* Add 'Stable Ordering' section to 'Pagination' section
* Add FAQ entry
* Small edits to the Pagination section
* Apply title case to all headers on page
* Small edit
Address findings from a code-bot adversarial review of the hybrid-search
materials:
- `hybrid-formula-decay/` (all 7 language sources + http.md +
`_description.md`): wrap the decay term in `MultExpression(mult=[0.1, ...])`
in every language. Previously the snippets summed `$score` with
`ExpDecayExpression` directly, modeling the failure mode the docs
explicitly warn against (un-weighted decay crowds out small RRF scores).
Also document the `defaults` requirement and the recommended datetime
payload index in `_description.md`. Build validated across all 6 SDKs.
- `hybrid-rrf/go.go`: add `Limit: qdrant.PtrOf(uint64(20))` to both
prefetches so the Go snippet matches the other language tabs.
- `hybrid-queries.md`:
- Reframe the weighted-RRF intro to drop "semantic search model
understands meaning better than a simple keyword matcher". On
SciFact (the corpus in the companion notebook) BM25 actually beats
dense, so the universal claim was contradicted by our own data.
- Clarify that the notebook provides a tuning helper to adapt to a
train/val split, not that it demonstrates the split itself.
- Add a one-line note that Qdrant uses zero-based rank positions so
readers can verify the RRF formula against actual scores.
- Apply brand-voice fixes: Title Case on "Multi-Stage Queries" and
"Re-Scoring Examples", replace "all the above techniques" with
"all of these techniques".
`generated/*.md` regenerated via `./docker.sh ./generate-md.py`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
Run `./generate-md.py` to update generated markdown files after
semi-manual changes made in the previous commit.
This commit serves as a gist of fixed issues found in snippets.
(it's easier to review 250 lines diff rather than 31k lines diff, isn't it?)
This commit both:
- Fixes pre-existing mistakes in snippets, aka wrong code samples.
- Adds hidden (`@hide`) statements that do not appear in the docs,
but satisfy typecheckers.
These changes are purely mechanical to differentiate them from manual
fixes/adjustments made in the next commit.
This results in broken code as some snippets contain errors.
Made in four steps:
1. Run ./migrate-snippet.py that converts `.md` files to code files
and perhaps adds missing lines under `// @hide` comments.
2. Sort Java imports.
3. Remove old `.md` files.
4. Run ./generate.md to produce `*/generated/*.md` files.
* Add score boosting section to hybrid queries
* add decay formulas docs
* Add datetime function to formula operators and update limitations
* add datetime_key expression
* use the name of the decay function in interface for the table
* update to use snippets in a dedicated folder
* mention that payload index is desired
* add python and rust snippets
* update snippets
* docs: Go snippets
Signed-off-by: Anush008 <anushshetty90@gmail.com>
* docs: C# snippets
Signed-off-by: Anush008 <anushshetty90@gmail.com>
* docs: Java snippets
Signed-off-by: Anush008 <anushshetty90@gmail.com>
* chore: Updated formula defaut C#, GO
Signed-off-by: Anush008 <anushshetty90@gmail.com>
* docs: Update C# snippets as per new changes
Signed-off-by: Anush008 <anushshetty90@gmail.com>
* add typescript snippets
* minor fixes
* Use score function in Rust client
---------
Signed-off-by: Anush008 <anushshetty90@gmail.com>
Co-authored-by: Anush008 <anushshetty90@gmail.com>
Co-authored-by: generall <andrey@vasnetsov.com>
Co-authored-by: timvisee <tim@visee.me>
* shortcode for rendering code snippets from separate markdown files
* formatted code
* fix and readme
* semi-automatically extracts snippets from markdown
* extract snippets from points.md
* extract snippets from vectors.md
* extract snippets from payload.md
* extract snippets from search.md + fixes
* extract snippets from explore.md
* extract snippets from hybrid-queries.md + mode query by id into search
* extract snippets from filtering.md
* extract snippets from storage.md + update outdated info
* extract snippets from indexing.md
* extract snippets from snapshots.md
* extract snippets from guides/optimize.md
* extract snippets from guides/multiple-partitions.md + fix aside note
* extract snippets from guides/quantization.md
* use auto-generated descriptions
* order json snippets first
---------
Co-authored-by: generall <andrey@vasnetsov.com>
István Zoltán Szabó