Skip to content

v0.35.0.0.md

Latest commit

 

History

History
84 lines (65 loc) · 2.77 KB

v0.35.0.0.md

File metadata and controls

84 lines (65 loc) · 2.77 KB
Raw
feature_pitch ZeroEntropy zembed-1 embeddings + zerank-2 cross-encoder reranking
required_action false

v0.35.0.0 migration notes

ZeroEntropy support landed. No required user action. Reranker is on by default for tokenmax mode only; embedding model is unchanged for everyone unless the user explicitly opts in via config file or env var.

What changed automatically

  • KNOBS_HASH_VERSION bumped 1 → 2 to fold reranker config into the query_cache.knobs_hash column. Expect a temporary cache hit-rate dip for ~1 hour (the default cache.ttl_seconds) as v=1 rows TTL out and v=2 rows backfill. Search still works during the dip; only cache hits are affected.
  • tokenmax mode now defaults search.reranker.enabled = true. If the user has ZEROENTROPY_API_KEY set AND uses tokenmax, reranker fires. Without the API key, the rerank attempt fails-open (audit-logged) and search returns the RRF order — same UX as before, just with an observable failure in gbrain doctor.
  • conservative and balanced modes default reranker = false. Nothing changes for those users without an explicit opt-in.

What the user can do (optional)

Try zembed-1 embeddings

Switching embedding models invalidates the vector index — you'll need to re-embed. Edit ~/.gbrain/config.json:

{
  "embedding_model": "zeroentropyai:zembed-1",
  "embedding_dimensions": 2560
}

Valid dims: 2560, 1280, 640, 320, 160, 80, 40 (Matryoshka-style; smaller trades quality for storage). Then:

export ZEROENTROPY_API_KEY=...
gbrain models doctor                  # verify config
gbrain embed --stale --limit 50       # smoke a small re-embed
gbrain embed --stale                  # full re-embed

Try zerank-2 on conservative/balanced

export ZEROENTROPY_API_KEY=...
gbrain config set search.reranker.enabled true
gbrain models doctor                  # verify reranker_config + reachability
gbrain query "some query that previously misranked"

To opt out:

gbrain config set search.reranker.enabled false

Opt out of reranker on tokenmax

If you're on tokenmax mode and don't want reranker spend:

gbrain config set search.reranker.enabled false

The override sticks above the mode bundle default.

Diagnostics

  • gbrain models doctor --json — probes embedding_config, reranker_config, and reranker reachability. Surfaces config issues with paste-ready fix hints.
  • gbrain doctor — runs reranker_health against the JSONL audit at ~/.gbrain/audit/rerank-failures-YYYY-Www.jsonl. Auth failures warn immediately; transient failures warn at >=5 in 7 days.
  • tail -100 ~/.gbrain/audit/rerank-failures-*.jsonl — raw failure log for direct inspection (privacy: query text is SHA-256 hashed; never raw).