brainy/src/api/DataAPI.ts

389 lines
9.7 KiB
TypeScript
Raw Normal View History

/**
* Data Management API for Brainy 3.0
* Provides backup, restore, import, export, and data management
*/
import { StorageAdapter, HNSWNoun, GraphVerb } from '../coreTypes.js'
import { Entity, Relation } from '../types/brainy.types.js'
import { NounType, VerbType } from '../types/graphTypes.js'
export interface BackupOptions {
includeVectors?: boolean
compress?: boolean
format?: 'json' | 'binary'
}
export interface RestoreOptions {
merge?: boolean
overwrite?: boolean
validate?: boolean
}
export interface ImportOptions {
format: 'json' | 'csv'
mapping?: Record<string, string>
batchSize?: number
validate?: boolean
}
export interface ExportOptions {
format?: 'json' | 'csv'
filter?: {
type?: NounType | NounType[]
where?: Record<string, any>
service?: string
}
includeVectors?: boolean
}
export interface BackupData {
version: string
timestamp: number
entities: Array<{
id: string
vector?: number[]
type: string
metadata: any
service?: string
}>
relations: Array<{
id: string
from: string
to: string
type: string
weight: number
metadata?: any
}>
config?: Record<string, any>
stats: {
entityCount: number
relationCount: number
vectorDimensions?: number
}
}
export interface ImportResult {
successful: number
failed: number
errors: Array<{ item: any; error: string }>
duration: number
}
export class DataAPI {
private brain: any // Reference to Brainy instance for neural import
constructor(
private storage: StorageAdapter,
private getEntity: (id: string) => Promise<Entity | null>,
private getRelation?: (id: string) => Promise<Relation | null>,
brain?: any
) {
this.brain = brain
}
async clear(params: {
entities?: boolean
relations?: boolean
config?: boolean
} = {}): Promise<void> {
const { entities = true, relations = true, config = false } = params
if (entities) {
// Clear all entities
const nounsResult = await this.storage.getNouns({
pagination: { limit: 1000000 }
})
for (const noun of nounsResult.items) {
await this.storage.deleteNoun(noun.id)
}
// Also clear the HNSW index if available
if (this.brain?.index?.clear) {
this.brain.index.clear()
}
// Clear metadata index if available
if (this.brain?.metadataIndex) {
await this.brain.metadataIndex.rebuild() // Rebuild empty index
}
}
if (relations) {
// Clear all relations
const verbsResult = await this.storage.getVerbs({
pagination: { limit: 1000000 }
})
for (const verb of verbsResult.items) {
await this.storage.deleteVerb(verb.id)
}
}
if (config) {
// Clear configuration would be handled by ConfigAPI
// For now, skip this
}
}
/**
* Import data from various formats
*/
async import(params: ImportOptions & { data: any }): Promise<ImportResult> {
const {
data,
format,
mapping = {},
batchSize = 100,
validate = true
} = params
const result: ImportResult = {
successful: 0,
failed: 0,
errors: [],
duration: 0
}
const startTime = Date.now()
try {
// ALWAYS use neural import for proper type matching
const { UniversalImportAPI } = await import('./UniversalImportAPI.js')
const universalImport = new UniversalImportAPI(this.brain)
await universalImport.init()
// Convert to ImportSource format
const neuralResult = await universalImport.import({
type: 'object',
data,
format: format || 'json',
metadata: { mapping, batchSize, validate }
})
// Convert neural result to ImportResult format
result.successful = neuralResult.stats.entitiesCreated
result.failed = 0 // Neural import always succeeds with best match
result.duration = neuralResult.stats.processingTimeMs
// Log relationships created
if (neuralResult.stats.relationshipsCreated > 0) {
console.log(`Neural import also created ${neuralResult.stats.relationshipsCreated} relationships`)
}
return result
} catch (error) {
// Fallback to legacy import ONLY if neural import fails to load
console.warn('Neural import failed, using legacy import:', error)
let items: any[] = []
// Parse data based on format
switch (format) {
case 'json':
items = Array.isArray(data) ? data : [data]
break
case 'csv':
// CSV parsing would go here
// For now, assume data is already parsed
items = data
break
// Parquet format removed - not implemented
default:
throw new Error(`Unsupported format: ${format}`)
}
// Process items in batches
for (let i = 0; i < items.length; i += batchSize) {
const batch = items.slice(i, i + batchSize)
for (const item of batch) {
try {
// Apply field mapping
const mapped = this.applyMapping(item, mapping)
// Validate if requested
if (validate) {
this.validateImportItem(mapped)
}
