@sparkleideas/embeddings 3.0.0-alpha.15 → 3.0.0-alpha.17

package/README.md

@@ -4,27 +4,26 @@
 [![npm downloads](https://img.shields.io/npm/dm/@claude-flow/embeddings.svg)](https://www.npmjs.com/package/@claude-flow/embeddings)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![TypeScript](https://img.shields.io/badge/TypeScript-5.0+-blue.svg)](https://www.typescriptlang.org/)
-[![Performance](https://img.shields.io/badge/Performance-<5ms-brightgreen.svg)](https://github.com/ruvnet/claude-flow)
+[![Performance](https://img.shields.io/badge/Performance-<100ms-brightgreen.svg)](https://github.com/ruvnet/claude-flow)
 
-> High-performance embedding generation module for Claude Flow V3 - multi-provider support with persistent caching, document chunking, normalization, hyperbolic embeddings, and neural substrate integration.
+> High-performance embedding generation module for Claude Flow V3 - multi-provider support, LRU caching, batch processing, and similarity computation.
 
 ## Features
 
-### Core Embedding
-- **Multiple Providers** - Agentic-Flow (ONNX), OpenAI, Transformers.js, and Mock
-- **Auto-Install** - Automatically installs agentic-flow when using `provider: 'auto'`
-- **Smart Fallback** - Graceful fallback chain: agentic-flow → transformers → mock
-- **LRU + Disk Caching** - In-memory LRU + SQLite persistent cache with TTL
+- **Multiple Providers** - OpenAI, Transformers.js (local), and Mock for testing
+- **LRU Caching** - Intelligent caching with configurable size and hit rate tracking
 - **Batch Processing** - Efficient batch embedding with partial cache hits
 - **Similarity Functions** - Cosine, Euclidean, and dot product metrics
-- **75x Faster** - Agentic-flow ONNX is 75x faster than Transformers.js
+- **Event System** - Observable embedding operations with event listeners
+- **Type-Safe** - Full TypeScript support with comprehensive type definitions
 
-### Advanced Features (New in v3.0.0-alpha.11)
-- **Document Chunking** - Character, sentence, paragraph, and token-based chunking with overlap
-- **Multiple Normalization** - L2, L1, min-max, and z-score normalization
-- **Hyperbolic Embeddings** - Poincaré ball model for hierarchical representations
-- **Neural Substrate** - Semantic drift detection, memory physics, swarm coordination
-- **Persistent Cache** - SQLite-backed disk cache with LRU eviction and TTL
+## Performance Targets
+
+| Operation | API Provider | Local Provider |
+|-----------|--------------|----------------|
+| Single embedding | <100ms | <50ms |
+| Batch (10 items) | <500ms | <200ms |
+| Cache hit | <1ms | <1ms |
 
 ## Installation
 
@@ -67,45 +66,19 @@ const similarity = cosineSimilarity(
 console.log(`Similarity: ${similarity.toFixed(4)}`);
 ```
 
-## CLI Usage
-
-```bash
-# Generate embedding from CLI
-claude-flow embeddings embed "Your text here"
-
-# Batch embed from file
-claude-flow embeddings batch documents.txt -o embeddings.json
-
-# Similarity search
-claude-flow embeddings search "query" --index ./vectors
-
-# Initialize agentic-flow model
-claude-flow embeddings init --provider agentic-flow
-```
-
 ## API Reference
 
 ### Factory Functions
 
 ```typescript
-import {
-  createEmbeddingService,
-  createEmbeddingServiceAsync,
-  getEmbedding
-} from '@claude-flow/embeddings';
+import { createEmbeddingService, getEmbedding } from '@claude-flow/embeddings';
 
-// Sync: Create with known provider
+// Create a service instance
 const service = createEmbeddingService({
   provider: 'openai',
   apiKey: 'your-api-key',
   model: 'text-embedding-3-small',
-});
-
-// Async: Auto-select best provider with fallback
-const autoService = await createEmbeddingServiceAsync({
-  provider: 'auto',       // agentic-flow → transformers → mock
-  autoInstall: true,      // Install agentic-flow if missing
-  fallback: 'transformers', // Custom fallback
+  cacheSize: 1000,
 });
 
 // Quick one-off embedding
@@ -135,22 +108,6 @@ const result = await service.embed('Your text here');
 console.log('Tokens used:', result.usage?.totalTokens);
 ```
 
-### Agentic-Flow Provider (Fastest)
-
-```typescript
-import { AgenticFlowEmbeddingService } from '@claude-flow/embeddings';
-
-const service = new AgenticFlowEmbeddingService({
-  provider: 'agentic-flow',
-  modelId: 'default',     // Uses optimized ONNX model
-  cacheSize: 256,
-});
-
-// 75x faster than Transformers.js (3ms vs 233ms)
-const result = await service.embed('Your text here');
-console.log(`ONNX embedding in ${result.latencyMs}ms`);
-```
-
 ### Transformers.js Provider (Local)
 
