ruvector 0.1.59 → 0.1.60

package/dist/core/onnx-embedder.d.ts

@@ -11,12 +11,19 @@
  * - Real semantic understanding (not hash-based)
  * - Cached model loading (downloads from HuggingFace on first use)
  * - Batch embedding support
+ * - Optional parallel workers for 3.8x batch speedup
  */
 export interface OnnxEmbedderConfig {
     modelId?: string;
     maxLength?: number;
     normalize?: boolean;
     cacheDir?: string;
+    /** Enable parallel workers for batch operations (default: auto-detect) */
+    enableParallel?: boolean | 'auto';
+    /** Number of worker threads (default: CPU cores - 1) */
+    numWorkers?: number;
+    /** Minimum batch size to use parallel processing (default: 4) */
+    parallelThreshold?: number;
 }
 export interface EmbeddingResult {
     embedding: number[];
@@ -41,6 +48,7 @@ export declare function initOnnxEmbedder(config?: OnnxEmbedderConfig): Promise<b
 export declare function embed(text: string): Promise<EmbeddingResult>;
 /**
  * Generate embeddings for multiple texts
+ * Uses parallel workers automatically for batches >= parallelThreshold
  */
 export declare function embedBatch(texts: string[]): Promise<EmbeddingResult[]>;
 /**
@@ -60,13 +68,21 @@ export declare function getDimension(): number;
  */
 export declare function isReady(): boolean;
 /**
- * Get embedder stats
+ * Get embedder stats including SIMD and parallel capabilities
  */
 export declare function getStats(): {
     ready: boolean;
     dimension: number;
     model: string;
+    simd: boolean;
+    parallel: boolean;
+    parallelWorkers: number;
+    parallelThreshold: number;
 };
+/**
+ * Shutdown parallel workers (call on exit)
+ */
+export declare function shutdown(): Promise<void>;
 export declare class OnnxEmbedder {
     private config;
     constructor(config?: OnnxEmbedderConfig);

