@soulcraft/brainy 3.27.1 → 3.29.0

package/CHANGELOG.md

@@ -2,6 +2,18 @@
 
 All notable changes to this project will be documented in this file. See [standard-version](https://github.com/conventional-changelog/standard-version) for commit guidelines.
 
+## [3.29.0](https://github.com/soulcraftlabs/brainy/compare/v3.28.0...v3.29.0) (2025-10-09)
+
+
+### 🐛 Bug Fixes
+
+* enable GCS native storage with Application Default Credentials ([1e77ecd](https://github.com/soulcraftlabs/brainy/commit/1e77ecd145d3dea46e04ca5ecc6692b41e569c1e))
+
+### [3.28.0](https://github.com/soulcraftlabs/brainy/compare/v3.27.1...v3.28.0) (2025-10-08)
+
+- feat: add unified import system with auto-detection and dual storage (a06e877)
+
+
 ### [3.27.1](https://github.com/soulcraftlabs/brainy/compare/v3.27.0...v3.27.1) (2025-10-08)
 
 - docs: clarify GCS storage type and config object pairing (dcbd0fd)

package/dist/brainy.d.ts

@@ -640,6 +640,56 @@ export declare class Brainy<T = any> implements BrainyInterface<T> {
         confidence?: number;
         limit?: number;
     }): Promise<string[]>;
+    /**
+     * Import files with auto-detection and dual storage (VFS + Knowledge Graph)
+     *
+     * Unified import system that:
+     * - Auto-detects format (Excel, PDF, CSV, JSON, Markdown)
+     * - Extracts entities and relationships
+     * - Stores in both VFS (organized files) and Knowledge Graph (connected entities)
+     * - Links VFS files to graph entities
+     *
+     * @example
+     * // Import from file path
+     * const result = await brain.import('/path/to/file.xlsx')
+     *
+     * @example
+     * // Import from buffer
+     * const result = await brain.import(buffer, { format: 'pdf' })
+     *
+     * @example
+     * // Import JSON object
+     * const result = await brain.import({ entities: [...] })
+     *
+     * @example
+     * // Custom VFS path and grouping
+     * const result = await brain.import(buffer, {
+     *   vfsPath: '/my-imports/data',
+     *   groupBy: 'type',
+     *   onProgress: (progress) => console.log(progress.message)
+     * })
+     */
+    import(source: Buffer | string | object, options?: {
+        format?: 'excel' | 'pdf' | 'csv' | 'json' | 'markdown';
+        vfsPath?: string;
+        groupBy?: 'type' | 'sheet' | 'flat' | 'custom';
+        customGrouping?: (entity: any) => string;
+        createEntities?: boolean;
+        createRelationships?: boolean;
+        preserveSource?: boolean;
+        enableNeuralExtraction?: boolean;
+        enableRelationshipInference?: boolean;
+        enableConceptExtraction?: boolean;
+        confidenceThreshold?: number;
+        onProgress?: (progress: {
+            stage: 'detecting' | 'extracting' | 'storing-vfs' | 'storing-graph' | 'complete';
+            message: string;
+            processed?: number;
+            total?: number;
+            entities?: number;
+            relationships?: number;
+        }) => void;
+    }): Promise<import("./import/ImportCoordinator.js").ImportResult>;
     /**
      * Virtual File System API - Knowledge Operating System
      */