 ```typescript
@@ -286,17 +243,10 @@ service.removeEventListener(listener);
 
 | Provider | Latency | Quality | Cost | Offline |
 |----------|---------|---------|------|---------|
-| **Agentic-Flow** | ~3ms | Good | Free | Yes |
 | **OpenAI** | ~50-100ms | Excellent | $0.02-0.13/1M tokens | No |
-| **Transformers.js** | ~230ms | Good | Free | Yes |
+| **Transformers.js** | ~20-50ms | Good | Free | Yes |
 | **Mock** | <1ms | N/A | Free | Yes |
 
-### Agentic-Flow (Recommended)
-
-| Model | Dimensions | Speed | Best For |
-|-------|------------|-------|----------|
-| `default` | 384 | 3ms | General purpose, fastest |
-
 ### OpenAI Models
 
 | Model | Dimensions | Max Tokens | Best For |
@@ -322,9 +272,7 @@ import type {
   EmbeddingConfig,
   OpenAIEmbeddingConfig,
   TransformersEmbeddingConfig,
-  AgenticFlowEmbeddingConfig,
   MockEmbeddingConfig,
-  AutoEmbeddingConfig,
 
   // Result types
   EmbeddingResult,
@@ -401,245 +349,6 @@ const queryResult = await embeddings.embed('Search query');
 const results = await index.search(new Float32Array(queryResult.embedding), 5);
 ```
 
-## Document Chunking
-
-Split long documents into overlapping chunks for embedding:
-
-```typescript
-import { chunkText, estimateTokens, reconstructFromChunks } from '@claude-flow/embeddings';
-
-// Chunk by sentence (default)
-const result = chunkText(longDocument, {
-  maxChunkSize: 512,
-  overlap: 50,
-  strategy: 'sentence',  // 'character' | 'sentence' | 'paragraph' | 'token'
-  minChunkSize: 100,
-});
-
-console.log('Chunks:', result.totalChunks);
-result.chunks.forEach((chunk, i) => {
-  console.log(`Chunk ${i}: ${chunk.length} chars, ~${chunk.tokenCount} tokens`);
-});
-
-// Estimate tokens
-const tokens = estimateTokens('Hello world');  // ~3 tokens
-
-// Reconstruct (approximate)
-const reconstructed = reconstructFromChunks(result.chunks);
-```
-
-## Normalization
-
-Normalize embeddings for consistent similarity computation:
-
-```typescript
-import {
-  l2Normalize,    // Unit vector (Euclidean norm = 1)
-  l1Normalize,    // Manhattan norm = 1
-  minMaxNormalize, // Values in [0, 1]
-  zScoreNormalize, // Mean 0, std 1
-  normalize,       // Generic with type option
-  l2Norm,
-  isNormalized,
-} from '@claude-flow/embeddings';
-
-const embedding = new Float32Array([3, 4, 0]);
-
-// L2 normalize (most common for cosine similarity)
-const l2 = l2Normalize(embedding);  // [0.6, 0.8, 0]
-console.log('L2 norm:', l2Norm(l2));  // 1.0
-
-// Check if already normalized
-console.log(isNormalized(l2));  // true
-console.log(isNormalized(embedding));  // false
-
-// Generic normalize with type
-const normalized = normalize(embedding, { type: 'l2' });
-```
-
-## Hyperbolic Embeddings (Poincaré Ball)
-
-Transform embeddings to hyperbolic space for better hierarchical representation:
-
-```typescript
-import {
-  euclideanToPoincare,
-  poincareToEuclidean,
-  hyperbolicDistance,
-  mobiusAdd,
-  isInPoincareBall,
-  batchEuclideanToPoincare,
-  hyperbolicCentroid,
-} from '@claude-flow/embeddings';
-
-// Convert Euclidean embedding to Poincaré ball
-const euclidean = new Float32Array([0.5, 0.3, 0.2]);
-const poincare = euclideanToPoincare(euclidean);
-
-// Check if point is in the ball
-console.log(isInPoincareBall(poincare));  // true
-
-// Round-trip conversion
-const back = poincareToEuclidean(poincare);
-
-// Hyperbolic distance (geodesic in Poincaré ball)
-const a = euclideanToPoincare(new Float32Array([0.1, 0.2, 0.1]));
-const b = euclideanToPoincare(new Float32Array([0.3, 0.1, 0.2]));
-const dist = hyperbolicDistance(a, b);
-
-// Möbius addition (hyperbolic "plus")
-const sum = mobiusAdd(a, b);
-
-// Batch conversion
