pdf-quiz-generator

danvics/pdf-quiz-generator

Fork 0

Commit graph

Author	SHA1	Message	Date
Daniel	a1459b2965	refactor: name the study plans ourselves, and stop reserving 64k tokens a call "PREP" is the American Academy of Pediatrics' trademark for their own product. The plans here are our own sets of questions grouped by year, so they are now named for what they are: Board Review 2021, and Mixed Review for the plan that draws from every year at once. Renamed in the database as well as the code — 13 plans, 14 quizzes a learner had already generated from a block, and the 12 year tags, which appear in the question bank's filters and are as visible as the plans. The seeder matches both the old and new names so a fresh import still finds its material, and the tagger mints the new one so the next run cannot undo this. Prompts and comments that described the source PDFs by that name now describe them by what they are. The generation run's 377 failures were not a bug Every call was reserving the model's full 64k output ceiling, and OpenRouter refuses the whole request when the balance is below the reservation — "you requested up to 64000 tokens, but can only afford 52017" — however short the answer would actually be. `_call_model` now takes a max_tokens, and the article writer asks for 4000, which is comfortable for three views of one topic and keeps each request small enough to be affordable. 98 articles were written before the balance ran down; 158 exist in total. Generation is paused at the user's request while credits are topped up. 208 backend, 243 frontend green. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TqXevQJhxFrM7jJg82cgZN	2026-09-11 01:41:18 +02:00
Daniel	2cbbfe00c3	Tag filtering, multi-category, bug fixes, image validation, docs - Fix tag filtering (sa_text import shadowing caused UnboundLocalError) - Add TagBrowser component with per-section search - Multi-category selection (OR within categories, AND with tags) - AI image validation: has_figure field in extraction prompt - Skip known branding images by MD5 hash + dimension filters - Fix quiz timer auto-submit (wrong useEffect dependency) - Fix QuizResponse schema: section_id nullable - Fix Question.quiz_id → source_quiz_id attribute name - Fix SQL injection in quizzes.py vector search - Add PDF processing progress steps via Redis - Add delete user from admin panel - Admin page: no spinner flash on data refresh - Upload progress: axios 1.x e.progress, remove manual Content-Type - Duplicate model error: 409 with clear message - Backend startup: retry DDL migration on lock timeout - Replace all silent except:pass with warning logs - Comprehensive multi-page documentation (docs/) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-04 22:48:26 +02:00
ifedan-ed	b876f13fac	Initial commit: PDF Quiz Generator app - FastAPI backend with JWT auth, roles (admin/moderator/user) - PDF upload (up to 500MB) with streaming, PyMuPDF text extraction - ChromaDB vectorization per page with metadata - LiteLLM AI question extraction from PDF (not generation) - Image extraction from PDF pages, graceful fallback - Quiz modes: timed (countdown timer) + learning (answers shown inline) - Page-by-page question navigation with dot navigator - TTS endpoint using LiteLLM (Google Vertex / OpenAI voices) - Admin dashboard: AI model management per task, user role management - Moderator role: upload PDFs, create sections, generate quizzes - Spaced repetition reminders via SMTP email (SM-2 intervals) - APScheduler daily reminder jobs - Celery + Redis for background PDF processing - React frontend with all pages - Docker Compose deployment (nginx + backend + celery + redis) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-03-30 20:04:53 +00:00

Author

SHA1

Message

Date

Daniel

a1459b2965

refactor: name the study plans ourselves, and stop reserving 64k tokens a call

"PREP" is the American Academy of Pediatrics' trademark for their own product.
The plans here are our own sets of questions grouped by year, so they are now
named for what they are: Board Review 2021, and Mixed Review for the plan that
draws from every year at once.

Renamed in the database as well as the code — 13 plans, 14 quizzes a learner had
already generated from a block, and the 12 year tags, which appear in the
question bank's filters and are as visible as the plans. The seeder matches both
the old and new names so a fresh import still finds its material, and the tagger
mints the new one so the next run cannot undo this. Prompts and comments that
described the source PDFs by that name now describe them by what they are.

The generation run's 377 failures were not a bug
Every call was reserving the model's full 64k output ceiling, and OpenRouter
refuses the whole request when the balance is below the reservation — "you
requested up to 64000 tokens, but can only afford 52017" — however short the
answer would actually be. `_call_model` now takes a max_tokens, and the article
writer asks for 4000, which is comfortable for three views of one topic and
keeps each request small enough to be affordable. 98 articles were written
before the balance ran down; 158 exist in total.

Generation is paused at the user's request while credits are topped up.

208 backend, 243 frontend green.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TqXevQJhxFrM7jJg82cgZN

2026-09-11 01:41:18 +02:00

Daniel

2cbbfe00c3

Tag filtering, multi-category, bug fixes, image validation, docs

- Fix tag filtering (sa_text import shadowing caused UnboundLocalError)
- Add TagBrowser component with per-section search
- Multi-category selection (OR within categories, AND with tags)
- AI image validation: has_figure field in extraction prompt
- Skip known branding images by MD5 hash + dimension filters
- Fix quiz timer auto-submit (wrong useEffect dependency)
- Fix QuizResponse schema: section_id nullable
- Fix Question.quiz_id → source_quiz_id attribute name
- Fix SQL injection in quizzes.py vector search
- Add PDF processing progress steps via Redis
- Add delete user from admin panel
- Admin page: no spinner flash on data refresh
- Upload progress: axios 1.x e.progress, remove manual Content-Type
- Duplicate model error: 409 with clear message
- Backend startup: retry DDL migration on lock timeout
- Replace all silent except:pass with warning logs
- Comprehensive multi-page documentation (docs/)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-04 22:48:26 +02:00

ifedan-ed

b876f13fac

Initial commit: PDF Quiz Generator app

- FastAPI backend with JWT auth, roles (admin/moderator/user)
- PDF upload (up to 500MB) with streaming, PyMuPDF text extraction
- ChromaDB vectorization per page with metadata
- LiteLLM AI question extraction from PDF (not generation)
- Image extraction from PDF pages, graceful fallback
- Quiz modes: timed (countdown timer) + learning (answers shown inline)
- Page-by-page question navigation with dot navigator
- TTS endpoint using LiteLLM (Google Vertex / OpenAI voices)
- Admin dashboard: AI model management per task, user role management
- Moderator role: upload PDFs, create sections, generate quizzes
- Spaced repetition reminders via SMTP email (SM-2 intervals)
- APScheduler daily reminder jobs
- Celery + Redis for background PDF processing
- React frontend with all pages
- Docker Compose deployment (nginx + backend + celery + redis)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-03-30 20:04:53 +00:00

3 commits