package/dist/brainy.js

@@ -1419,6 +1419,42 @@ export class Brainy {
         // Apply limit if specified
         return options?.limit ? concepts.slice(0, options.limit) : concepts;
     }
+    /**
+     * Import files with auto-detection and dual storage (VFS + Knowledge Graph)
+     *
+     * Unified import system that:
+     * - Auto-detects format (Excel, PDF, CSV, JSON, Markdown)
+     * - Extracts entities and relationships
+     * - Stores in both VFS (organized files) and Knowledge Graph (connected entities)
+     * - Links VFS files to graph entities
+     *
+     * @example
+     * // Import from file path
+     * const result = await brain.import('/path/to/file.xlsx')
+     *
+     * @example
+     * // Import from buffer
+     * const result = await brain.import(buffer, { format: 'pdf' })
+     *
+     * @example
+     * // Import JSON object
+     * const result = await brain.import({ entities: [...] })
+     *
+     * @example
+     * // Custom VFS path and grouping
+     * const result = await brain.import(buffer, {
+     *   vfsPath: '/my-imports/data',
+     *   groupBy: 'type',
+     *   onProgress: (progress) => console.log(progress.message)
+     * })
+     */
+    async import(source, options) {
+        // Lazy load ImportCoordinator
+        const { ImportCoordinator } = await import('./import/ImportCoordinator.js');
+        const coordinator = new ImportCoordinator(this);
+        await coordinator.init();
+        return await coordinator.import(source, options);
+    }
     /**
      * Virtual File System API - Knowledge Operating System
      */
@@ -2238,8 +2274,24 @@ export class Brainy {
      */
     normalizeConfig(config) {
         // Validate storage configuration
-        if (config?.storage?.type && !['auto', 'memory', 'filesystem', 'opfs', 'remote', 's3', 'r2', 'gcs'].includes(config.storage.type)) {
-            throw new Error(`Invalid storage type: ${config.storage.type}. Must be one of: auto, memory, filesystem, opfs, remote, s3, r2, gcs`);
+        if (config?.storage?.type && !['auto', 'memory', 'filesystem', 'opfs', 'remote', 's3', 'r2', 'gcs', 'gcs-native'].includes(config.storage.type)) {
+            throw new Error(`Invalid storage type: ${config.storage.type}. Must be one of: auto, memory, filesystem, opfs, remote, s3, r2, gcs, gcs-native`);
+        }
+        // Validate storage type/config pairing (catch common mismatches)
+        if (config?.storage) {
+            const storage = config.storage;
+            // Check for gcs/gcsNativeStorage mismatch
+            if (storage.type === 'gcs' && storage.gcsNativeStorage) {
+                throw new Error(`Storage type/config mismatch: type 'gcs' requires 'gcsStorage' config object (S3-compatible). ` +
+                    `You provided 'gcsNativeStorage' which requires type 'gcs-native'. ` +
+                    `Either change type to 'gcs-native' or use 'gcsStorage' instead of 'gcsNativeStorage'.`);
+            }
+            // Check for gcs-native/gcsStorage mismatch
+            if (storage.type === 'gcs-native' && storage.gcsStorage) {
+                throw new Error(`Storage type/config mismatch: type 'gcs-native' requires 'gcsNativeStorage' config object. ` +
+                    `You provided 'gcsStorage' which requires type 'gcs' (S3-compatible). ` +
+                    `Either change type to 'gcs' or use 'gcsNativeStorage' instead of 'gcsStorage'.`);
+            }
         }
         // Validate model configuration
         if (config?.model?.type && !['fast', 'accurate', 'custom'].includes(config.model.type)) {

package/dist/config/storageAutoConfig.d.ts

@@ -11,6 +11,7 @@ export declare enum StorageType {
     OPFS = "opfs",
     S3 = "s3",
     GCS = "gcs",
+    GCS_NATIVE = "gcs-native",
     R2 = "r2"
 }
 /**
@@ -22,7 +23,7 @@ export declare enum StoragePreset {
     DISK = "disk",
     CLOUD = "cloud"
 }
-export type StorageTypeString = 'memory' | 'filesystem' | 'opfs' | 's3' | 'gcs' | 'r2';
+export type StorageTypeString = 'memory' | 'filesystem' | 'opfs' | 's3' | 'gcs' | 'r2' | 'gcs-native';
 export type StoragePresetString = 'auto' | 'memory' | 'disk' | 'cloud';
 export interface StorageConfigResult {
     type: StorageType | StorageTypeString;

package/dist/config/storageAutoConfig.js

@@ -13,6 +13,7 @@ export var StorageType;
     StorageType["OPFS"] = "opfs";
     StorageType["S3"] = "s3";
     StorageType["GCS"] = "gcs";
+    StorageType["GCS_NATIVE"] = "gcs-native";
     StorageType["R2"] = "r2";
 })(StorageType || (StorageType = {}));
 /**
@@ -170,14 +171,14 @@ async function detectCloudStorage() {
             }
         };
     }
-    // Google Cloud Storage Detection
+    // Google Cloud Storage Detection (Native SDK with ADC)
     if (hasGCPConfig()) {
         return {
-            type: StorageType.GCS,
+            type: StorageType.GCS_NATIVE,
             config: {
-                gcsStorage: {
+                gcsNativeStorage: {
                     bucketName: process.env.GCS_BUCKET || process.env.GOOGLE_STORAGE_BUCKET || 'brainy-data',
-                    // Credentials will be picked up by GCP SDK automatically
+                    // Application Default Credentials will be picked up automatically
                 }
             }
         };