feat(v4.0.0): Complete metadata/vector separation architecture with Azure support This commit completes the core v4.0.0 architecture changes for billion-scale performance with metadata/vector separation. NO RELEASE YET - remaining optimizations and testing required before production release. ## Core v4.0.0 Architecture Changes ### Type System Updates - Fixed all TypeScript compilation errors (zero errors achieved) - Updated HNSWNoun/HNSWVerb to separate core fields from metadata - Implemented HNSWNounWithMetadata/HNSWVerbWithMetadata for API boundaries - Added required 'noun' field to NounMetadata for semantic structure - Renamed verb.type to verb.verb for consistency ### Storage Adapter Updates **All adapters updated for v4.0.0 two-file storage pattern:** - memoryStorage: Proper metadata/vector separation - fileSystemStorage: Two-file pattern with sharding - opfsStorage: Browser persistent storage updated - s3CompatibleStorage: AWS/MinIO/DigitalOcean support - r2Storage: Cloudflare R2 optimization - gcsStorage: Google Cloud with ADC support - **azureBlobStorage: NEW - Full Azure Blob Storage support** ### Storage Features - BaseStorage: Internal vs public method separation (_getNoun vs getNoun) - Two-file storage: Vectors in one file, metadata in another - Change tracking: getChangesSince return type updated - Pagination: getNounsWithPagination returns WithMetadata types ### Azure Blob Storage Integration (NEW) - Native @azure/storage-blob SDK integration - Four authentication methods: * DefaultAzureCredential (Managed Identity) - recommended * Connection String - simplest setup * Account Name + Key - traditional auth * SAS Token - delegated access - High-volume mode with write buffering - Adaptive backpressure for throttling - UUID-based sharding for billion-scale - Full HNSW support with graph persistence ### Utility Updates - EmbeddingManager: Updated to accept Record<string, unknown> - LSMTree: Wrapped data in NounMetadata structure with 'noun' field - EntityIdMapper: Fixed nested metadata.data structure access - MetadataIndex: Fixed field type inference integration - PeriodicCleanup: Updated for new metadata structure ### Core API Updates - Brainy: Updated verb property access from v.type to v.verb - ConfigAPI: Fixed NounMetadata access patterns - DataAPI: Updated metadata handling ### Documentation Updates - CREATING-AUGMENTATIONS.md: v4.0.0 breaking changes guide - DEVELOPER-GUIDE.md: Migration checklist and examples - COMPLETE-REFERENCE.md: v4.0.0 architecture improvements - **finite-type-system.md: NEW - Revolutionary type system benefits** ### Build & Dependencies - Zero TypeScript compilation errors - Added @azure/storage-blob and @azure/identity - 591 tests passing (23 timeout in long-running neural tests) ## What's NOT in This Release This is a work-in-progress commit. Before v4.0.0 release we need: - Storage adapter optimizations (batch operations, compression) - Azure blob tier management (Hot/Cool/Archive) - Cost optimization implementations - Additional performance testing at billion-scale - Migration guides for v3.x users ## Testing - Clean build: ✅ - Type checking: ✅ (zero errors) - Test suite: ✅ (591/614 passing, timeouts in neural tests only) 🔐 Generated with Claude Code https://claude.com/claude-code Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-17 12:29:27 -07:00
// v4.0.0: Save entity - separate vector and metadata
const id = mapped.id || this.generateId()
const noun: HNSWNoun = {
feat(v4.0.0): Complete metadata/vector separation architecture with Azure support This commit completes the core v4.0.0 architecture changes for billion-scale performance with metadata/vector separation. NO RELEASE YET - remaining optimizations and testing required before production release. ## Core v4.0.0 Architecture Changes ### Type System Updates - Fixed all TypeScript compilation errors (zero errors achieved) - Updated HNSWNoun/HNSWVerb to separate core fields from metadata - Implemented HNSWNounWithMetadata/HNSWVerbWithMetadata for API boundaries - Added required 'noun' field to NounMetadata for semantic structure - Renamed verb.type to verb.verb for consistency ### Storage Adapter Updates **All adapters updated for v4.0.0 two-file storage pattern:** - memoryStorage: Proper metadata/vector separation - fileSystemStorage: Two-file pattern with sharding - opfsStorage: Browser persistent storage updated - s3CompatibleStorage: AWS/MinIO/DigitalOcean support - r2Storage: Cloudflare R2 optimization - gcsStorage: Google Cloud with ADC support - **azureBlobStorage: NEW - Full Azure Blob Storage support** ### Storage Features - BaseStorage: Internal vs public method separation (_getNoun vs getNoun) - Two-file storage: Vectors in one file, metadata in another - Change tracking: getChangesSince return type updated - Pagination: getNounsWithPagination returns WithMetadata types ### Azure Blob Storage Integration (NEW) - Native @azure/storage-blob SDK integration - Four authentication methods: * DefaultAzureCredential (Managed Identity) - recommended * Connection String - simplest setup * Account Name + Key - traditional auth * SAS Token - delegated access - High-volume mode with write buffering - Adaptive backpressure for throttling - UUID-based sharding for billion-scale - Full HNSW support with graph persistence ### Utility Updates - EmbeddingManager: Updated to accept Record<string, unknown> - LSMTree: Wrapped data in NounMetadata structure with 'noun' field - EntityIdMapper: Fixed nested metadata.data structure access - MetadataIndex: Fixed field type inference integration - PeriodicCleanup: Updated for new metadata structure ### Core API Updates - Brainy: Updated verb property access from v.type to v.verb - ConfigAPI: Fixed NounMetadata access patterns - DataAPI: Updated metadata handling ### Documentation Updates - CREATING-AUGMENTATIONS.md: v4.0.0 breaking changes guide - DEVELOPER-GUIDE.md: Migration checklist and examples - COMPLETE-REFERENCE.md: v4.0.0 architecture improvements - **finite-type-system.md: NEW - Revolutionary type system benefits** ### Build & Dependencies - Zero TypeScript compilation errors - Added @azure/storage-blob and @azure/identity - 591 tests passing (23 timeout in long-running neural tests) ## What's NOT in This Release This is a work-in-progress commit. Before v4.0.0 release we need: - Storage adapter optimizations (batch operations, compression) - Azure blob tier management (Hot/Cool/Archive) - Cost optimization implementations - Additional performance testing at billion-scale - Migration guides for v3.x users ## Testing - Clean build: ✅ - Type checking: ✅ (zero errors) - Test suite: ✅ (591/614 passing, timeouts in neural tests only) 🔐 Generated with Claude Code https://claude.com/claude-code Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-17 12:29:27 -07:00
id,
vector: mapped.vector || new Array(384).fill(0),
connections: new Map(),
feat(v4.0.0): Complete metadata/vector separation architecture with Azure support This commit completes the core v4.0.0 architecture changes for billion-scale performance with metadata/vector separation. NO RELEASE YET - remaining optimizations and testing required before production release. ## Core v4.0.0 Architecture Changes ### Type System Updates - Fixed all TypeScript compilation errors (zero errors achieved) - Updated HNSWNoun/HNSWVerb to separate core fields from metadata - Implemented HNSWNounWithMetadata/HNSWVerbWithMetadata for API boundaries - Added required 'noun' field to NounMetadata for semantic structure - Renamed verb.type to verb.verb for consistency ### Storage Adapter Updates **All adapters updated for v4.0.0 two-file storage pattern:** - memoryStorage: Proper metadata/vector separation - fileSystemStorage: Two-file pattern with sharding - opfsStorage: Browser persistent storage updated - s3CompatibleStorage: AWS/MinIO/DigitalOcean support - r2Storage: Cloudflare R2 optimization - gcsStorage: Google Cloud with ADC support - **azureBlobStorage: NEW - Full Azure Blob Storage support** ### Storage Features - BaseStorage: Internal vs public method separation (_getNoun vs getNoun) - Two-file storage: Vectors in one file, metadata in another - Change tracking: getChangesSince return type updated - Pagination: getNounsWithPagination returns WithMetadata types ### Azure Blob Storage Integration (NEW) - Native @azure/storage-blob SDK integration - Four authentication methods: * DefaultAzureCredential (Managed Identity) - recommended * Connection String - simplest setup * Account Name + Key - traditional auth * SAS Token - delegated access - High-volume mode with write buffering - Adaptive backpressure for throttling - UUID-based sharding for billion-scale - Full HNSW support with graph persistence ### Utility Updates - EmbeddingManager: Updated to accept Record<string, unknown> - LSMTree: Wrapped data in NounMetadata structure with 'noun' field - EntityIdMapper: Fixed nested metadata.data structure access - MetadataIndex: Fixed field type inference integration - PeriodicCleanup: Updated for new metadata structure ### Core API Updates - Brainy: Updated verb property access from v.type to v.verb - ConfigAPI: Fixed NounMetadata access patterns - DataAPI: Updated metadata handling ### Documentation Updates - CREATING-AUGMENTATIONS.md: v4.0.0 breaking changes guide - DEVELOPER-GUIDE.md: Migration checklist and examples - COMPLETE-REFERENCE.md: v4.0.0 architecture improvements - **finite-type-system.md: NEW - Revolutionary type system benefits** ### Build & Dependencies - Zero TypeScript compilation errors - Added @azure/storage-blob and @azure/identity - 591 tests passing (23 timeout in long-running neural tests) ## What's NOT in This Release This is a work-in-progress commit. Before v4.0.0 release we need: - Storage adapter optimizations (batch operations, compression) - Azure blob tier management (Hot/Cool/Archive) - Cost optimization implementations - Additional performance testing at billion-scale - Migration guides for v3.x users ## Testing - Clean build: ✅ - Type checking: ✅ (zero errors) - Test suite: ✅ (591/614 passing, timeouts in neural tests only) 🔐 Generated with Claude Code https://claude.com/claude-code Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-17 12:29:27 -07:00
level: 0
}
await this.storage.saveNoun(noun)
feat(v4.0.0): Complete metadata/vector separation architecture with Azure support This commit completes the core v4.0.0 architecture changes for billion-scale performance with metadata/vector separation. NO RELEASE YET - remaining optimizations and testing required before production release. ## Core v4.0.0 Architecture Changes ### Type System Updates - Fixed all TypeScript compilation errors (zero errors achieved) - Updated HNSWNoun/HNSWVerb to separate core fields from metadata - Implemented HNSWNounWithMetadata/HNSWVerbWithMetadata for API boundaries - Added required 'noun' field to NounMetadata for semantic structure - Renamed verb.type to verb.verb for consistency ### Storage Adapter Updates **All adapters updated for v4.0.0 two-file storage pattern:** - memoryStorage: Proper metadata/vector