Recipe 06: Multiple topic labels #6

Recipe 06 of 60 · Level 1 (Beginner) · Language & content · Noul

Use case

Tag customer feedback with every applicable topic by asking an independent yes-or-no question for each predefined label.

What to build

The folder recipes/06-multiple-topic-labels/ with notebook.ipynb, README.md, and fixtures/, meeting the recipe contract. Start from python tools/new_recipe.py 06 and the template in recipes/_template/.

Build notes

• One independent Noul per predefined topic label, all sent in a single request.
• Fixtures need multi-label gold sets, including items with no label and items with three or more.
• Explain why this is not one Choice: labels are not mutually exclusive.
• Python applies a per-label threshold and assembles the tag set.

Decision design

• Noul. Write each proposition as a statement that is true or false. One independent question per label or concern, sent together in one request. Noul has no confidence field, so each threshold is chosen from examples and evaluated.

Level 1 scope

One bounded judgment over a short prepared input with direct inspection of typed results.

Acceptance criteria

• recipes/06-multiple-topic-labels/notebook.ipynb runs top to bottom offline, with no key and no network, and its outputs are committed
• Live mode is opt-in (JEV_COOKBOOK_LIVE=1 with TYPESAFE_API_KEY) and uses the same question definitions as the offline run
• Fixtures are synthetic, include the hard cases named in the build notes, carry gold labels, and pass the fixture validator
• Every response fixture records its provenance, and the notebook states which mode it ran in
• Evaluation: Per-label precision and recall, micro and macro F1, and exact-set match.
• A reader with basic Python can follow it end to end; every new term is explained where it first appears
• At least three individual typed answers are displayed and discussed before any aggregate metric
• No statement about Jev's quality, latency, or cost appears without recorded live inference; in a synthetic run, metrics are labelled as pipeline checks
• recipes/06-multiple-topic-labels/README.md says what the recipe teaches, how to run it, and what was and was not measured live
• The pull request changes only recipes/06-multiple-topic-labels/ and CI is green

Dependencies

• Blocked by Foundation: CI executes every notebook offline and validates fixtures #69 (CI executes every notebook offline and validates fixtures)
• Tracked in Epic: Level 1 · Beginner recipes #75

Sources

Read these before writing the questions.

• S02 · TypeSafe AI: Primitives (Questions): Choice, Noul, Score, independent questions, and dependent follow-up calls.
• S03 · TypeSafe AI: Confidence: Distribution-derived confidence and task-specific thresholds informed by observed outcomes.
• S07 · TypeSafe AI: Jev 1.13 jaggedness: Version-specific limitations affecting arithmetic, context selection, adversarial content, and generation.

Out of scope

• Changes to shared code, the catalog, or the root README. If the shared package is missing something, open a foundation issue and link it here.
• Real side effects of any kind. Actions are simulated.