package/dist/import/EntityDeduplicator.d.ts

@@ -0,0 +1,84 @@
+/**
+ * Entity Deduplicator
+ *
+ * Finds and merges duplicate entities across imports using:
+ * - Embedding-based similarity matching
+ * - Type-aware comparison
+ * - Confidence-weighted merging
+ * - Provenance tracking
+ *
+ * NO MOCKS - Production-ready implementation
+ */
+import { Brainy } from '../brainy.js';
+import { NounType } from '../types/graphTypes.js';
+export interface EntityCandidate {
+    id?: string;
+    name: string;
+    type: NounType;
+    description: string;
+    confidence: number;
+    metadata: Record<string, any>;
+}
+export interface DuplicateMatch {
+    existingId: string;
+    existingName: string;
+    similarity: number;
+    shouldMerge: boolean;
+    reason: string;
+}
+export interface EntityDeduplicationOptions {
+    /** Similarity threshold for considering entities as duplicates (0-1) */
+    similarityThreshold?: number;
+    /** Only match entities of the same type */
+    strictTypeMatching?: boolean;
+    /** Enable fuzzy name matching */
+    enableFuzzyMatching?: boolean;
+    /** Minimum confidence to consider for merging */
+    minConfidence?: number;
+}
+export interface MergeResult {
+    mergedEntityId: string;
+    wasMerged: boolean;
+    mergedWith?: string;
+    confidence: number;
+    provenance: string[];
+}
+/**
+ * EntityDeduplicator - Prevents duplicate entities across imports
+ */
+export declare class EntityDeduplicator {
+    private brain;
+    constructor(brain: Brainy);
+    /**
+     * Find duplicate entities in the knowledge graph
+     */
+    findDuplicates(candidate: EntityCandidate, options?: EntityDeduplicationOptions): Promise<DuplicateMatch | null>;
+    /**
+     * Merge entity data with existing entity
+     */
+    mergeEntity(existingId: string, candidate: EntityCandidate, importSource: string): Promise<MergeResult>;
+    /**
+     * Create or merge entity with deduplication
+     */
+    createOrMerge(candidate: EntityCandidate, importSource: string, options?: EntityDeduplicationOptions): Promise<MergeResult>;
+    /**
+     * Normalize string for comparison
+     */
+    private normalizeString;
+    /**
+     * Check if two names are similar (fuzzy matching)
+     */
+    private areSimilarNames;
+    /**
+     * Calculate Levenshtein distance between two strings
+     */
+    private levenshteinDistance;
+    /**
+     * Merge confidence scores (weighted average favoring higher confidence)
+     */
+    private mergeConfidence;
+    /**
+     * Merge metadata fields intelligently
+     */
+    private mergeMetadataFields;
+}