package/dist/core/onnx-embedder.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"onnx-embedder.d.ts","sourceRoot":"","sources":["../../src/core/onnx-embedder.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;GAaG;AAWH,MAAM,WAAW,kBAAkB;IACjC,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,QAAQ,CAAC,EAAE,MAAM,CAAC;CACnB;AAED,MAAM,WAAW,eAAe;IAC9B,SAAS,EAAE,MAAM,EAAE,CAAC;IACpB,SAAS,EAAE,MAAM,CAAC;IAClB,MAAM,EAAE,MAAM,CAAC;CAChB;AAED,MAAM,WAAW,gBAAgB;IAC/B,UAAU,EAAE,MAAM,CAAC;IACnB,MAAM,EAAE,MAAM,CAAC;CAChB;AAYD;;GAEG;AACH,wBAAgB,eAAe,IAAI,OAAO,CAOzC;AAED;;GAEG;AACH,wBAAsB,gBAAgB,CAAC,MAAM,GAAE,kBAAuB,GAAG,OAAO,CAAC,OAAO,CAAC,CAkExF;AAED;;GAEG;AACH,wBAAsB,KAAK,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAC,eAAe,CAAC,CAiBlE;AAED;;GAEG;AACH,wBAAsB,UAAU,CAAC,KAAK,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC,eAAe,EAAE,CAAC,CAyB5E;AAED;;GAEG;AACH,wBAAsB,UAAU,CAAC,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAAG,OAAO,CAAC,gBAAgB,CAAC,CAaxF;AAED;;GAEG;AACH,wBAAgB,gBAAgB,CAAC,CAAC,EAAE,MAAM,EAAE,EAAE,CAAC,EAAE,MAAM,EAAE,GAAG,MAAM,CAiBjE;AAED;;GAEG;AACH,wBAAgB,YAAY,IAAI,MAAM,CAErC;AAED;;GAEG;AACH,wBAAgB,OAAO,IAAI,OAAO,CAEjC;AAED;;GAEG;AACH,wBAAgB,QAAQ,IAAI;IAAE,KAAK,EAAE,OAAO,CAAC;IAAC,SAAS,EAAE,MAAM,CAAC;IAAC,KAAK,EAAE,MAAM,CAAA;CAAE,CAM/E;AAGD,qBAAa,YAAY;IACvB,OAAO,CAAC,MAAM,CAAqB;gBAEvB,MAAM,GAAE,kBAAuB;IAIrC,IAAI,IAAI,OAAO,CAAC,OAAO,CAAC;IAIxB,KAAK,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,EAAE,CAAC;IAKtC,UAAU,CAAC,KAAK,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC,MAAM,EAAE,EAAE,CAAC;IAKhD,UAAU,CAAC,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC;IAK/D,IAAI,SAAS,IAAI,MAAM,CAEtB;IAED,IAAI,KAAK,IAAI,OAAO,CAEnB;CACF;AAED,eAAe,YAAY,CAAC"}
+{"version":3,"file":"onnx-embedder.d.ts","sourceRoot":"","sources":["../../src/core/onnx-embedder.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;GAcG;AAWH,MAAM,WAAW,kBAAkB;IACjC,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,0EAA0E;IAC1E,cAAc,CAAC,EAAE,OAAO,GAAG,MAAM,CAAC;IAClC,wDAAwD;IACxD,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,iEAAiE;IACjE,iBAAiB,CAAC,EAAE,MAAM,CAAC;CAC5B;AAMD,MAAM,WAAW,eAAe;IAC9B,SAAS,EAAE,MAAM,EAAE,CAAC;IACpB,SAAS,EAAE,MAAM,CAAC;IAClB,MAAM,EAAE,MAAM,CAAC;CAChB;AAED,MAAM,WAAW,gBAAgB;IAC/B,UAAU,EAAE,MAAM,CAAC;IACnB,MAAM,EAAE,MAAM,CAAC;CAChB;AAeD;;GAEG;AACH,wBAAgB,eAAe,IAAI,OAAO,CAOzC;AA6DD;;GAEG;AACH,wBAAsB,gBAAgB,CAAC,MAAM,GAAE,kBAAuB,GAAG,OAAO,CAAC,OAAO,CAAC,CA2ExF;AAED;;GAEG;AACH,wBAAsB,KAAK,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAC,eAAe,CAAC,CAiBlE;AAED;;;GAGG;AACH,wBAAsB,UAAU,CAAC,KAAK,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC,eAAe,EAAE,CAAC,CAwC5E;AAED;;GAEG;AACH,wBAAsB,UAAU,CAAC,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAAG,OAAO,CAAC,gBAAgB,CAAC,CAaxF;AAED;;GAEG;AACH,wBAAgB,gBAAgB,CAAC,CAAC,EAAE,MAAM,EAAE,EAAE,CAAC,EAAE,MAAM,EAAE,GAAG,MAAM,CAiBjE;AAED;;GAEG;AACH,wBAAgB,YAAY,IAAI,MAAM,CAErC;AAED;;GAEG;AACH,wBAAgB,OAAO,IAAI,OAAO,CAEjC;AAED;;GAEG;AACH,wBAAgB,QAAQ,IAAI;IAC1B,KAAK,EAAE,OAAO,CAAC;IACf,SAAS,EAAE,MAAM,CAAC;IAClB,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,EAAE,OAAO,CAAC;IACd,QAAQ,EAAE,OAAO,CAAC;IAClB,eAAe,EAAE,MAAM,CAAC;IACxB,iBAAiB,EAAE,MAAM,CAAC;CAC3B,CAUA;AAED;;GAEG;AACH,wBAAsB,QAAQ,IAAI,OAAO,CAAC,IAAI,CAAC,CAM9C;AAGD,qBAAa,YAAY;IACvB,OAAO,CAAC,MAAM,CAAqB;gBAEvB,MAAM,GAAE,kBAAuB;IAIrC,IAAI,IAAI,OAAO,CAAC,OAAO,CAAC;IAIxB,KAAK,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,EAAE,CAAC;IAKtC,UAAU,CAAC,KAAK,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC,MAAM,EAAE,EAAE,CAAC;IAKhD,UAAU,CAAC,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC;IAK/D,IAAI,SAAS,IAAI,MAAM,CAEtB;IAED,IAAI,KAAK,IAAI,OAAO,CAEnB;CACF;AAED,eAAe,YAAY,CAAC"}

