThan` | Less than | `{price: {lessThan: 100}}` |
| `greaterEqual` | Greater or equal | `{score: {greaterEqual: 90}}` |
| `lessEqual` | Less or equal | `{rating: {lessEqual: 3}}` |
| `oneOf` | In array | `{color: {oneOf: ['red', 'blue']}}` |
| `notOneOf` | Not in array | `{status: {notOneOf: ['deleted']}}` |
| `contains` | Contains value | `{tags: {contains: 'ai'}}` |
| `startsWith` | String prefix | `{name: {startsWith: 'John'}}` |
| `endsWith` | String suffix | `{email: {endsWith: '@gmail.com'}}` |
| `matches` | Pattern match | `{text: {matches: /^[A-Z]/}}` |
| `between` | Range | `{year: {between: [2020, 2024]}}` |
---
## Examples
### Basic Usage
```typescript
// Add data
const id = await brain.addNoun('Quantum computing breakthrough', {
category: 'technology',
year: 2024,
importance: 'high'
})
// Simple search
const results = await brain.search('quantum physics', 5)
// Complex query with Triple Intelligence
const articles = await brain.find({
like: 'quantum computing',
where: {
year: { greaterThan: 2022 },
importance: { oneOf: ['high', 'critical'] }
},
connected: {
via: 'references',
depth: 2
},
limit: 10
})
```
## Migration from v1.x
### Creating Knowledge Graphs
```typescript
// Add entities
const ai = await brain.addNoun('Artificial Intelligence')
const ml = await brain.addNoun('Machine Learning')
const dl = await brain.addNoun('Deep Learning')
See the [Migration Guide](../MIGRATION.md) for upgrading from Brainy 1.x to 2.0.
// Create relationships
await brain.addVerb(ml, ai, 'subset_of')
await brain.addVerb(dl, ml, 'subset_of')
await brain.addVerb(dl, ai, 'enables')
// Traverse the graph
const aiEcosystem = await brain.find({
connected: { from: ai, depth: 3 }
})
```
### Using Neural Features
```typescript
// Find similar concepts
const similarity = await brain.neural.similar(
'renewable energy',
'sustainable power'
)
// Auto-cluster documents
const clusters = await brain.neural.clusters({
method: 'kmeans',
k: 5
})
// Generate visualization
const vizData = await brain.neural.visualize({
maxNodes: 200,
algorithm: 'force',
dimensions: 3
})
// Use vizData with D3.js, Cytoscape, etc.
```
---
## Key Features
### ✨ Zero Configuration
Works instantly with sensible defaults. No setup required.
### 🧠 Triple Intelligence
Combines vector search, graph traversal, and metadata filtering in one query.
### 🚀 Auto-Embedding
Text automatically converts to vectors - no manual embedding needed.
### 📊 Built-in Visualization
Export data formatted for popular visualization libraries.
### 🔒 Clean Operators
Readable, intuitive operators - no cryptic symbols.
### 🎯 Everything Included
All features in the MIT licensed package - no premium tiers.
---
## Support
- **GitHub**: [github.com/soulcraft/brainy](https://github.com/soulcraft/brainy)
- **Documentation**: [docs.soulcraft.com/brainy](https://docs.soulcraft.com/brainy)
- **License**: MIT
---
*Brainy 2.0 - Intelligence for Everyone*

View file

@ -462,7 +462,7 @@ for (const order of orders) {
// Similar to graph databases but with added benefits:
// 1. Automatic vector embeddings for similarity
// 2. Natural language querying
// 3. Unified with field filtering
// 3. Unified with metadata filtering
// Enhanced graph queries
const results = await brain.find("similar users who purchased similar products")