package/dist/import/EntityDeduplicator.js

@@ -0,0 +1,255 @@
+/**
+ * Entity Deduplicator
+ *
+ * Finds and merges duplicate entities across imports using:
+ * - Embedding-based similarity matching
+ * - Type-aware comparison
+ * - Confidence-weighted merging
+ * - Provenance tracking
+ *
+ * NO MOCKS - Production-ready implementation
+ */
+/**
+ * EntityDeduplicator - Prevents duplicate entities across imports
+ */
+export class EntityDeduplicator {
+    constructor(brain) {
+        this.brain = brain;
+    }
+    /**
+     * Find duplicate entities in the knowledge graph
+     */
+    async findDuplicates(candidate, options = {}) {
+        const opts = {
+            similarityThreshold: options.similarityThreshold || 0.85,
+            strictTypeMatching: options.strictTypeMatching !== false,
+            enableFuzzyMatching: options.enableFuzzyMatching !== false,
+            minConfidence: options.minConfidence || 0.6
+        };
+        // Skip low-confidence candidates
+        if (candidate.confidence < opts.minConfidence) {
+            return null;
+        }
+        // Search for similar entities by name and description
+        const searchText = `${candidate.name} ${candidate.description}`.trim();
+        try {
+            const results = await this.brain.find({
+                query: searchText,
+                limit: 5,
+                where: opts.strictTypeMatching ? { type: candidate.type } : undefined
+            });
+            // Check each result for potential duplicates
+            for (const result of results) {
+                const similarity = result.score || 0;
+                const existingName = result.entity.metadata?.name || result.id;
+                const existingType = result.entity.metadata?.type || result.entity.metadata?.nounType || result.entity.type;
+                // Skip if below similarity threshold
+                if (similarity < opts.similarityThreshold) {
+                    continue;
+                }
+                // Type matching check
+                if (opts.strictTypeMatching && existingType !== candidate.type) {
+                    continue;
+                }
+                // Exact name match (case-insensitive)
+                if (this.normalizeString(candidate.name) === this.normalizeString(existingName)) {
+                    return {
+                        existingId: result.id,
+                        existingName,
+                        similarity: 1.0,
+                        shouldMerge: true,
+                        reason: 'Exact name match'
+                    };
+                }
+                // High similarity match
+                if (similarity >= opts.similarityThreshold) {
+                    // Additional validation for fuzzy matching
+                    if (opts.enableFuzzyMatching && this.areSimilarNames(candidate.name, existingName)) {
+                        return {
+                            existingId: result.id,
+                            existingName,
+                            similarity,
+                            shouldMerge: true,
+                            reason: `High similarity (${(similarity * 100).toFixed(1)}%)`
+                        };
+                    }
+                }
+            }
+        }
+        catch (error) {
+            // If search fails, assume no duplicates
+            return null;
+        }
+        return null;
+    }
+    /**
+     * Merge entity data with existing entity
+     */
+    async mergeEntity(existingId, candidate, importSource) {
+        try {
+            // Get existing entity
+            const existing = await this.brain.get(existingId);
+            if (!existing) {
+                throw new Error(`Entity ${existingId} not found`);
+            }
+            // Merge metadata
+            const mergedMetadata = {
+                ...existing.metadata,
+                // Track provenance
+                imports: [
+                    ...(existing.metadata?.imports || []),
+                    importSource
+                ],
+                // Merge VFS paths
+                vfsPaths: [
+                    ...(existing.metadata?.vfsPaths || [existing.metadata?.vfsPath]).filter(Boolean),
+                    candidate.metadata?.vfsPath
+                ].filter(Boolean),
+                // Update confidence (weighted average)
+                confidence: this.mergeConfidence(existing.metadata?.confidence || 0.5, candidate.confidence),
+                // Merge other metadata
+                ...this.mergeMetadataFields(existing.metadata, candidate.metadata),
+                // Track last update
+                lastUpdated: Date.now(),
+                mergeCount: (existing.metadata?.mergeCount || 0) + 1
+            };
+            // Update entity
+            await this.brain.update({
+                id: existingId,
+                metadata: mergedMetadata,
+                merge: true
+            });
+            return {
+                mergedEntityId: existingId,
+                wasMerged: true,
+                mergedWith: existing.metadata?.name || existingId,
+                confidence: mergedMetadata.confidence,
+                provenance: mergedMetadata.imports
+            };
+        }
+        catch (error) {
+            throw new Error(`Failed to merge entity: ${error instanceof Error ? error.message : String(error)}`);
+        }
+    }
+    /**
+     * Create or merge entity with deduplication
+     */
+    async createOrMerge(candidate, importSource, options = {}) {
+        // Check for duplicates
+        const duplicate = await this.findDuplicates(candidate, options);
+        if (duplicate && duplicate.shouldMerge) {
+            // Merge with existing entity
+            return await this.mergeEntity(duplicate.existingId, candidate, importSource);
+        }
+        // No duplicate found, create new entity
+        const entityId = await this.brain.add({
+            data: candidate.description || candidate.name,
+            type: candidate.type,
+            metadata: {
+                ...candidate.metadata,
+                name: candidate.name,
+                confidence: candidate.confidence,
+                imports: [importSource],
+                vfsPaths: [candidate.metadata?.vfsPath].filter(Boolean),
+                createdAt: Date.now(),
+                mergeCount: 0
+            }
+        });
+        // Update candidate with new ID
+        candidate.id = entityId;
+        return {
+            mergedEntityId: entityId,
+            wasMerged: false,
+            confidence: candidate.confidence,
+            provenance: [importSource]
+        };
+    }
+    /**
+     * Normalize string for comparison
+     */
+    normalizeString(str) {
+        return str
+            .toLowerCase()
+            .trim()
+            .replace(/[^a-z0-9]/g, '');
+    }
+    /**
+     * Check if two names are similar (fuzzy matching)
+     */
+    areSimilarNames(name1, name2) {
+        const n1 = this.normalizeString(name1);
+        const n2 = this.normalizeString(name2);
+        // Exact match
+        if (n1 === n2)
+            return true;
+        // Length difference check
+        const lengthDiff = Math.abs(n1.length - n2.length);
+        if (lengthDiff > 3)
+            return false;
+        // Levenshtein distance
+        const distance = this.levenshteinDistance(n1, n2);
+        const maxLength = Math.max(n1.length, n2.length);
+        const similarity = 1 - (distance / maxLength);
+        return similarity >= 0.85;
+    }
+    /**
+     * Calculate Levenshtein distance between two strings
+     */
+    levenshteinDistance(str1, str2) {
+        const m = str1.length;
+        const n = str2.length;
+        const dp = Array(m + 1).fill(null).map(() => Array(n + 1).fill(0));
+        for (let i = 0; i <= m; i++)
+            dp[i][0] = i;
+        for (let j = 0; j <= n; j++)
+            dp[0][j] = j;
+        for (let i = 1; i <= m; i++) {
+            for (let j = 1; j <= n; j++) {
+                if (str1[i - 1] === str2[j - 1]) {
+                    dp[i][j] = dp[i - 1][j - 1];
+                }
+                else {
+                    dp[i][j] = Math.min(dp[i - 1][j] + 1, // deletion
+                    dp[i][j - 1] + 1, // insertion
+                    dp[i - 1][j - 1] + 1 // substitution
+                    );
+                }
+            }
+        }
+        return dp[m][n];
+    }
+    /**
+     * Merge confidence scores (weighted average favoring higher confidence)
+     */
+    mergeConfidence(existing, incoming) {
+        // Weight higher confidence more heavily
+        const weights = existing > incoming ? [0.6, 0.4] : [0.4, 0.6];
+        return existing * weights[0] + incoming * weights[1];
+    }
+    /**
+     * Merge metadata fields intelligently
+     */
+    mergeMetadataFields(existing, incoming) {
+        const merged = {};
+        // Merge arrays
+        const arrayFields = ['concepts', 'tags', 'categories'];
+        for (const field of arrayFields) {
+            if (existing[field] || incoming[field]) {
+                const combined = [
+                    ...(existing[field] || []),
+                    ...(incoming[field] || [])
+                ];
+                // Deduplicate
+                merged[field] = [...new Set(combined)];
+            }
+        }
+        // Prefer longer descriptions
+        if (existing.description || incoming.description) {
+            merged.description = (existing.description || '').length > (incoming.description || '').length
+                ? existing.description
+                : incoming.description;
+        }
+        return merged;
+    }
+}
+//# sourceMappingURL=EntityDeduplicator.js.map