-const embeddings = [vec1, vec2, vec3];
-const hyperbolic = batchEuclideanToPoincare(embeddings);
-
-// Hyperbolic centroid (Fréchet mean)
-const centroid = hyperbolicCentroid(hyperbolic);
-```
-
-### Why Hyperbolic?
-
-Hyperbolic space has natural properties for representing hierarchical data:
-- **Exponential growth** - Tree-like structures fit naturally
-- **Better hierarchy** - Parent-child relationships preserved
-- **Lower distortion** - Taxonomies represented with less error
-
-## Neural Substrate Integration
-
-Access agentic-flow's neural features for advanced embedding operations:
-
-```typescript
-import {
-  NeuralEmbeddingService,
-  createNeuralService,
-  isNeuralAvailable,
-  listEmbeddingModels,
-  downloadEmbeddingModel,
-} from '@claude-flow/embeddings';
-
-// Check if neural features are available
-const available = await isNeuralAvailable();
-
-// Create neural service
-const neural = createNeuralService({ dimension: 384 });
-await neural.init();
-
-if (neural.isAvailable()) {
-  // Semantic drift detection
-  await neural.setDriftBaseline('Initial context about the topic');
-  const drift = await neural.detectDrift('New input to check for drift');
-  console.log('Drift:', drift?.trend);  // 'stable' | 'drifting' | 'accelerating'
-
-  // Memory with interference detection
-  const stored = await neural.storeMemory('mem-1', 'Important information');
-  console.log('Interference:', stored?.interference);
-
-  // Recall by similarity
-  const memories = await neural.recallMemories('query', 5);
-
-  // Swarm coordination
-  await neural.addSwarmAgent('agent-1', 'researcher');
-  const coordination = await neural.coordinateSwarm('Analyze this task');
-
-  // Coherence checking
-  await neural.calibrateCoherence(['good output 1', 'good output 2']);
-  const coherence = await neural.checkCoherence('Output to check');
-
-  // Health status
-  const health = neural.health();
-  console.log('Memory count:', health?.memoryCount);
-}
-
-// List available ONNX models
-const models = await listEmbeddingModels();
-console.log(models);
-// [{ id: 'all-MiniLM-L6-v2', dimension: 384, size: '23MB', ... }]
-
-// Download model
-const path = await downloadEmbeddingModel('all-MiniLM-L6-v2', '.models');
-```
-
-## Persistent Disk Cache
-
-SQLite-backed persistent cache for embeddings:
-
-```typescript
-import { PersistentEmbeddingCache, isPersistentCacheAvailable } from '@claude-flow/embeddings';
-
-// Check if SQLite is available
-const hasSQLite = await isPersistentCacheAvailable();
-
-// Create persistent cache
-const cache = new PersistentEmbeddingCache({
-  dbPath: './embeddings.db',  // SQLite database path
-  maxSize: 10000,             // Max entries before LRU eviction
-  ttlMs: 7 * 24 * 60 * 60 * 1000,  // 7 day TTL
-});
-
-// Initialize
-await cache.init();
-
-// Store embedding
-await cache.set('my text', new Float32Array([0.1, 0.2, 0.3]));
-
-// Retrieve
-const embedding = await cache.get('my text');
-
-// Get stats
-const stats = await cache.getStats();
-console.log('Cache stats:', {
-  size: stats.totalEntries,
-  hitRate: stats.hitRate,
-  avgLatency: stats.avgLatencyMs,
-});
-
-// Close when done
-await cache.close();
-```
-
-### Enable in Embedding Service
-
-```typescript
-const service = createEmbeddingService({
-  provider: 'openai',
-  apiKey: process.env.OPENAI_API_KEY!,
-  persistentCache: {
-    enabled: true,
-    dbPath: './cache/embeddings.db',
-    maxSize: 50000,
-    ttlMs: 30 * 24 * 60 * 60 * 1000,  // 30 days
-  },
-  normalization: 'l2',  // Auto-normalize embeddings
-});
-```
-
-## CLI Commands (New)
-
-```bash
-# Document chunking
-claude-flow embeddings chunk document.txt --strategy sentence --max-size 512
