Every classification request lands here. The numbers update once a
second from /api/stats. The cache is a real
mneme.SemanticCache backed by SQLite, embedding with
sentence-transformers locally, classifying with
nemotron-3-nano on {{ config.SPARK_URL }}.
get; entries already cached are not re-evaluated.
compact() would reclaim.
| Exact-match (Layer 1) | 0 |
|---|---|
| Semantic-match (Layer 2) | 0 |
| Misses (LLM call) | 0 |
| Namespace | Queries | L1 | L2 | Miss |
|---|
| Time | Namespace | Layer | Latency | Query | → Intent |
|---|
Reclaims memory from tombstoned (deleted) rows in the in-memory index. Cheap when there are no tombstones; rebuilds the matrix when there are.
Backed by the library: cache.clear() for all namespaces, cache.clear_namespace(ns) for a single tenant.