package/dist/import/FormatDetector.d.ts

@@ -0,0 +1,65 @@
+/**
+ * Format Detector
+ *
+ * Unified format detection for all import types using:
+ * - Magic byte signatures (PDF, Excel, images)
+ * - File extensions
+ * - Content analysis (JSON, Markdown, CSV)
+ *
+ * NO MOCKS - Production-ready implementation
+ */
+export type SupportedFormat = 'excel' | 'pdf' | 'csv' | 'json' | 'markdown';
+export interface DetectionResult {
+    format: SupportedFormat;
+    confidence: number;
+    evidence: string[];
+}
+/**
+ * FormatDetector - Detect file format from various inputs
+ */
+export declare class FormatDetector {
+    /**
+     * Detect format from buffer
+     */
+    detectFromBuffer(buffer: Buffer): DetectionResult | null;
+    /**
+     * Detect format from file path
+     */
+    detectFromPath(path: string): DetectionResult | null;
+    /**
+     * Detect format from string content
+     */
+    detectFromString(content: string): DetectionResult | null;
+    /**
+     * Detect format from object
+     */
+    detectFromObject(obj: any): DetectionResult | null;
+    /**
+     * Detect by magic bytes
+     */
+    private detectByMagicBytes;
+    /**
+     * Detect by content analysis
+     */
+    private detectByContent;
+    /**
+     * Check if content looks like JSON
+     */
+    private looksLikeJSON;
+    /**
+     * Check if content looks like Markdown
+     */
+    private looksLikeMarkdown;
+    /**
+     * Check if content looks like CSV
+     */
+    private looksLikeCSV;
+    /**
+     * Check if content is text-based (not binary)
+     */
+    private isTextContent;
+    /**
+     * Get file extension from path
+     */
+    private getExtension;
+}