Expands MRR with Mean Reciprocal Rank and a Wikipedia link where the
metric becomes operational, matching the inline expansion treatment
already given to NDCG. Drops the IR acronym in favor of the plainer
"ranking metrics" phrasing. Strips the parenthetical subtitle from the
Pitfalls heading and normalizes the intro to use "golden sets".
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Aligns the layer-2 tutorial title with the parallel "Measuring X" /
"Evaluating X" pattern used by the other two and maps directly to the
four-layer framework. Slug stays the same to preserve URLs and the
golden-set artifact identity in the path. Also updates the nav descriptions
to reflect the tutorial's full scope (build + score, not just build).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Replaces the external pointer to retrieval-quality-fundamentals with an
inline scenario-to-metric table plus guidance on picking k. The ladder
pointer now references the four-layer section inside ANN Precision rather
than the fundamentals page.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- 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
- Switch the metrics section from three hand-rolled functions
(recall@k, MRR, NDCG@k) and a bespoke evaluate() loop to a
single ranx-based example. Handles binary and graded labels
in one call (mrscoopers, line 59).
- Reframe the Anthropic synthetic-generation snippet as a
minimal prompt shape, point at Ragas for readers who want a
maintained testset generator, and fix a bug (Anthropic() was
called without importing the class; switched to
anthropic.Anthropic()). Addresses abdonpijpelink line 53 and
mrscoopers line 31.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Open the tutorial by anchoring it at layer 2 of the evaluation
ladder and linking to the levels table in retrieval-quality-
fundamentals (abdonpijpelink, line 14).
- Point layer-1 readers (ANN recall vs exact kNN) at the Search
Quality tab in the Qdrant Web UI instead of the retrieval-quality
tutorial (mrscoopers, line 13).
- Trim the duplicate layer-1 pointer at the end of "Using the
Golden Set" (mrscoopers, line 113).
- Open cross-tutorial links in a new tab to match the repo
convention.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Introduces two new conceptual tutorials under tutorials-search-engineering:
- Retrieval Quality Fundamentals covers the three-level evaluation
framework (ANN recall, retrieval relevance, business impact), the
evaluation ladder that connects them in practice, and a which-metric-
when decision table keyed by scenario and available ground truth.
- Building a Golden Query Set covers query generation at scale (logs,
LLM synthesis, human annotation) and the failure modes commonly
lumped together as data leakage: synthetic-query unrealism,
embedding-model contamination, near-duplicate documents, temporal
drift, and reviewer reproducibility.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Dylan Couzon