separation - fileSystemStorage: Two-file pattern with sharding - opfsStorage: Browser persistent storage updated - s3CompatibleStorage: AWS/MinIO/DigitalOcean support - r2Storage: Cloudflare R2 optimization - gcsStorage: Google Cloud with ADC support - **azureBlobStorage: NEW - Full Azure Blob Storage support** ### Storage Features - BaseStorage: Internal vs public method separation (_getNoun vs getNoun) - Two-file storage: Vectors in one file, metadata in another - Change tracking: getChangesSince return type updated - Pagination: getNounsWithPagination returns WithMetadata types ### Azure Blob Storage Integration (NEW) - Native @azure/storage-blob SDK integration - Four authentication methods: * DefaultAzureCredential (Managed Identity) - recommended * Connection String - simplest setup * Account Name + Key - traditional auth * SAS Token - delegated access - High-volume mode with write buffering - Adaptive backpressure for throttling - UUID-based sharding for billion-scale - Full HNSW support with graph persistence ### Utility Updates - EmbeddingManager: Updated to accept Record<string, unknown> - LSMTree: Wrapped data in NounMetadata structure with 'noun' field - EntityIdMapper: Fixed nested metadata.data structure access - MetadataIndex: Fixed field type inference integration - PeriodicCleanup: Updated for new metadata structure ### Core API Updates - Brainy: Updated verb property access from v.type to v.verb - ConfigAPI: Fixed NounMetadata access patterns - DataAPI: Updated metadata handling ### Documentation Updates - CREATING-AUGMENTATIONS.md: v4.0.0 breaking changes guide - DEVELOPER-GUIDE.md: Migration checklist and examples - COMPLETE-REFERENCE.md: v4.0.0 architecture improvements - **finite-type-system.md: NEW - Revolutionary type system benefits** ### Build & Dependencies - Zero TypeScript compilation errors - Added @azure/storage-blob and @azure/identity - 591 tests passing (23 timeout in long-running neural tests) ## What's NOT in This Release This is a work-in-progress commit. Before v4.0.0 release we need: - Storage adapter optimizations (batch operations, compression) - Azure blob tier management (Hot/Cool/Archive) - Cost optimization implementations - Additional performance testing at billion-scale - Migration guides for v3.x users ## Testing - Clean build: ✅ - Type checking: ✅ (zero errors) - Test suite: ✅ (591/614 passing, timeouts in neural tests only) 🔐 Generated with Claude Code https://claude.com/claude-code Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-17 12:29:27 -07:00
await this.storage.saveNounMetadata(id, { ...mapped, createdAt: Date.now() })
result.successful++
} catch (error) {
result.failed++
result.errors.push({
item,
error: (error as Error).message
})
}
}
}
result.duration = Date.now() - startTime
return result
}
}
/**
* Export data to various formats
*/
async export(params: ExportOptions = {}): Promise<any> {
const {
format = 'json',
filter = {},
includeVectors = false
} = params
// Get filtered entities
const nounsResult = await this.storage.getNouns({
pagination: { limit: 1000000 }
})
let entities = nounsResult.items
// Apply filters
if (filter.type) {
const types = Array.isArray(filter.type) ? filter.type : [filter.type]
entities = entities.filter(e =>
types.includes(e.metadata?.noun as NounType)
)
}
if (filter.service) {
entities = entities.filter(e =>
e.metadata?.service === filter.service
)
}
if (filter.where) {
entities = entities.filter(e =>
this.matchesFilter(e.metadata, filter.where!)
)
}
// Format data based on export format
switch (format) {
case 'json':
return entities.map(e => ({
id: e.id,
vector: includeVectors ? e.vector : undefined,
...e.metadata
}))
case 'csv':
// Convert to CSV format
// For now, return simplified format
return this.convertToCSV(entities)
// Parquet format removed - not implemented
default:
throw new Error(`Unsupported export format: ${format}`)
}
}
/**
* Get storage statistics
*/
async getStats(): Promise<{
entities: number
relations: number
storageSize?: number
vectorDimensions?: number
}> {
const nounsResult = await this.storage.getNouns({
pagination: { limit: 1 }
})
const verbsResult = await this.storage.getVerbs({
pagination: { limit: 1 }
})
const firstNoun = nounsResult.items[0]
return {
entities: nounsResult.totalCount || nounsResult.items.length,
relations: verbsResult.totalCount || verbsResult.items.length,
vectorDimensions: firstNoun?.vector?.length
}
}
// Helper methods
private applyMapping(item: any, mapping: Record<string, string>): any {
const mapped: any = {}
for (const [key, value] of Object.entries(item)) {
const mappedKey = mapping[key] || key
mapped[mappedKey] = value
}
return mapped
}
private validateImportItem(item: any): void {
// Basic validation
if (!item || typeof item !== 'object') {
throw new Error('Invalid item: must be an object')
}
// Could add more validation here
}
private matchesFilter(metadata: any, filter: Record<string, any>): boolean {
for (const [key, value] of Object.entries(filter)) {
if (metadata[key] !== value) {
return false
}
}
return true
}