View file

@ -1,6 +1,6 @@
# Architecture Overview
Brainy is a multi-dimensional AI database that combines vector similarity, graph relationships, and field filtering into a unified query system. This document provides a comprehensive overview of the system architecture.
Brainy is a multi-dimensional AI database that combines vector similarity, graph relationships, and metadata filtering into a unified query system. This document provides a comprehensive overview of the system architecture.
## Core Components
@ -23,7 +23,7 @@ Brainy's revolutionary feature that unifies three types of search:
const results = await brain.find({
like: "machine learning papers", // Vector similarity
connected: { to: "research-team", depth: 2 }, // Graph traversal
where: { published: { $gte: "2024-01-01" } } // Field filtering
where: { published: { $gte: "2024-01-01" } } // Metadata filtering
})
```

View file

@ -1,10 +1,10 @@
# Triple Intelligence System
The Triple Intelligence System is Brainy's revolutionary query engine that unifies vector similarity, graph relationships, and field filtering into a single, optimized query interface.
The Triple Intelligence System is Brainy's revolutionary query engine that unifies vector similarity, graph relationships, and metadata filtering into a single, optimized query interface.
## Overview
Traditional databases force you to choose between vector search, graph traversal, OR field filtering. Brainy combines all three intelligences into one magical API that automatically optimizes execution for maximum performance.
Traditional databases force you to choose between vector search, graph traversal, OR metadata filtering. Brainy combines all three intelligences into one magical API that automatically optimizes execution for maximum performance.
## Query Interface
@ -116,7 +116,7 @@ const results = await brain.find({
like: "recent posts", // Applied to filtered set
limit: 5
})
// Field filter first, then vector search on results
// Metadata filter first, then vector search on results
```
## Fusion Ranking
@ -193,7 +193,7 @@ Brainy uses itself to optimize queries:
Triple Intelligence leverages all available indexes:
- **HNSW Index**: For vector similarity
- **Metadata Index**: For field filtering
- **Metadata Index**: For metadata filtering
- **Graph Index**: For relationship traversal
## Advanced Features

View file

@ -0,0 +1,18 @@
# Augmentations Documentation Archive
This directory contains historical augmentation documentation from the Brainy 2.0 development process.
## Current Documentation
The definitive augmentation documentation is now located at:
- **`/docs/augmentations/README.md`** - Main augmentation guide
- **`/docs/architecture/augmentations.md`** - Architecture details
## Archived Documents
These documents represent the evolution of the augmentation system design:
- Various implementation approaches
- Pipeline architecture exploration
- Storage augmentation patterns
- Example implementations
## Note
These documents are archived to preserve development history while maintaining a clean documentation structure.