package/dist/core/onnx-embedder.js

@@ -12,6 +12,7 @@
  * - Real semantic understanding (not hash-based)
  * - Cached model loading (downloads from HuggingFace on first use)
  * - Batch embedding support
+ * - Optional parallel workers for 3.8x batch speedup
  */
 var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
     if (k2 === undefined) k2 = k;
@@ -57,18 +58,25 @@ exports.cosineSimilarity = cosineSimilarity;
 exports.getDimension = getDimension;
 exports.isReady = isReady;
 exports.getStats = getStats;
+exports.shutdown = shutdown;
 const path = __importStar(require("path"));
 const fs = __importStar(require("fs"));
 const url_1 = require("url");
 // Force native dynamic import (avoids TypeScript transpiling to require)
 // eslint-disable-next-line @typescript-eslint/no-implied-eval
 const dynamicImport = new Function('specifier', 'return import(specifier)');
+// Capability detection
+let simdAvailable = false;
+let parallelAvailable = false;
 // Lazy-loaded module state
 let wasmModule = null;
 let embedder = null;
+let parallelEmbedder = null;
 let loadError = null;
 let loadPromise = null;
 let isInitialized = false;
+let parallelEnabled = false;
+let parallelThreshold = 4;
 // Default model
 const DEFAULT_MODEL = 'all-MiniLM-L6-v2';
 /**
@@ -83,6 +91,63 @@ function isOnnxAvailable() {
         return false;
     }
 }
+/**
+ * Check if parallel workers are available (npm package installed)
+ */
+async function detectParallelAvailable() {
+    try {
+        await dynamicImport('ruvector-onnx-embeddings-wasm/parallel');
+        parallelAvailable = true;
+        return true;
+    }
+    catch {
+        parallelAvailable = false;
+        return false;
+    }
+}
+/**
+ * Check if SIMD is available (from WASM module)
+ */
+function detectSimd() {
+    try {
+        if (wasmModule && typeof wasmModule.simd_available === 'function') {
+            simdAvailable = wasmModule.simd_available();
+            return simdAvailable;
+        }
+    }
+    catch { }
+    return false;
+}
+/**
+ * Try to load ParallelEmbedder from npm package (optional)
+ */
+async function tryInitParallel(config) {
+    // Skip if explicitly disabled
+    if (config.enableParallel === false)
+        return false;
+    // For 'auto' or true, try to initialize
+    try {
+        const parallelModule = await dynamicImport('ruvector-onnx-embeddings-wasm/parallel');
+        const { ParallelEmbedder } = parallelModule;
+        parallelEmbedder = new ParallelEmbedder({
+            numWorkers: config.numWorkers,
+        });
+        await parallelEmbedder.init(config.modelId || DEFAULT_MODEL);
+        parallelThreshold = config.parallelThreshold || 4;
+        parallelEnabled = true;
+        parallelAvailable = true;
+        console.error(`Parallel embedder ready: ${parallelEmbedder.numWorkers} workers, SIMD: ${simdAvailable}`);
+        return true;
+    }
+    catch (e) {
+        parallelAvailable = false;
+        if (config.enableParallel === true) {
+            // Only warn if explicitly requested
+            console.error(`Parallel embedder not available: ${e.message}`);
+        }
+        return false;
+    }
+}
 /**
  * Initialize the ONNX embedder (downloads model if needed)
  */
@@ -132,8 +197,15 @@ async function initOnnxEmbedder(config = {}) {
                 .setNormalize(config.normalize !== false)
                 .setPooling(0); // Mean pooling
             embedder = wasmModule.WasmEmbedder.withConfig(modelBytes, tokenizerJson, embedderConfig);
-            console.error(`ONNX embedder ready: ${embedder.dimension()}d`);
+            // Detect SIMD capability
+            detectSimd();
+            console.error(`ONNX embedder ready: ${embedder.dimension()}d, SIMD: ${simdAvailable}`);
             isInitialized = true;
+            // Try parallel by default ('auto') or if explicitly enabled
+            const shouldTryParallel = config.enableParallel !== false;
+            if (shouldTryParallel) {
+                await tryInitParallel(config);
+            }
         }
         catch (e) {
             loadError = new Error(`Failed to initialize ONNX embedder: ${e.message}`);
@@ -164,6 +236,7 @@ async function embed(text) {
 }
 /**
  * Generate embeddings for multiple texts
+ * Uses parallel workers automatically for batches >= parallelThreshold
  */
 async function embedBatch(texts) {
     if (!isInitialized) {
@@ -173,6 +246,18 @@ async function embedBatch(texts) {
         throw new Error('ONNX embedder not initialized');
     }
     const start = performance.now();
+    // Use parallel workers for large batches
+    if (parallelEnabled && parallelEmbedder && texts.length >= parallelThreshold) {
+        const batchResults = await parallelEmbedder.embedBatch(texts);
+        const totalTime = performance.now() - start;
+        const dimension = parallelEmbedder.dimension || 384;
+        return batchResults.map((emb) => ({
+            embedding: Array.from(emb),
+            dimension,
+            timeMs: totalTime / texts.length,
+        }));
+    }
+    // Sequential fallback
     const batchEmbeddings = embedder.embedBatch(texts);
     const totalTime = performance.now() - start;
     const dimension = embedder.dimension();
@@ -233,15 +318,29 @@ function isReady() {
     return isInitialized;
 }
 /**
- * Get embedder stats
+ * Get embedder stats including SIMD and parallel capabilities
  */
 function getStats() {
     return {
         ready: isInitialized,
         dimension: embedder ? embedder.dimension() : 384,
         model: DEFAULT_MODEL,
+        simd: simdAvailable,
+        parallel: parallelEnabled,
+        parallelWorkers: parallelEmbedder?.numWorkers || 0,
+        parallelThreshold,
     };
 }
+/**
+ * Shutdown parallel workers (call on exit)
+ */
+async function shutdown() {
+    if (parallelEmbedder) {
+        await parallelEmbedder.shutdown();
+        parallelEmbedder = null;
+        parallelEnabled = false;
+    }
+}
 // Export class wrapper for compatibility
 class OnnxEmbedder {
     constructor(config = {}) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ruvector",
-  "version": "0.1.59",
+  "version": "0.1.60",
   "description": "High-performance vector database for Node.js with automatic native/WASM fallback",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",