feat(v4.0.0): Complete metadata/vector separation architecture with Azure support This commit completes the core v4.0.0 architecture changes for billion-scale performance with metadata/vector separation. NO RELEASE YET - remaining optimizations and testing required before production release. ## Core v4.0.0 Architecture Changes ### Type System Updates - Fixed all TypeScript compilation errors (zero errors achieved) - Updated HNSWNoun/HNSWVerb to separate core fields from metadata - Implemented HNSWNounWithMetadata/HNSWVerbWithMetadata for API boundaries - Added required 'noun' field to NounMetadata for semantic structure - Renamed verb.type to verb.verb for consistency ### Storage Adapter Updates **All adapters updated for v4.0.0 two-file storage pattern:** - memoryStorage: Proper metadata/vector separation - fileSystemStorage: Two-file pattern with sharding - opfsStorage: Browser persistent storage updated - s3CompatibleStorage: AWS/MinIO/DigitalOcean support - r2Storage: Cloudflare R2 optimization - gcsStorage: Google Cloud with ADC support - **azureBlobStorage: NEW - Full Azure Blob Storage support** ### Storage Features - BaseStorage: Internal vs public method separation (_getNoun vs getNoun) - Two-file storage: Vectors in one file, metadata in another - Change tracking: getChangesSince return type updated - Pagination: getNounsWithPagination returns WithMetadata types ### Azure Blob Storage Integration (NEW) - Native @azure/storage-blob SDK integration - Four authentication methods: * DefaultAzureCredential (Managed Identity) - recommended * Connection String - simplest setup * Account Name + Key - traditional auth * SAS Token - delegated access - High-volume mode with write buffering - Adaptive backpressure for throttling - UUID-based sharding for billion-scale - Full HNSW support with graph persistence ### Utility Updates - EmbeddingManager: Updated to accept Record<string, unknown> - LSMTree: Wrapped data in NounMetadata structure with 'noun' field - EntityIdMapper: Fixed nested metadata.data structure access - MetadataIndex: Fixed field type inference integration - PeriodicCleanup: Updated for new metadata structure ### Core API Updates - Brainy: Updated verb property access from v.type to v.verb - ConfigAPI: Fixed NounMetadata access patterns - DataAPI: Updated metadata handling ### Documentation Updates - CREATING-AUGMENTATIONS.md: v4.0.0 breaking changes guide - DEVELOPER-GUIDE.md: Migration checklist and examples - COMPLETE-REFERENCE.md: v4.0.0 architecture improvements - **finite-type-system.md: NEW - Revolutionary type system benefits** ### Build & Dependencies - Zero TypeScript compilation errors - Added @azure/storage-blob and @azure/identity - 591 tests passing (23 timeout in long-running neural tests) ## What's NOT in This Release This is a work-in-progress commit. Before v4.0.0 release we need: - Storage adapter optimizations (batch operations, compression) - Azure blob tier management (Hot/Cool/Archive) - Cost optimization implementations - Additional performance testing at billion-scale - Migration guides for v3.x users ## Testing - Clean build: ✅ - Type checking: ✅ (zero errors) - Test suite: ✅ (591/614 passing, timeouts in neural tests only) 🔐 Generated with Claude Code https://claude.com/claude-code Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-17 12:29:27 -07:00
private convertToCSV(entities: Array<{ id: string; metadata?: any }>): string {
if (entities.length === 0) return ''
feat(v4.0.0): Complete metadata/vector separation architecture with Azure support This commit completes the core v4.0.0 architecture changes for billion-scale performance with metadata/vector separation. NO RELEASE YET - remaining optimizations and testing required before production release. ## Core v4.0.0 Architecture Changes ### Type System Updates - Fixed all TypeScript compilation errors (zero errors achieved) - Updated HNSWNoun/HNSWVerb to separate core fields from metadata - Implemented HNSWNounWithMetadata/HNSWVerbWithMetadata for API boundaries - Added required 'noun' field to NounMetadata for semantic structure - Renamed verb.type to verb.verb for consistency ### Storage Adapter Updates **All adapters updated for v4.0.0 two-file storage pattern:** - memoryStorage: Proper metadata/vector separation - fileSystemStorage: Two-file pattern with sharding - opfsStorage: Browser persistent storage updated - s3CompatibleStorage: AWS/MinIO/DigitalOcean support - r2Storage: Cloudflare R2 optimization - gcsStorage: Google Cloud with ADC support - **azureBlobStorage: NEW - Full Azure Blob Storage support** ### Storage Features - BaseStorage: Internal vs public method separation (_getNoun vs getNoun) - Two-file storage: Vectors in one file, metadata in another - Change tracking: getChangesSince return type updated - Pagination: getNounsWithPagination returns WithMetadata types ### Azure Blob Storage Integration (NEW) - Native @azure/storage-blob SDK integration - Four authentication methods: * DefaultAzureCredential (Managed Identity) - recommended * Connection String - simplest setup * Account Name + Key - traditional auth * SAS Token - delegated access - High-volume mode with write buffering - Adaptive backpressure for throttling - UUID-based sharding for billion-scale - Full HNSW support with graph persistence ### Utility Updates - EmbeddingManager: Updated to