View file

@ -15,7 +15,7 @@ Unified query system that automatically combines:
// All three intelligences work together automatically
const results = await brain.find({
like: 'AI research', // Vector search
where: { year: 2024 }, // Field filtering
where: { year: 2024 }, // Metadata filtering
connected: { to: authorId } // Graph traversal
})
```

View file

@ -1,6 +1,6 @@
# Getting Started with Brainy
This guide will help you get up and running with Brainy, the multi-dimensional AI database that combines vector similarity, graph relationships, and field filtering.
This guide will help you get up and running with Brainy, the multi-dimensional AI database that combines vector similarity, graph relationships, and metadata filtering.
## Installation
@ -90,7 +90,7 @@ results.forEach(result => {
const results = await brain.find("show me technology articles about AI from 2023")
// Automatically interprets: topic, category, and time range
// Structured queries with vector similarity and field filtering
// Structured queries with vector similarity and metadata filtering
const structured = await brain.find({
like: "artificial intelligence",
where: {

View file

@ -162,7 +162,7 @@ The natural language is converted to a structured Triple Intelligence query:
### 5. Execution
The structured query is executed using Triple Intelligence, combining:
- Vector similarity search
- Field filtering
- Metadata filtering
- Graph traversal
## Advanced Features

View file

@ -20,7 +20,7 @@
- ✅ Natural language queries ("find developers")
- ✅ Vector similarity search (`similar: 'text'`)
- ✅ Graph traversal (`connected: { to: 'node' }`)
- ✅ Field filtering (`where: { field: 'value' }`)
- ✅ Metadata filtering (`where: { field: 'value' }`)
- ✅ Combined intelligence with fusion scoring
- ✅ Performance optimized for complex queries
- **Status: PRODUCTION READY**
@ -94,7 +94,7 @@ const viz = await neural.visualize()
```
### Core Innovation Validated
- ✅ **Triple Intelligence**: Vector + Graph + Field search unified
- ✅ **Triple Intelligence**: Vector + Graph + Metadata search unified
- ✅ **Intelligent Verb Scoring**: Smart relationship weights
- ✅ **Neural APIs**: Ready for external visualization libraries
- ✅ **Zero Config**: Works perfectly out of the box
@ -118,7 +118,7 @@ const viz = await neural.visualize()
- **Scalability**: Tested with complex datasets
### Innovation Leadership ✅
- **First True Triple Intelligence**: Vector + Graph + Field unified
- **First True Triple Intelligence**: Vector + Graph + Metadata unified
- **Smart by Default**: No configuration required
- **Revolutionary Data Model**: Noun-verb taxonomy
- **Neural API**: Ready for external clustering/visualization libraries
@ -133,7 +133,7 @@ const viz = await neural.visualize()
Brainy 2.0 represents a fundamental leap forward in vector database technology:
1. **Triple Intelligence** solves the problem of having to choose between vector, graph, or field search
1. **Triple Intelligence** solves the problem of having to choose between vector, graph, or metadata search
2. **Intelligent Verb Scoring** automatically computes optimal relationship weights
3. **Neural APIs** enable external libraries to build advanced visualizations
4. **Zero Configuration** makes it accessible to all developers

View file

@ -4,7 +4,7 @@
### Core Features
- ✅ **Noun-Verb Taxonomy** - Complete implementation with addNoun() and addVerb()
- ✅ **Triple Intelligence Engine** - Vector + Graph + Field unified queries
- ✅ **Triple Intelligence Engine** - Vector + Graph + Metadata unified queries
- ✅ **Natural Language find()** - Basic NLP with 220+ embedded patterns
- ✅ **HNSW Vector Search** - O(log n) similarity search
- ✅ **Field Indexing** - O(1) metadata lookups via FieldIndex class

View file

@ -6,7 +6,7 @@ After thorough investigation of the codebase, here's what's ACTUALLY implemented
### Core Features
- ✅ **Noun-Verb Taxonomy** - Complete with addNoun() and addVerb()
- ✅ **Triple Intelligence Engine** - Vector + Graph + Field unified queries
- ✅ **Triple Intelligence Engine** - Vector + Graph + Metadata unified queries
- ✅ **Natural Language find()** - Basic NLP with 220+ embedded patterns
- ✅ **HNSW Vector Search** - O(log n) similarity search with partitioning support
- ✅ **Field Indexing** - O(1) metadata lookups via FieldIndex class

View file

@ -6,7 +6,7 @@
### Core Features (100% Complete)
- ✅ **Noun-Verb Taxonomy**: Revolutionary data model
- ✅ **Triple Intelligence**: Vector + Graph + Field unified queries
- ✅ **Triple Intelligence**: Vector + Graph + Metadata unified queries
- ✅ **HNSW Indexing**: O(log n) vector search
- ✅ **384 Dimensions**: Fixed with all-MiniLM-L6-v2
- ✅ **Zero-Config**: Works out of the box

View file

@ -32,7 +32,7 @@
- Real transformer models (no mocking)
### 6. Natural Language ✅
- `tests/triple-intelligence.test.ts` - Vector + Graph + Field queries
- `tests/triple-intelligence.test.ts` - Vector + Graph + Metadata queries
- Natural language query understanding
### 7. Error Handling ✅

View file

@ -225,7 +225,7 @@ const brain = new BrainyData({
const results = await brain.search("query", { limit: 10 })
```
3. **Consider field filtering first**
3. **Consider metadata filtering first**
```typescript
// Filter by metadata first, then semantic search
const results = await brain.search("query", {