Improve memory search: normalize query, AND-first, relevance scoring

Fork: 0

root / navi-1

Browse code Improve memory search: normalize query, AND-first, relevance scoring - _normalize_query(): hyphens/underscores/slashes/dots → word boundaries, strip all other punctuation, lowercase — fixes comma-separated keyword bug - Auto-dump: if ≤ 60 facts in DB, skip search and return all (no false negatives in a small personal memory store) - AND-first: try matching all terms; fall back to OR only when AND returns nothing - OR-fallback with scoring: facts matching more terms rank higher (score DESC), ties broken by recency Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> feature/navi-code master vmkdemo
1 parent 4250b26 commit 4050c2429c6e6cb17baadb87b4ba4b004c86841b Eugene Sukhodolskiy authored on 21 Apr

Browse code

- _normalize_query(): hyphens/underscores/slashes/dots → word boundaries,
  strip all other punctuation, lowercase — fixes comma-separated keyword bug
- Auto-dump: if ≤ 60 facts in DB, skip search and return all (no false negatives
  in a small personal memory store)
- AND-first: try matching all terms; fall back to OR only when AND returns nothing
- OR-fallback with scoring: facts matching more terms rank higher (score DESC),
  ties broken by recency

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

feature/navi-code master vmkdemo

1 parent 4250b26 commit 4050c2429c6e6cb17baadb87b4ba4b004c86841b

Eugene Sukhodolskiy authored on 21 Apr

Patch

Unified Split

Showing 1 changed file

Ignore Space Show notes View navi/memory/store.py

Show line notes below