accept Record<string, unknown> - LSMTree: Wrapped data in NounMetadata structure with 'noun' field - EntityIdMapper: Fixed nested metadata.data structure access - MetadataIndex: Fixed field type inference integration - PeriodicCleanup: Updated for new metadata structure ### Core API Updates - Brainy: Updated verb property access from v.type to v.verb - ConfigAPI: Fixed NounMetadata access patterns - DataAPI: Updated metadata handling ### Documentation Updates - CREATING-AUGMENTATIONS.md: v4.0.0 breaking changes guide - DEVELOPER-GUIDE.md: Migration checklist and examples - COMPLETE-REFERENCE.md: v4.0.0 architecture improvements - **finite-type-system.md: NEW - Revolutionary type system benefits** ### Build & Dependencies - Zero TypeScript compilation errors - Added @azure/storage-blob and @azure/identity - 591 tests passing (23 timeout in long-running neural tests) ## What's NOT in This Release This is a work-in-progress commit. Before v4.0.0 release we need: - Storage adapter optimizations (batch operations, compression) - Azure blob tier management (Hot/Cool/Archive) - Cost optimization implementations - Additional performance testing at billion-scale - Migration guides for v3.x users ## Testing - Clean build: ✅ - Type checking: ✅ (zero errors) - Test suite: ✅ (591/614 passing, timeouts in neural tests only) 🔐 Generated with Claude Code https://claude.com/claude-code Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-17 12:29:27 -07:00
// Get all unique keys from metadata
const keys = new Set<string>()
for (const entity of entities) {
if (entity.metadata) {
Object.keys(entity.metadata).forEach(k => keys.add(k))
}
}
feat(v4.0.0): Complete metadata/vector separation architecture with Azure support This commit completes the core v4.0.0 architecture changes for billion-scale performance with metadata/vector separation. NO RELEASE YET - remaining optimizations and testing required before production release. ## Core v4.0.0 Architecture Changes ### Type System Updates - Fixed all TypeScript compilation errors (zero errors achieved) - Updated HNSWNoun/HNSWVerb to separate core fields from metadata - Implemented HNSWNounWithMetadata/HNSWVerbWithMetadata for API boundaries - Added required 'noun' field to NounMetadata for semantic structure - Renamed verb.type to verb.verb for consistency ### Storage Adapter Updates **All adapters updated for v4.0.0 two-file storage pattern:** - memoryStorage: Proper metadata/vector separation - fileSystemStorage: Two-file pattern with sharding - opfsStorage: Browser persistent storage updated - s3CompatibleStorage: AWS/MinIO/DigitalOcean support - r2Storage: Cloudflare R2 optimization - gcsStorage: Google Cloud with ADC support - **azureBlobStorage: NEW - Full Azure Blob Storage support** ### Storage Features - BaseStorage: Internal vs public method separation (_getNoun vs getNoun) - Two-file storage: Vectors in one file, metadata in another - Change tracking: getChangesSince return type updated - Pagination: getNounsWithPagination returns WithMetadata types ### Azure Blob Storage Integration (NEW) - Native @azure/storage-blob SDK integration - Four authentication methods: * DefaultAzureCredential (Managed Identity) - recommended * Connection String - simplest setup * Account Name + Key - traditional auth * SAS Token - delegated access - High-volume mode with write buffering - Adaptive backpressure for throttling - UUID-based sharding for billion-scale - Full HNSW support with graph persistence ### Utility Updates - EmbeddingManager: Updated to accept Record<string, unknown> - LSMTree: Wrapped data in NounMetadata structure with 'noun' field - EntityIdMapper: Fixed nested metadata.data structure access - MetadataIndex: Fixed field type inference integration - PeriodicCleanup: Updated for new metadata structure ### Core API Updates - Brainy: Updated verb property access from v.type to v.verb - ConfigAPI: Fixed NounMetadata access patterns - DataAPI: Updated metadata handling ### Documentation Updates - CREATING-AUGMENTATIONS.md: v4.0.0 breaking changes guide - DEVELOPER-GUIDE.md: Migration checklist and examples - COMPLETE-REFERENCE.md: v4.0.0 architecture improvements - **finite-type-system.md: NEW - Revolutionary type system benefits** ### Build & Dependencies - Zero TypeScript compilation errors - Added @azure/storage-blob and @azure/identity - 591 tests passing (23 timeout in long-running neural tests) ## What's NOT in This Release This is a work-in-progress commit. Before v4.0.0 release we need: - Storage adapter optimizations (batch operations, compression) - Azure blob tier management (Hot/Cool/Archive) - Cost optimization implementations - Additional performance testing at billion-scale - Migration guides for v3.x users ## Testing - Clean build: ✅ - Type checking: ✅ (zero errors) - Test suite: ✅ (591/614 passing, timeouts in neural tests only) 🔐 Generated with Claude Code https://claude.com/claude-code Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-17 12:29:27 -07:00
// Create CSV header
const headers = ['id', ...Array.from(keys)]
const rows = [headers.join(',')]