-
-# Normalize embedding file
-claude-flow embeddings normalize embeddings.json --type l2 -o normalized.json
-
-# Convert to hyperbolic
-claude-flow embeddings hyperbolic embeddings.json -o poincare.json
-
-# Neural operations
-claude-flow embeddings neural drift --baseline "context" --input "check this"
-claude-flow embeddings neural store --id mem-1 --content "data"
-claude-flow embeddings neural recall "query" --top-k 5
-
-# List/download models
-claude-flow embeddings models list
-claude-flow embeddings models download all-MiniLM-L6-v2
-
-# Cache management
-claude-flow embeddings cache stats
-claude-flow embeddings cache clear --older-than 7d
-```
-
 ## Related Packages
 
 - [@claude-flow/memory](../memory) - HNSW indexing and vector storage

package/dist/__tests__/embedding-service.test.d.ts

@@ -0,0 +1,2 @@
+export {};
+//# sourceMappingURL=embedding-service.test.d.ts.map

package/dist/__tests__/embedding-service.test.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"embedding-service.test.d.ts","sourceRoot":"","sources":["../../src/__tests__/embedding-service.test.ts"],"names":[],"mappings":""}

package/dist/__tests__/embedding-service.test.js

@@ -0,0 +1,98 @@
+/**
+ * Tests for EmbeddingService
+ */
+import { describe, it, expect, beforeEach } from 'vitest';
+import { createEmbeddingService, MockEmbeddingService, cosineSimilarity, euclideanDistance, dotProduct, computeSimilarity, } from '../index.js';
+describe('EmbeddingService', () => {
+    describe('MockEmbeddingService', () => {
+        let service;
+        beforeEach(() => {
+            service = new MockEmbeddingService({ provider: 'mock', dimensions: 128 });
+        });
+        it('should generate embeddings with correct dimensions', async () => {
+            const result = await service.embed('Hello, world!');
+            expect(result.embedding).toHaveLength(128);
+        });
+        it('should generate deterministic embeddings for same text', async () => {
+            const result1 = await service.embed('test text');
+            const result2 = await service.embed('test text');
+            // Mock service should be deterministic
+            expect(Array.from(result1.embedding)).toEqual(Array.from(result2.embedding));
+        });
+        it('should handle batch embeddings', async () => {
+            const texts = ['text1', 'text2', 'text3'];
+            const results = await service.embedBatch(texts);
+            expect(results.embeddings).toHaveLength(3);
+            // Each embedding should have correct dimensions
+            results.embeddings.forEach((emb) => {
+                expect(emb.length).toBe(128);
+            });
+        });
+    });
+    describe('createEmbeddingService', () => {
+        it('should create mock service', () => {
+            const service = createEmbeddingService({
+                provider: 'mock',
+                dimensions: 64,
+            });
+            expect(service).toBeInstanceOf(MockEmbeddingService);
+        });
+    });
+});
+describe('Similarity Functions', () => {
+    const vec1 = new Float32Array([1, 0, 0]);
+    const vec2 = new Float32Array([1, 0, 0]);
+    const vec3 = new Float32Array([0, 1, 0]);
+    const vec4 = new Float32Array([-1, 0, 0]);
+    describe('cosineSimilarity', () => {
+        it('should return 1 for identical vectors', () => {
+            expect(cosineSimilarity(vec1, vec2)).toBeCloseTo(1);
+        });
+        it('should return 0 for orthogonal vectors', () => {
+            expect(cosineSimilarity(vec1, vec3)).toBeCloseTo(0);
+        });
+        it('should return -1 for opposite vectors', () => {
