Andy Lee 9a5c197acd fix: auto-detect normalized embeddings and use cosine distance ...

- Add automatic detection for normalized embedding models (OpenAI, Voyage AI, Cohere)
- Automatically set distance_metric='cosine' for normalized embeddings
- Add warnings when using non-optimal distance metrics
- Implement manual L2 normalization in HNSW backend (custom Faiss build lacks normalize_L2)
- Fix DiskANN zmq_port compatibility with lazy loading strategy
- Add documentation for normalized embeddings feature

This fixes the low accuracy issue when using OpenAI text-embedding-3-small model with default MIPS metric.

2025-07-27 20:21:05 -07:00

..

leann

fix ruff errors and formatting

2025-07-27 02:22:54 -07:00

leann-backend-diskann

fix: auto-detect normalized embeddings and use cosine distance

2025-07-27 20:21:05 -07:00

leann-backend-hnsw

fix: auto-detect normalized embeddings and use cosine distance

2025-07-27 20:21:05 -07:00

leann-core

fix: auto-detect normalized embeddings and use cosine distance

2025-07-27 20:21:05 -07:00

wechat-exporter

fix ruff errors and formatting

2025-07-27 02:22:54 -07:00

__init__.py

fix ruff errors and formatting

2025-07-27 02:22:54 -07:00