tidaldb/ai-lookup/features/query-language.md
jx12n 4051077cff docs(m12): refresh API, specs, ops, and roadmap to the shipped M12 reality
- API.md: document `similar_to`/`region`/`unavailable_shards` on /feed and
  /search, the new POST /vector_search k-NN probe, and the cluster-node-only
  routes (/cluster/*, /sharded/*, /hardnegs)
- CHANGELOG.md: M12 entries — multi-vector preference + ANN candidate-gen,
  idle-readiness + TLS scale-up (m12p5/p6), sharded ingestion (m12p4)
- ROADMAP.md: mark M11 + M12 COMPLETE; restate the v1.0 bar (30-day-green
  nightly calendar + Ref-A/k3s throughput re-runs)
- prometheus-alerts.yaml: add ship-stall, quorum-lag, divergence-quarantine,
  reseed-pending, and snapshot-pin-force-drop cluster alerts
- check-docs.sh: self-updating milestone-status freshness guard derived from
  ROADMAP's latest COMPLETE milestone
- refresh specs (00-14), ai-lookup, guides, and runbooks to M0-M12
2026-06-23 21:39:55 -06:00

1.6 KiB

Query Language

Last Updated: 2026-02-19 Confidence: High

Summary

The query interface is a single operation that encapsulates candidate retrieval, filtering, ranking, and diversity enforcement. Three primary operations: RETRIEVE (feed/browse), SEARCH (text+semantic), and SIGNAL (engagement write-back).

Key Facts:

  • One query replaces what currently requires 6 systems
  • RETRIEVE: feed generation, browse, related content
  • SEARCH: keyword + semantic + hybrid retrieval
  • SIGNAL: engagement event write-back (closes the feedback loop in the same transaction)
  • All queries accept: FOR USER, USING PROFILE, FILTER, DIVERSITY, LIMIT
  • RETRIEVE also accepts SIMILAR TO (similar_to — a seed item for "more like this") and an optional ef_search ANN-recall/latency override
  • Filters are composable — any combination is valid

File Pointer: VISION.md:47-57

Query Shapes

Feed retrieval:

RETRIEVE items
FOR USER @user_id
CONTEXT feed
USING PROFILE for_you
FILTER unseen, unblocked, format:video
DIVERSITY max_per_creator:2, format_mix:true
LIMIT 50

Search:

SEARCH items
QUERY "rust tutorial beginner"
VECTOR query_vector
FOR USER @user_id
USING PROFILE search
DIVERSITY max_per_creator:2
LIMIT 20

Signal write:

SIGNAL like
item: @item_id
user: @user_id
timestamp: now()

Related content:

RETRIEVE items
SIMILAR TO @item_id
FOR USER @user_id
USING PROFILE related
FILTER unseen
EF_SEARCH 128        # optional: tune ANN recall vs. latency per query
LIMIT 10