+            expect(cosineSimilarity(vec1, vec4)).toBeCloseTo(-1);
+        });
+    });
+    describe('euclideanDistance', () => {
+        it('should return 0 for identical vectors', () => {
+            expect(euclideanDistance(vec1, vec2)).toBeCloseTo(0);
+        });
+        it('should return sqrt(2) for unit orthogonal vectors', () => {
+            expect(euclideanDistance(vec1, vec3)).toBeCloseTo(Math.sqrt(2));
+        });
+        it('should return 2 for opposite unit vectors', () => {
+            expect(euclideanDistance(vec1, vec4)).toBeCloseTo(2);
+        });
+    });
+    describe('dotProduct', () => {
+        it('should return 1 for identical unit vectors', () => {
+            expect(dotProduct(vec1, vec2)).toBeCloseTo(1);
+        });
+        it('should return 0 for orthogonal vectors', () => {
+            expect(dotProduct(vec1, vec3)).toBeCloseTo(0);
+        });
+        it('should return -1 for opposite unit vectors', () => {
+            expect(dotProduct(vec1, vec4)).toBeCloseTo(-1);
+        });
+    });
+    describe('computeSimilarity', () => {
+        it('should use cosine metric by default', () => {
+            const result = computeSimilarity(vec1, vec2);
+            expect(result.metric).toBe('cosine');
+            expect(result.score).toBeCloseTo(1);
+        });
+        it('should support euclidean metric', () => {
+            const result = computeSimilarity(vec1, vec3, 'euclidean');
+            expect(result.metric).toBe('euclidean');
+            expect(result.score).toBeCloseTo(Math.sqrt(2));
+        });
+        it('should support dot product metric', () => {
+            const result = computeSimilarity(vec1, vec4, 'dot');
+            expect(result.metric).toBe('dot');
+            expect(result.score).toBeCloseTo(-1);
+        });
+    });
+});
+//# sourceMappingURL=embedding-service.test.js.map

package/dist/__tests__/embedding-service.test.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"embedding-service.test.js","sourceRoot":"","sources":["../../src/__tests__/embedding-service.test.ts"],"names":[],"mappings":"AAAA;;GAEG;AACH,OAAO,EAAE,QAAQ,EAAE,EAAE,EAAE,MAAM,EAAE,UAAU,EAAE,MAAM,QAAQ,CAAC;AAC1D,OAAO,EACL,sBAAsB,EACtB,oBAAoB,EACpB,gBAAgB,EAChB,iBAAiB,EACjB,UAAU,EACV,iBAAiB,GAClB,MAAM,aAAa,CAAC;AAErB,QAAQ,CAAC,kBAAkB,EAAE,GAAG,EAAE;IAChC,QAAQ,CAAC,sBAAsB,EAAE,GAAG,EAAE;QACpC,IAAI,OAA6B,CAAC;QAElC,UAAU,CAAC,GAAG,EAAE;YACd,OAAO,GAAG,IAAI,oBAAoB,CAAC,EAAE,QAAQ,EAAE,MAAM,EAAE,UAAU,EAAE,GAAG,EAAE,CAAC,CAAC;QAC5E,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,oDAAoD,EAAE,KAAK,IAAI,EAAE;YAClE,MAAM,MAAM,GAAG,MAAM,OAAO,CAAC,KAAK,CAAC,eAAe,CAAC,CAAC;YACpD,MAAM,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,YAAY,CAAC,GAAG,CAAC,CAAC;QAC7C,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,wDAAwD,EAAE,KAAK,IAAI,EAAE;YACtE,MAAM,OAAO,GAAG,MAAM,OAAO,CAAC,KAAK,CAAC,WAAW,CAAC,CAAC;YACjD,MAAM,OAAO,GAAG,MAAM,OAAO,CAAC,KAAK,CAAC,WAAW,CAAC,CAAC;YAEjD,uCAAuC;YACvC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC,CAAC;QAC/E,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,gCAAgC,EAAE,KAAK,IAAI,EAAE;YAC9C,MAAM,KAAK,GAAG,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,CAAC;YAC1C,MAAM,OAAO,GAAG,MAAM,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,CAAC;YAEhD,MAAM,CAAC,OAAO,CAAC,UAAU,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,CAAC;YAC3C,gDAAgD;YAChD,OAAO,CAAC,UAAU,CAAC,OAAO,CAAC,CAAC,GAAG,EAAE,EAAE;gBACjC,MAAM,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;YAC/B,CAAC,CAAC,CAAC;QACL,CAAC,CAAC,CAAC;IACL,CAAC,CAAC,CAAC;IAEH,QAAQ,CAAC,wBAAwB,EAAE,GAAG,EAAE;QACtC,EAAE,CAAC,4BAA4B,EAAE,GAAG,EAAE;YACpC,MAAM,OAAO,GAAG,sBAAsB,CAAC;gBACrC,QAAQ,EAAE,MAAM;gBAChB,UAAU,EAAE,EAAE;aACf,CAAC,CAAC;YAEH,MAAM,CAAC,OAAO,CAAC,CAAC,cAAc,CAAC,oBAAoB,CAAC,CAAC;QACvD,CAAC,CAAC,CAAC;IACL,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC;AAEH,QAAQ,CAAC,sBAAsB,EAAE,GAAG,EAAE;IACpC,MAAM,IAAI,GAAG,IAAI,YAAY,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;IACzC,MAAM,IAAI,GAAG,IAAI,YAAY,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;IACzC,MAAM,IAAI,GAAG,IAAI,YAAY,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;IACzC,MAAM,IAAI,GAAG,IAAI,YAAY,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;IAE1C,QAAQ,CAAC,kBAAkB,EAAE,GAAG,EAAE;QAChC,EAAE,CAAC,uCAAuC,EAAE,GAAG,EAAE;YAC/C,MAAM,CAAC,gBAAgB,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC;QACtD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,wCAAwC,EAAE,GAAG,EAAE;YAChD,MAAM,CAAC,gBAAgB,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC;QACtD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,uCAAuC,EAAE,GAAG,EAAE;YAC/C,MAAM,CAAC,gBAAgB,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,CAAC;QACvD,CAAC,CAAC,CAAC;IACL,CAAC,CAAC,CAAC;IAEH,QAAQ,CAAC,mBAAmB,EAAE,GAAG,EAAE;QACjC,EAAE,CAAC,uCAAuC,EAAE,GAAG,EAAE;YAC/C,MAAM,CAAC,iBAAiB,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC;QACvD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,mDAAmD,EAAE,GAAG,EAAE;YAC3D,MAAM,CAAC,iBAAiB,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,CAAC;QAClE,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,2CAA2C,EAAE,GAAG,EAAE;YACnD,MAAM,CAAC,iBAAiB,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC;QACvD,CAAC,CAAC,CAAC;IACL,CAAC,CAAC,CAAC;IAEH,QAAQ,CAAC,YAAY,EAAE,GAAG,EAAE;QAC1B,EAAE,CAAC,4CAA4C,EAAE,GAAG,EAAE;YACpD,MAAM,CAAC,UAAU,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC;QAChD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,wCAAwC,EAAE,GAAG,EAAE;YAChD,MAAM,CAAC,UAAU,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC;QAChD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,4CAA4C,EAAE,GAAG,EAAE;YACpD,MAAM,CAAC,UAAU,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,CAAC;QACjD,CAAC,CAAC,CAAC;IACL,CAAC,CAAC,CAAC;IAEH,QAAQ,CAAC,mBAAmB,EAAE,GAAG,EAAE;QACjC,EAAE,CAAC,qCAAqC,EAAE,GAAG,EAAE;YAC7C,MAAM,MAAM,GAAG,iBAAiB,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;YAC7C,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;YACrC,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC;QACtC,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,iCAAiC,EAAE,GAAG,EAAE;YACzC,MAAM,MAAM,GAAG,iBAAiB,CAAC,IAAI,EAAE,IAAI,EAAE,WAAW,CAAC,CAAC;YAC1D,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC;YACxC,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,CAAC;QACjD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,mCAAmC,EAAE,GAAG,EAAE;YAC3C,MAAM,MAAM,GAAG,iBAAiB,CAAC,IAAI,EAAE,IAAI,EAAE,KAAK,CAAC,CAAC;YACpD,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;YAClC,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,CAAC;QACvC,CAAC,CAAC,CAAC;IACL,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC"}

package/dist/embedding-service.d.ts

@@ -0,0 +1,113 @@
+/**
+ * V3 Embedding Service Implementation
+ *
+ * Production embedding service aligned with agentic-flow@alpha:
+ * - OpenAI provider (text-embedding-3-small/large)
+ * - Transformers.js provider (local ONNX models)
+ * - Mock provider (development/testing)
+ *
+ * Performance Targets:
+ * - Single embedding: <100ms (API), <50ms (local)
+ * - Batch embedding: <500ms for 10 items
+ * - Cache hit: <1ms
+ */
+import { EventEmitter } from 'events';
