Hybrid retrieval

Hybrid retrieval combines semantic dense similarity with lexical sparse matching. QQL exposes a shorthand and an explicit multi-stage form.

Shorthand

QQLSchema-resolved hybrid searchTry in playground↗

QUERY TEXT 'zero downtime deployment' FROM runbooks
USING HYBRID DENSE dense SPARSE sparse FUSION RRF
WHERE service = 'gateway'
LIMIT 10;

If the collection has exactly one dense and one sparse vector, omit the names:

QQLHybrid defaultsTry in playground↗

QUERY 'zero downtime deployment' FROM runbooks
USING HYBRID
LIMIT 10;

Explicit candidate stages

QQLWeighted RRF pipelineTry in playground↗

WITH
  semantic AS (
    QUERY TEXT 'zero downtime deployment'
    USING dense
    WHERE service = 'gateway'
    LIMIT 120
  ),
  lexical AS (
    QUERY TEXT 'zero downtime deployment'
    USING sparse
    WHERE service = 'gateway'
    LIMIT 180
  )
QUERY FUSION RRF
FROM runbooks
PREFETCH (semantic, lexical)
PARAMS (rrf_k = 40, rrf_weights = [0.7, 0.3])
LIMIT 10;

Use the explicit form when candidate limits, filters, or weights differ by stage. rrf_weights length must equal the prefetch count.

RRF or DBSF?

Fusion	Prefer when
RRF	Ranking positions are reliable but score scales differ
DBSF	Normalized score magnitude carries useful information