This repository has been archived on 2026-09-03. You can view files and clone it, but you cannot make any changes to it's state, such as pushing and creating new issues, pull requests or comments.

David Snelling 10b772423b 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.		2025-08-29 10:23:23 -07:00
..
lightweight-embedder.ts	fix: use fp32 models consistently everywhere to ensure compatibility	2025-08-29 10:23:23 -07:00
model-manager.ts	feat: reliable multi-source model delivery system	2025-08-28 08:45:35 -07:00
universal-memory-manager.ts	fix: use fp32 models consistently everywhere to ensure compatibility	2025-08-29 10:23:23 -07:00
worker-embedding.ts	fix: use fp32 models consistently everywhere to ensure compatibility	2025-08-29 10:23:23 -07:00
worker-manager.ts	🧠 Brainy 2.0.0 - Zero-Configuration AI Database with Triple Intelligence™	2025-08-26 12:32:21 -07:00