feat(v4.0.0): Complete metadata/vector separation architecture with Azure support This commit completes the core v4.0.0 architecture changes for billion-scale performance with metadata/vector separation. NO RELEASE YET - remaining optimizations and testing required before production release. ## Core v4.0.0 Architecture Changes ### Type System Updates - Fixed all TypeScript compilation errors (zero errors achieved) - Updated HNSWNoun/HNSWVerb to separate core fields from metadata - Implemented HNSWNounWithMetadata/HNSWVerbWithMetadata for API boundaries - Added required 'noun' field to NounMetadata for semantic structure - Renamed verb.type to verb.verb for consistency ### Storage Adapter Updates **All adapters updated for v4.0.0 two-file storage pattern:** - memoryStorage: Proper metadata/vector separation - fileSystemStorage: Two-file pattern with sharding - opfsStorage: Browser persistent storage updated - s3CompatibleStorage: AWS/MinIO/DigitalOcean support - r2Storage: Cloudflare R2 optimization - gcsStorage: Google Cloud with ADC support - **azureBlobStorage: NEW - Full Azure Blob Storage support** ### Storage Features - BaseStorage: Internal vs public method separation (_getNoun vs getNoun) - Two-file storage: Vectors in one file, metadata in another - Change tracking: getChangesSince return type updated - Pagination: getNounsWithPagination returns WithMetadata types ### Azure Blob Storage Integration (NEW) - Native @azure/storage-blob SDK integration - Four authentication methods: * DefaultAzureCredential (Managed Identity) - recommended * Connection String - simplest setup * Account Name + Key - traditional auth * SAS Token - delegated access - High-volume mode with write buffering - Adaptive backpressure for throttling - UUID-based sharding for billion-scale - Full HNSW support with graph persistence ### Utility Updates - EmbeddingManager: Updated to accept Record<string, unknown> - LSMTree: Wrapped data in NounMetadata structure with 'noun' field - EntityIdMapper: Fixed nested metadata.data structure access - MetadataIndex: Fixed field type inference integration - PeriodicCleanup: Updated for new metadata structure ### Core API Updates - Brainy: Updated verb property access from v.type to v.verb - ConfigAPI: Fixed NounMetadata access patterns - DataAPI: Updated metadata handling ### Documentation Updates - CREATING-AUGMENTATIONS.md: v4.0.0 breaking changes guide - DEVELOPER-GUIDE.md: Migration checklist and examples - COMPLETE-REFERENCE.md: v4.0.0 architecture improvements - **finite-type-system.md: NEW - Revolutionary type system benefits** ### Build & Dependencies - Zero TypeScript compilation errors - Added @azure/storage-blob and @azure/identity - 591 tests passing (23 timeout in long-running neural tests) ## What's NOT in This Release This is a work-in-progress commit. Before v4.0.0 release we need: - Storage adapter optimizations (batch operations, compression) - Azure blob tier management (Hot/Cool/Archive) - Cost optimization implementations - Additional performance testing at billion-scale - Migration guides for v3.x users ## Testing - Clean build: ✅ - Type checking: ✅ (zero errors) - Test suite: ✅ (591/614 passing, timeouts in neural tests only) 🔐 Generated with Claude Code https://claude.com/claude-code Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-17 12:29:27 -07:00
// Add data rows
for (const entity of entities) {
const row = [entity.id]
for (const key of keys) {
const value = entity.metadata?.[key] || ''
// Escape values that contain commas
feat(v4.0.0): Complete metadata/vector separation architecture with Azure support This commit completes the core v4.0.0 architecture changes for billion-scale performance with metadata/vector separation. NO RELEASE YET - remaining optimizations and testing required before production release. ## Core v4.0.0 Architecture Changes ### Type System Updates - Fixed all TypeScript compilation errors (zero errors achieved) - Updated HNSWNoun/HNSWVerb to separate core fields from metadata - Implemented HNSWNounWithMetadata/HNSWVerbWithMetadata for API boundaries - Added required 'noun' field to NounMetadata for semantic structure - Renamed verb.type to verb.verb for consistency ### Storage Adapter Updates **All adapters updated for v4.0.0 two-file storage pattern:** - memoryStorage: Proper metadata/vector separation - fileSystemStorage: Two-file pattern with sharding - opfsStorage: Browser persistent storage updated - s3CompatibleStorage: AWS/MinIO/DigitalOcean support - r2Storage: Cloudflare R2 optimization - gcsStorage: Google Cloud with ADC support - **azureBlobStorage: NEW - Full Azure Blob Storage support** ### Storage Features - BaseStorage: Internal vs public method separation (_getNoun vs getNoun) - Two-file storage: Vectors in one file, metadata in another - Change tracking: getChangesSince return type updated - Pagination: getNounsWithPagination returns WithMetadata types ### Azure Blob Storage Integration (NEW) - Native @azure/storage-blob SDK integration - Four authentication methods: * DefaultAzureCredential (Managed Identity) - recommended * Connection String - simplest setup * Account Name + Key - traditional auth * SAS Token - delegated access - High-volume mode with write buffering - Adaptive backpressure for throttling - UUID-based sharding for