+import type { EmbeddingProvider, EmbeddingConfig, OpenAIEmbeddingConfig, TransformersEmbeddingConfig, MockEmbeddingConfig, EmbeddingResult, BatchEmbeddingResult, IEmbeddingService, EmbeddingEvent, EmbeddingEventListener, SimilarityMetric, SimilarityResult } from './types.js';
+declare class LRUCache<K, V> {
+    private readonly maxSize;
+    private cache;
+    private hits;
+    private misses;
+    constructor(maxSize: number);
+    get(key: K): V | undefined;
+    set(key: K, value: V): void;
+    clear(): void;
+    get size(): number;
+    get hitRate(): number;
+    getStats(): {
+        size: number;
+        maxSize: number;
+        hits: number;
+        misses: number;
+        hitRate: number;
+    };
+}
+declare abstract class BaseEmbeddingService extends EventEmitter implements IEmbeddingService {
+    protected readonly config: EmbeddingConfig;
+    abstract readonly provider: EmbeddingProvider;
+    protected cache: LRUCache<string, Float32Array>;
+    protected embeddingListeners: Set<EmbeddingEventListener>;
+    constructor(config: EmbeddingConfig);
+    abstract embed(text: string): Promise<EmbeddingResult>;
+    abstract embedBatch(texts: string[]): Promise<BatchEmbeddingResult>;
+    protected emitEvent(event: EmbeddingEvent): void;
+    addEventListener(listener: EmbeddingEventListener): void;
+    removeEventListener(listener: EmbeddingEventListener): void;
+    clearCache(): void;
+    getCacheStats(): {
+        size: number;
+        maxSize: number;
+        hitRate: number;
+    };
+    shutdown(): Promise<void>;
+}
+export declare class OpenAIEmbeddingService extends BaseEmbeddingService {
+    readonly provider: EmbeddingProvider;
+    private readonly apiKey;
+    private readonly model;
+    private readonly baseURL;
+    private readonly timeout;
+    private readonly maxRetries;
+    constructor(config: OpenAIEmbeddingConfig);
+    embed(text: string): Promise<EmbeddingResult>;
+    embedBatch(texts: string[]): Promise<BatchEmbeddingResult>;
+    private callOpenAI;
+}
+export declare class TransformersEmbeddingService extends BaseEmbeddingService {
+    readonly provider: EmbeddingProvider;
+    private pipeline;
+    private readonly modelName;
+    private initialized;
+    constructor(config: TransformersEmbeddingConfig);
+    private initialize;
+    embed(text: string): Promise<EmbeddingResult>;
+    embedBatch(texts: string[]): Promise<BatchEmbeddingResult>;
+}
+export declare class MockEmbeddingService extends BaseEmbeddingService {
+    readonly provider: EmbeddingProvider;
+    private readonly dimensions;
+    private readonly simulatedLatency;
+    constructor(config: MockEmbeddingConfig);
+    embed(text: string): Promise<EmbeddingResult>;
+    embedBatch(texts: string[]): Promise<BatchEmbeddingResult>;
+    /**
+     * Generate deterministic hash-based embedding
+     */
+    private hashEmbedding;
+}
+/**
+ * Create embedding service based on configuration
+ */
+export declare function createEmbeddingService(config: EmbeddingConfig): IEmbeddingService;
+/**
+ * Convenience function for quick embeddings
+ */
+export declare function getEmbedding(text: string, config?: Partial<EmbeddingConfig>): Promise<Float32Array | number[]>;
+/**
+ * Compute cosine similarity between two embeddings
+ */
+export declare function cosineSimilarity(a: Float32Array | number[], b: Float32Array | number[]): number;
+/**
+ * Compute Euclidean distance between two embeddings
+ */
+export declare function euclideanDistance(a: Float32Array | number[], b: Float32Array | number[]): number;
+/**
+ * Compute dot product between two embeddings
+ */
+export declare function dotProduct(a: Float32Array | number[], b: Float32Array | number[]): number;
+/**
+ * Compute similarity using specified metric
+ */
