fix: use fp32 models consistently everywhere to ensure compatibility

Changed default dtype from q8 to fp32 across all embedding implementations:
- embedding.ts: Default dtype changed to fp32
- worker-embedding.ts: Use fp32 for consistency
- universal-memory-manager.ts: Use fp32 for consistency
- lightweight-embedder.ts: Use fp32 for consistency
- hybridModelManager.ts: Use fp32 for all configurations

This ensures we use the exact same model (model.onnx) everywhere,
maintaining data compatibility and avoiding 404 errors for quantized models.

models/.brainy-models-bundled

@@ -1,5 +0,0 @@
-{
-  "model": "Xenova/all-MiniLM-L6-v2",
-  "bundledAt": "2025-08-22T20:58:25.896Z",
-  "version": "1.0.0"
-}

models/Xenova/all-MiniLM-L6-v2/config.json

@@ -1,25 +0,0 @@
-{
-  "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
-  "architectures": [
-    "BertModel"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
-  "initializer_range": 0.02,
-  "intermediate_size": 1536,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "transformers_version": "4.29.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
-}

models/Xenova/all-MiniLM-L6-v2/tokenizer_config.json

@@ -1,15 +0,0 @@
-{
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
-}

src/embeddings/lightweight-embedder.ts

@@ -113,7 +113,7 @@ 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()

src/embeddings/universal-memory-manager.ts

@@ -139,7 +139,7 @@ export class UniversalMemoryManager {
       
       this.embeddingFunction = new TransformerEmbedding({
         verbose: false,
-        dtype: 'q8',
+        dtype: 'fp32',
         localFilesOnly: process.env.BRAINY_ALLOW_REMOTE_MODELS !== 'true'
       })
       

src/embeddings/worker-embedding.ts

@@ -16,7 +16,7 @@ async function initModel(): Promise<void> {
   if (!model) {
     model = new TransformerEmbedding({
       verbose: false,
-      dtype: 'q8',
+      dtype: 'fp32',
       localFilesOnly: process.env.BRAINY_ALLOW_REMOTE_MODELS !== 'true'
     })
     await model.init()

src/utils/embedding.ts

@@ -128,7 +128,7 @@ export class TransformerEmbedding implements EmbeddingModel {
       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'
     }
     
@@ -262,7 +262,7 @@ export class TransformerEmbedding implements EmbeddingModel {
       const pipelineOptions: any = {
         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

src/utils/hybridModelManager.ts

@@ -104,7 +104,7 @@ class HybridModelManager {
       // Smart configuration based on environment
       let options: TransformerEmbeddingOptions = {
         verbose: !isTest && !isServerless,
-        dtype: 'q8',
+        dtype: 'fp32',
         device: 'cpu'
       }
 
@@ -113,7 +113,7 @@ class HybridModelManager {
         options = {
           ...options,
           localFilesOnly: forceLocalOnly || false, // Respect environment variable
-          dtype: 'q8',
+          dtype: 'fp32',
           device: 'cpu',
           verbose: false
         }
@@ -121,7 +121,7 @@ class HybridModelManager {
         options = {
           ...options,
           localFilesOnly: forceLocalOnly || true, // Default true for serverless, but respect env
-          dtype: 'q8',
+          dtype: 'fp32',
           device: 'cpu',
           verbose: false
         }
@@ -138,7 +138,7 @@ class HybridModelManager {
         options = {
           ...options,
           localFilesOnly: forceLocalOnly || false, // Respect environment variable for tests
-          dtype: 'q8',
+          dtype: 'fp32',
           device: 'cpu',
           verbose: false
         }
@@ -146,7 +146,7 @@ class HybridModelManager {
         options = {
           ...options,
           localFilesOnly: forceLocalOnly || false, // Respect environment variable for default node
-          dtype: 'q8',
+          dtype: 'fp32',
           device: 'auto',
           verbose: true
         }
@@ -201,7 +201,7 @@ class HybridModelManager {
       { ...options, localFilesOnly: false, verbose: true, source: 'fallback-verbose' },
       
       // 3. Last resort: basic configuration
-      { verbose: false, dtype: 'q8' as const, device: 'cpu' as const, localFilesOnly: false, source: 'last-resort' }
+      { verbose: false, dtype: 'fp32' as const, device: 'cpu' as const, localFilesOnly: false, source: 'last-resort' }
     ]
 
     let lastError: Error | null = null