krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-10-10 21:38:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

Switch hybrid-rrf snippets to RrfQuery API

Browse Source 
Replaces the older `FusionQuery(fusion=Fusion.RRF)` enum form with
`RrfQuery(rrf=Rrf())` across all language tabs (Python, TypeScript,
Rust, Go, Java, C#) plus the REST body in `http.md`, for both the
`hybrid-rrf/` snippet and the inner RRF prefetch inside
`hybrid-formula-decay/`. The newer dedicated `Rrf` message is the
recommended path going forward; the old enum stays supported for
backward compatibility. Server-side both forms converge to the same
`FusionInternal::Rrf { k: 2, weights: None }`, verified against the
qdrant/qdrant source.

`generated/*.md` files in both directories regenerated via
`./docker.sh ./generate-md.py`. `./docker.sh ./check.py build` passes
across all six SDKs.

Also softens the DBSF prose in hybrid-queries.md to drop the
"weighted RRF tends to win" framing. Neither method dominates the
other in general.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Dylan Couzon
2026-05-15 21:04:09 -04:00
co-authored by Claude Opus 4.7
parent 06fbbf7fc3
commit fc299a0e9c
27 changed files with 41 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/documentation/search/hybrid-queries.md
+1 -1
View File
@@ -98,7 +98,7 @@ Normalized scores are summed across retrievers. Different score magnitudes no lo
<aside role="status"><code>dbsf</code> is stateless and computes its normalization limits from each query's returned points, not from all the scores it has seen. Scores are <strong>not</strong> clipped to [0, 1]; values outside the 3-sigma range remain outside it after the remap. If all returned scores are identical (or only one point is returned), DBSF emits <code>0.5</code> rather than dividing by zero.</aside>
DBSF is a reasonable choice when you trust your retrievers' raw scores to carry magnitude information. Weighted RRF tends to win when you have an eval set and can grid-search, but DBSF remains competitive on retrievers with well-calibrated score distributions. Two caveats apply: the statistics come from the prefetch top-k (a small sample), and a single dominant outlier in that top-k can skew normalization for that query. Increase the prefetch `limit` if you see unstable rankings.
DBSF is a reasonable choice when you trust your retrievers' raw scores to carry magnitude information. On well-calibrated retrievers DBSF can outperform tuned weighted RRF; on others weighted RRF wins. Neither dominates the other in general, so use your eval set to choose between them. Two caveats apply: the statistics come from the prefetch top-k (a small sample), and a single dominant outlier in that top-k can skew normalization for that query. Increase the prefetch `limit` if you see unstable rankings.
{{< code-snippet path="/documentation/headless/snippets/query-points/hybrid-dbsf/" >}}