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.

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