billion-scale - Full HNSW support with graph persistence ### Utility Updates - EmbeddingManager: Updated to accept Record<string, unknown> - LSMTree: Wrapped data in NounMetadata structure with 'noun' field - EntityIdMapper: Fixed nested metadata.data structure access - MetadataIndex: Fixed field type inference integration - PeriodicCleanup: Updated for new metadata structure ### Core API Updates - Brainy: Updated verb property access from v.type to v.verb - ConfigAPI: Fixed NounMetadata access patterns - DataAPI: Updated metadata handling ### Documentation Updates - CREATING-AUGMENTATIONS.md: v4.0.0 breaking changes guide - DEVELOPER-GUIDE.md: Migration checklist and examples - COMPLETE-REFERENCE.md: v4.0.0 architecture improvements - **finite-type-system.md: NEW - Revolutionary type system benefits** ### Build & Dependencies - Zero TypeScript compilation errors - Added @azure/storage-blob and @azure/identity - 591 tests passing (23 timeout in long-running neural tests) ## What's NOT in This Release This is a work-in-progress commit. Before v4.0.0 release we need: - Storage adapter optimizations (batch operations, compression) - Azure blob tier management (Hot/Cool/Archive) - Cost optimization implementations - Additional performance testing at billion-scale - Migration guides for v3.x users ## Testing - Clean build: ✅ - Type checking: ✅ (zero errors) - Test suite: ✅ (591/614 passing, timeouts in neural tests only) 🔐 Generated with Claude Code https://claude.com/claude-code Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-17 12:29:27 -07:00
const escaped = String(value).includes(',')
? `"${String(value).replace(/"/g, '""')}"`
: String(value)
row.push(escaped)
}
rows.push(row.join(','))
}
feat(v4.0.0): Complete metadata/vector separation architecture with Azure support This commit completes the core v4.0.0 architecture changes for billion-scale performance with metadata/vector separation. NO RELEASE YET - remaining optimizations and testing required before production release. ## Core v4.0.0 Architecture Changes ### Type System Updates - Fixed all TypeScript compilation errors (zero errors achieved) - Updated HNSWNoun/HNSWVerb to separate core fields from metadata - Implemented HNSWNounWithMetadata/HNSWVerbWithMetadata for API boundaries - Added required 'noun' field to NounMetadata for semantic structure - Renamed verb.type to verb.verb for consistency ### Storage Adapter Updates **All adapters updated for v4.0.0 two-file storage pattern:** - memoryStorage: Proper metadata/vector separation - fileSystemStorage: Two-file pattern with sharding - opfsStorage: Browser persistent storage updated - s3CompatibleStorage: AWS/MinIO/DigitalOcean support - r2Storage: Cloudflare R2 optimization - gcsStorage: Google Cloud with ADC support - **azureBlobStorage: NEW - Full Azure Blob Storage support** ### Storage Features - BaseStorage: Internal vs public method separation (_getNoun vs getNoun) - Two-file storage: Vectors in one file, metadata in another - Change tracking: getChangesSince return type updated - Pagination: getNounsWithPagination returns WithMetadata types ### Azure Blob Storage Integration (NEW) - Native @azure/storage-blob SDK integration - Four authentication methods: * DefaultAzureCredential (Managed Identity) - recommended * Connection String - simplest setup * Account Name + Key - traditional auth * SAS Token - delegated access - High-volume mode with write buffering - Adaptive backpressure for throttling - UUID-based sharding for billion-scale - Full HNSW support with graph persistence ### Utility Updates - EmbeddingManager: Updated to accept Record<string, unknown> - LSMTree: Wrapped data in NounMetadata structure with 'noun' field - EntityIdMapper: Fixed nested metadata.data structure access - MetadataIndex: Fixed field type inference integration - PeriodicCleanup: Updated for new metadata structure ### Core API Updates - Brainy: Updated verb property access from v.type to v.verb - ConfigAPI: Fixed NounMetadata access patterns - DataAPI: Updated metadata handling ### Documentation Updates - CREATING-AUGMENTATIONS.md: v4.0.0 breaking changes guide - DEVELOPER-GUIDE.md: Migration checklist and examples - COMPLETE-REFERENCE.md: v4.0.0 architecture improvements - **finite-type-system.md: NEW - Revolutionary type system benefits** ### Build & Dependencies - Zero TypeScript compilation errors - Added @azure/storage-blob and @azure/identity - 591 tests passing (23 timeout in long-running neural tests) ## What's NOT in This Release This is a work-in-progress commit. Before v4.0.0 release we need: - Storage adapter optimizations (batch operations, compression) - Azure blob tier management (Hot/Cool/Archive) - Cost optimization implementations - Additional performance testing at billion-scale - Migration guides for v3.x users ## Testing - Clean build: ✅ - Type checking: ✅ (zero errors) - Test suite: ✅ (591/614 passing, timeouts in neural tests only) 🔐 Generated with Claude Code https://claude.com/claude-code Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-17 12:29:27 -07:00
return rows.join('\n')
}
private generateId(): string {
return `import_${Date.now()}_${Math.random().toString(36).substr(2, 9)}`
}
}