- Add "why measure retrieval quality" lead-in paragraph
- Expand ANN on first use; flag sparse vectors as out of scope
for layer 1 (they use exact matching)
- Add LLM-as-judge to layer-2 ground-truth options
- Break the Tooling bullet into per-layer recommendations: Web UI
for L1, ranx for L2, Ragas/Phoenix/DeepEval for L3
- Reorder Quality Metrics so layer 1 (ANN recall formula + exact
kNN equivalence) comes before the generic layer-2 relevance
metrics; trim a redundant sentence
- Add end-to-end answer quality as a distinct third layer in the
prose intro so it matches the ladder table's four rows
- Standardize vocabulary on "layer" (was mixing "level" in the
intro with "layer" everywhere else); update the section anchor
to #connecting-the-layers-in-practice in this file and the two
cross-linking tutorials
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Update title, H1, and Time in retrieval-quality.md
(30 min -> 15 min reflects the pivot to Web UI)
- Rename references in tutorials-lp-overview.md and the headless
tutorial index; swap the pill from Python to Web UI to reflect
the new primary flow
- Replace "ANN recall" with "ANN precision" in Fundamentals
(4 places: intro, comparison note, ladder table, cross-link)
and in the golden-set tutorial's layer-1 cross-reference
- Filename kept as retrieval-quality.md so existing URLs and
aliases still work
The Search Quality tab in the Web UI reports precision@k, not
recall@k, so the whole tutorial now uses precision@k as the metric
label: "ANN recall" -> "ANN precision" in the anchor, section
headers, Python helper (avg_precision_at_k), and prose. Kept a
one-line bridge note that ANN-benchmarks terminology calls this
recall@k, since both searches return exactly k items.
- Drop the dataset-setup walkthrough (HF loading, collection
create, upload, wait-for-green). Readers at this phase already
have a collection.
- Replace the Python evaluation block with a "Measure ANN Recall
with the Web UI" section built around the Search Quality tab.
Default run is one-click (sample size 10); HNSW tuning uses the
tab's advanced mode instead of update_collection. Three
screenshot placeholders at
/documentation/tutorials/retrieval-quality/*.png.
- Reflect that the tab reports precision@k; note the recall@k
equivalence already spelled out in the ANN Recall section.
- Keep Python but move it to an "Automate in CI" section with a
reusable skeleton function.
- Collapse the standalone "Embeddings Quality" section into a
one-sentence MTEB pointer inside ANN Recall.
- Rewrite Wrapping Up to match the new scope.
- Link the HNSW tuning section to Optimize Performance for the
full parameter reference.
- Rewrite the intro so the ANN algorithm reads as one of several
levers shaping retrieval quality (alongside the embedding model,
retrieval strategy, filtering, reranking) rather than the only
factor beyond embeddings. Addresses mrscoopers on the reductive
"embeddings + ANN" framing.
- Rename the "Retrieval Quality" section to "ANN Recall" and
rewrite its opening paragraph to match; ANN approximation quality
isn't the same as retrieval quality broadly.
- Drop the RAG-evaluation-guide link from the three places it
appeared in this file. This tutorial isn't RAG-specific.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add a layer-1 anchor sentence under the Time/Level table
pointing at the evaluation ladder in Fundamentals, mirroring
the golden-set tutorial's anchor. Addresses abdonpijpelink's
ask for a levels-table link and a "this tutorial focuses on
level 1" framing.
- Title-case the six H2 headers for consistency across the
tutorials-search-engineering set.
Deferred: streaming the 60K training items into upload_points
instead of materializing as a list (abdonpijpelink line 69) —
pending manager confirmation before proceeding.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Renames precision to recall throughout the ANN-evaluation tutorial so
the page aligns with the ANN-benchmarks convention and with the new
Retrieval Quality Fundamentals page. The numerical formula is
unchanged: when ANN and exact search both return exactly k items,
recall@k and precision@k are numerically identical.
Other changes:
- Remove the Quality metrics subsection, now covered by the
Fundamentals page, and replace it with a short link across.
- Bump weight from 4 to 6 so the three retrieval-quality pages
order as Fundamentals, Golden Query Set, Evaluation.
- Fix a pre-existing prose/code mismatch: the prose said "first
50000 items" while the code uses range(60000).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* initial commit; fixed anchor links on internal docs pages
* add back in absolute paths for links in code comments
* fix: update linkchecker include filter to match server port 1314
PR #1629 changed the Hugo server to port 1314 but forgot to update
the --include filter, which still matched port 1313. This caused all
links to be excluded, making the checker a no-op (0 checked, 82277 excluded).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Fix url rewrite regex so images are not impacted
* Fix links from non-documentation pages
* Fix broken links
* more broken links
* more broken links
* broken link
* Add srcset width descriptor to .lycheeignore
* Ignore URLs that contain a % character
* Anchor regex so it matches the entire URL
---------
Co-authored-by: kanungle <neil.kanungo@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Abdon Pijpelink <abdon.pijpelink@qdrant.com>
Dylan Couzon