mirror of
https://github.com/ruvnet/RuVector.git
synced 2026-05-25 15:03:46 +00:00
ff70a98ec6
Search-path optimization: - normalize_embedding() L2-normalizes on write and on Firestore ingest - cosine_similarity_normalized() is pure dot product (no norm computation) - search_memories() normalizes query once, uses fast dot for all comparisons - Stored memories migrated in-place during hydration Network optimization: - tower-http compression-gzip feature enabled - CompressionLayer applied to all responses - JSON compresses 5-10x, saves ~100-200ms on return path Expected: search 771ms → ~475ms (38% improvement) Server compute: ~67ms → ~25ms (3x via pre-normalization) Network: ~600ms → ~450ms (25% via gzip) Co-Authored-By: claude-flow <ruv@ruv.net> |
||
|---|---|---|
| .. | ||
| agents | ||
| commands | ||
| helpers | ||
| hooks | ||
| intelligence | ||
| skills | ||
| agentic-flow-fast.sh | ||
| ruvector-fast.sh | ||
| scheduled_tasks.lock | ||
| settings.json | ||
| statusline-command.sh | ||
| statusline.mjs | ||