Precomputed top-K similarity cache replacing the naive Python-scan search_similar(). Also covers fixes for: embeddings table missing from _init_database, fusion N+1 query, and ai_provider 429 retry.
Precomputed top-K similarity cache replacing the naive Python-scan search_similar(). Also covers fixes for: embeddings table missing from _init_database, fusion N+1 query, and ai_provider 429 retry.