+export declare function computeSimilarity(a: Float32Array | number[], b: Float32Array | number[], metric?: SimilarityMetric): SimilarityResult;
+export {};
+//# sourceMappingURL=embedding-service.d.ts.map

package/dist/embedding-service.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"embedding-service.d.ts","sourceRoot":"","sources":["../src/embedding-service.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;GAYG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,QAAQ,CAAC;AACtC,OAAO,KAAK,EACV,iBAAiB,EACjB,eAAe,EACf,qBAAqB,EACrB,2BAA2B,EAC3B,mBAAmB,EACnB,eAAe,EACf,oBAAoB,EACpB,iBAAiB,EACjB,cAAc,EACd,sBAAsB,EACtB,gBAAgB,EAChB,gBAAgB,EACjB,MAAM,YAAY,CAAC;AAMpB,cAAM,QAAQ,CAAC,CAAC,EAAE,CAAC;IAKL,OAAO,CAAC,QAAQ,CAAC,OAAO;IAJpC,OAAO,CAAC,KAAK,CAAwB;IACrC,OAAO,CAAC,IAAI,CAAK;IACjB,OAAO,CAAC,MAAM,CAAK;gBAEU,OAAO,EAAE,MAAM;IAE5C,GAAG,CAAC,GAAG,EAAE,CAAC,GAAG,CAAC,GAAG,SAAS;IAa1B,GAAG,CAAC,GAAG,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,GAAG,IAAI;IAa3B,KAAK,IAAI,IAAI;IAMb,IAAI,IAAI,IAAI,MAAM,CAEjB;IAED,IAAI,OAAO,IAAI,MAAM,CAGpB;IAED,QAAQ;;;;;;;CAST;AAMD,uBAAe,oBAAqB,SAAQ,YAAa,YAAW,iBAAiB;IAKvE,SAAS,CAAC,QAAQ,CAAC,MAAM,EAAE,eAAe;IAJtD,QAAQ,CAAC,QAAQ,CAAC,QAAQ,EAAE,iBAAiB,CAAC;IAC9C,SAAS,CAAC,KAAK,EAAE,QAAQ,CAAC,MAAM,EAAE,YAAY,CAAC,CAAC;IAChD,SAAS,CAAC,kBAAkB,EAAE,GAAG,CAAC,sBAAsB,CAAC,CAAa;gBAEvC,MAAM,EAAE,eAAe;IAKtD,QAAQ,CAAC,KAAK,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAC,eAAe,CAAC;IACtD,QAAQ,CAAC,UAAU,CAAC,KAAK,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC,oBAAoB,CAAC;IAEnE,SAAS,CAAC,SAAS,CAAC,KAAK,EAAE,cAAc,GAAG,IAAI;IAWhD,gBAAgB,CAAC,QAAQ,EAAE,sBAAsB,GAAG,IAAI;IAIxD,mBAAmB,CAAC,QAAQ,EAAE,sBAAsB,GAAG,IAAI;IAI3D,UAAU,IAAI,IAAI;IAMlB,aAAa;;;;;IASP,QAAQ,IAAI,OAAO,CAAC,IAAI,CAAC;CAIhC;AAMD,qBAAa,sBAAuB,SAAQ,oBAAoB;IAC9D,QAAQ,CAAC,QAAQ,EAAE,iBAAiB,CAAY;IAChD,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAS;IAChC,OAAO,CAAC,QAAQ,CAAC,KAAK,CAAS;IAC/B,OAAO,CAAC,QAAQ,CAAC,OAAO,CAAS;IACjC,OAAO,CAAC,QAAQ,CAAC,OAAO,CAAS;IACjC,OAAO,CAAC,QAAQ,CAAC,UAAU,CAAS;gBAExB,MAAM,EAAE,qBAAqB;IASnC,KAAK,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAC,eAAe,CAAC;IAwC7C,UAAU,CAAC,KAAK,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC,oBAAoB,CAAC;YA6DlD,UAAU;CA+CzB;AAMD,qBAAa,4BAA6B,SAAQ,oBAAoB;IACpE,QAAQ,CAAC,QAAQ,EAAE,iBAAiB,CAAkB;IACtD,OAAO,CAAC,QAAQ,CAAa;IAC7B,OAAO,CAAC,QAAQ,CAAC,SAAS,CAAS;IACnC,OAAO,CAAC,WAAW,CAAS;gBAEhB,MAAM,EAAE,2BAA2B;YAKjC,UAAU;IAYlB,KAAK,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAC,eAAe,CAAC;IAsC7C,UAAU,CAAC,KAAK,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC,oBAAoB,CAAC;CAoCjE;AAMD,qBAAa,oBAAqB,SAAQ,oBAAoB;IAC5D,QAAQ,CAAC,QAAQ,EAAE,iBAAiB,CAAU;IAC9C,OAAO,CAAC,QAAQ,CAAC,UAAU,CAAS;IACpC,OAAO,CAAC,QAAQ,CAAC,gBAAgB,CAAS;gBAE9B,MAAM,EAAE,mBAAmB;IAMjC,KAAK,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAC,eAAe,CAAC;IAgC7C,UAAU,CAAC,KAAK,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC,oBAAoB,CAAC;IAiChE;;OAEG;IACH,OAAO,CAAC,aAAa;CAyBtB;AAMD;;GAEG;AACH,wBAAgB,sBAAsB,CAAC,MAAM,EAAE,eAAe,GAAG,iBAAiB,CAYjF;AAED;;GAEG;AACH,wBAAsB,YAAY,CAChC,IAAI,EAAE,MAAM,EACZ,MAAM,CAAC,EAAE,OAAO,CAAC,eAAe,CAAC,GAChC,OAAO,CAAC,YAAY,GAAG,MAAM,EAAE,CAAC,CAalC;AAMD;;GAEG;AACH,wBAAgB,gBAAgB,CAC9B,CAAC,EAAE,YAAY,GAAG,MAAM,EAAE,EAC1B,CAAC,EAAE,YAAY,GAAG,MAAM,EAAE,GACzB,MAAM,CAiBR;AAED;;GAEG;AACH,wBAAgB,iBAAiB,CAC/B,CAAC,EAAE,YAAY,GAAG,MAAM,EAAE,EAC1B,CAAC,EAAE,YAAY,GAAG,MAAM,EAAE,GACzB,MAAM,CAYR;AAED;;GAEG;AACH,wBAAgB,UAAU,CACxB,CAAC,EAAE,YAAY,GAAG,MAAM,EAAE,EAC1B,CAAC,EAAE,YAAY,GAAG,MAAM,EAAE,GACzB,MAAM,CAWR;AAED;;GAEG;AACH,wBAAgB,iBAAiB,CAC/B,CAAC,EAAE,YAAY,GAAG,MAAM,EAAE,EAC1B,CAAC,EAAE,YAAY,GAAG,MAAM,EAAE,EAC1B,MAAM,GAAE,gBAA2B,GAClC,gBAAgB,CAYlB"}