pdf-quiz-generator/docs
Daniel 3f57bda6aa feat: a reading voice in Settings, and a tutor that reads every figure
The voice picker was a dropdown in the quiz player, beside the question — the
one control on that screen with nothing to do with answering it, and one a
learner sets once and never touches. It is a setting now, on the user rather
than in a Redis blob, with a play button beside each voice because a voice is
worth hearing before it is chosen. Choosing nothing stays a real choice: it
means whatever an administrator marked default, so a site that changes its
default reaches everybody without a row being edited.

The tutor reads figures from `question_media` rather than the two legacy path
columns. Those agree exactly today, so nothing was being lost — the first
question given a second figure in the editor would have been the one that
broke it, silently and only for the tutor. The legacy columns remain as a
fallback for anything not projected into that table yet.

And the retrieval thresholds are written down in docs/retrieval-thresholds.md:
the three answers, the sixteen queries they were measured against, why they are
deliberately not the retrieval floor, and how to re-measure when the corpus
grows. Worth keeping the headline in mind — "discuss love" scores 0.491,
alongside "tell me a joke". A number in the 0.4s is noise, not a weak signal.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TqXevQJhxFrM7jJg82cgZN
2026-09-12 16:48:09 +02:00
..
quiz-revamp feat: authorize tutor context and protect uploaded media 2026-09-07 15:04:00 +02:00
adaptive-sessions.md feat: a session prepared for you, and a model that can see when the one on the job cannot 2026-09-12 15:46:04 +02:00
api-reference.md feat: Cap replaces hCaptcha, self-hosted beside the app 2026-09-12 06:14:14 +02:00
architecture.md feat: Cap replaces hCaptcha, self-hosted beside the app 2026-09-12 06:14:14 +02:00
deployment.md feat: Cap replaces hCaptcha, self-hosted beside the app 2026-09-12 06:14:14 +02:00
frontend.md feat: Cap replaces hCaptcha, self-hosted beside the app 2026-09-12 06:14:14 +02:00
migrations.md fix: gateway-agnostic URL handling for TTS and embeddings, docs cleanup 2026-04-19 02:17:35 +02:00
quiz-revamp-plan.md docs: sync backlog with what shipped today 2026-09-09 20:11:20 +02:00
quiz-revamp-progress.md feat: Cap replaces hCaptcha, self-hosted beside the app 2026-09-12 06:14:14 +02:00
README.md feat: a solid highlight, a five-minute warning, and the adaptive algorithm 2026-09-12 05:47:30 +02:00
retrieval-thresholds.md feat: a reading voice in Settings, and a tutor that reads every figure 2026-09-12 16:48:09 +02:00
services.md Improve quiz TTS and Android release build 2026-05-12 01:01:01 +02:00
study-recommendations.md fix: leaving and resuming take one press; session actions sit with the result 2026-09-11 23:03:09 +02:00
tied-conditions.md chore: merge the 99 duplicated conditions that had a clear home 2026-09-11 13:37:35 +02:00
TODO.md feat: thumbnails for uploaded images, at two widths and no others 2026-09-12 08:49:20 +02:00

PedsHub Documentation

Deep technical documentation for the PedsHub pediatric learning platform.

Pages

Document Description
Architecture System overview, database schema, multi-worker setup, vector search, auth, rate limiting, concurrent quiz protection
API Reference Every endpoint: method, path, auth, request/response, notes
Services Backend service layer: AI extraction, embedding, vector search, PDF processing, email, reminders
Frontend React app structure, pages, components, state patterns, runtime config
Deployment Docker setup, environment variables, HTTPS, rebuilding, monitoring, troubleshooting, scaling
Adaptive sessions What the Adaptive toggle selects, where the code is, and what it deliberately ignores
Study recommendations How focus areas are ranked and what readiness means