@soulcraft/brainy 2.7.3 → 2.7.4

package/CHANGELOG.md

@@ -5,6 +5,15 @@ All notable changes to Brainy will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [2.7.4] - 2025-08-29
+
+### Fixed
+- Use fp32 models consistently everywhere to ensure compatibility
+- Changed default dtype from q8 to fp32 across all embedding implementations
+- Ensures the exact same model (model.onnx) is used everywhere
+- Prevents 404 errors when looking for quantized models that don't exist on CDN
+- Maintains data compatibility across all Brainy instances
+
 ## [2.7.3] - 2025-08-29
 
 ### Fixed

package/dist/embeddings/lightweight-embedder.js

@@ -97,7 +97,7 @@ export class LightweightEmbedder {
             console.log('⚠️ Loading ONNX model for complex text...');
             const { TransformerEmbedding } = await import('../utils/embedding.js');
             this.onnxEmbedder = new TransformerEmbedding({
-                dtype: 'q8',
+                dtype: 'fp32',
                 verbose: false
             });
             await this.onnxEmbedder.init();

package/dist/embeddings/universal-memory-manager.js

@@ -107,7 +107,7 @@ export class UniversalMemoryManager {
             const { TransformerEmbedding } = await import('../utils/embedding.js');
             this.embeddingFunction = new TransformerEmbedding({
                 verbose: false,
-                dtype: 'q8',
+                dtype: 'fp32',
                 localFilesOnly: process.env.BRAINY_ALLOW_REMOTE_MODELS !== 'true'
             });
             await this.embeddingFunction.init();

package/dist/embeddings/worker-embedding.js

@@ -13,7 +13,7 @@ async function initModel() {
     if (!model) {
         model = new TransformerEmbedding({
             verbose: false,
-            dtype: 'q8',
+            dtype: 'fp32',
             localFilesOnly: process.env.BRAINY_ALLOW_REMOTE_MODELS !== 'true'
         });
         await model.init();

package/dist/utils/embedding.js

@@ -98,7 +98,7 @@ export class TransformerEmbedding {
             verbose: this.verbose,
             cacheDir: options.cacheDir || './models',
             localFilesOnly: localFilesOnly,
-            dtype: options.dtype || 'q8', // Changed from fp32 to q8 for 75% memory reduction
+            dtype: options.dtype || 'fp32', // Use fp32 by default as quantized models aren't available on CDN
             device: options.device || 'auto'
         };
         if (this.verbose) {
@@ -216,7 +216,7 @@ export class TransformerEmbedding {
             const pipelineOptions = {
                 cache_dir: cacheDir,
                 local_files_only: isBrowser() ? false : this.options.localFilesOnly,
-                dtype: this.options.dtype || 'q8', // Use quantized model for lower memory
+                dtype: this.options.dtype || 'fp32', // Use fp32 model as quantized models aren't available on CDN
                 // CRITICAL: ONNX memory optimizations
                 session_options: {
                     enableCpuMemArena: false, // Disable pre-allocated memory arena

package/dist/utils/hybridModelManager.js

@@ -83,7 +83,7 @@ class HybridModelManager {
             // Smart configuration based on environment
             let options = {
                 verbose: !isTest && !isServerless,
-                dtype: 'q8',
+                dtype: 'fp32',
                 device: 'cpu'
             };
             // Environment-specific optimizations
@@ -91,7 +91,7 @@ class HybridModelManager {
                 options = {
                     ...options,
                     localFilesOnly: forceLocalOnly || false, // Respect environment variable
-                    dtype: 'q8',
+                    dtype: 'fp32',
                     device: 'cpu',
                     verbose: false
                 };
@@ -100,7 +100,7 @@ class HybridModelManager {
                 options = {
                     ...options,
                     localFilesOnly: forceLocalOnly || true, // Default true for serverless, but respect env
-                    dtype: 'q8',
+                    dtype: 'fp32',
                     device: 'cpu',
                     verbose: false
                 };
@@ -119,7 +119,7 @@ class HybridModelManager {
                 options = {
                     ...options,
                     localFilesOnly: forceLocalOnly || false, // Respect environment variable for tests
-                    dtype: 'q8',
+                    dtype: 'fp32',
                     device: 'cpu',
                     verbose: false
                 };
@@ -128,7 +128,7 @@ class HybridModelManager {
                 options = {
                     ...options,
                     localFilesOnly: forceLocalOnly || false, // Respect environment variable for default node
-                    dtype: 'q8',
+                    dtype: 'fp32',
                     device: 'auto',
                     verbose: true
                 };
@@ -168,7 +168,7 @@ class HybridModelManager {
             // 2. If that fails, explicitly allow remote with verbose logging
             { ...options, localFilesOnly: false, verbose: true, source: 'fallback-verbose' },
             // 3. Last resort: basic configuration
-            { verbose: false, dtype: 'q8', device: 'cpu', localFilesOnly: false, source: 'last-resort' }
+            { verbose: false, dtype: 'fp32', device: 'cpu', localFilesOnly: false, source: 'last-resort' }
         ];
         let lastError = null;
         for (const attemptOptions of attempts) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@soulcraft/brainy",
-  "version": "2.7.3",
+  "version": "2.7.4",
   "description": "Universal Knowledge Protocol™ - World's first Triple Intelligence database unifying vector, graph, and document search in one API. 31 nouns × 40 verbs for infinite expressiveness.",
   "main": "dist/index.js",
   "module": "dist/index.js",