docs: correct Reading Journey & Book System in the beta README
Evidence: spikersoft-backend@master SpikerSoft.EventHandlers.UploadCoordinator/Services/UploadOrchestrator.cs:134 a clean security scan runs before metadata extraction. Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
1 parent
e3796db009
commit
1b5953b11f
1 file changed
+11
-10
@@ -2243,19 +2243,20 @@ Key files: `SpikerSoft.Api/Domain/Photography/PhotographyController.cs`, `Spiker
|
||||
|
||||
## Reading Journey & Book System
|
||||
|
||||
The Reading Journey is the platform's digital library and learning hub. Members upload books (PDF or EPUB), which pass through an AI-powered processing pipeline that generates metadata, embeddings, and comprehension quizzes. The reader supports bookmarks, progress tracking, and multiple reading profiles.
|
||||
The Reading Journey is the platform's digital library and learning hub. Members upload books (PDF or EPUB), which pass through an AI-powered processing pipeline that generates metadata, embeddings, and comprehension quizzes. The reader supports bookmarks, progress tracking, and font, theme, and layout preferences.
|
||||
|
||||
### Book Processing Pipeline
|
||||
|
||||
```
|
||||
User uploads PDF/EPUB → Staff approval queue
|
||||
User uploads PDF or EPUB
|
||||
↓
|
||||
Staff approves → Processing pipeline begins
|
||||
Reading Journey uploads start processing immediately. Other uploads wait for staff approval.
|
||||
↓
|
||||
┌──── MetadataExtractor → Extract title, author, page count, TOC
|
||||
├──── Embeddings → Chunk text, generate vector embeddings (LLamaSharp)
|
||||
├──── QuizGeneration → LLM-powered comprehension quizzes per chapter
|
||||
└──── SecurityScanner → Content safety check
|
||||
Security scan → metadata extraction (title, author, page count, and page text)
|
||||
↓
|
||||
Book record and file storage
|
||||
↓
|
||||
Image descriptions, when the book has images → embeddings (LLamaSharp) → quiz questions per page
|
||||
↓
|
||||
SignalR notifications update the user in real time (BookProcessingStage)
|
||||
↓
|
||||
@@ -2269,9 +2270,9 @@ Book available in library
|
||||
- **Progress tracking** — Automatic page + scroll position saving per book
|
||||
- **Bookmarks** — Save and annotate specific locations
|
||||
- **Reading preferences** — Font size, theme, layout customization
|
||||
- **Reading profiles** — Multiple reading profiles per user (e.g., "Study", "Leisure")
|
||||
- **Reading profiles** — Named profiles are stored at `/api/reader/profiles`
|
||||
- **Recently read** — Quick access to books in progress
|
||||
- **Quizzes** — AI-generated comprehension quizzes tied to book chapters
|
||||
- **Quizzes** — AI-generated comprehension questions, written per page and tagged with the chapter
|
||||
|
||||
### API Endpoints
|
||||
|
||||
@@ -2305,7 +2306,7 @@ Book available in library
|
||||
|
||||
### Semantic search & vector indexes
|
||||
|
||||
`api/books/search` (GET + POST + stats, `BookSearchController`) runs semantic search over the embeddings the pipeline generates, and `api/vector-indexes` (`VectorIndexController`) gives staff CRUD/inspection over the Redis vector indexes backing it.
|
||||
`api/books/search` (GET + POST + stats, `BookSearchController`) runs semantic search over the embeddings the pipeline generates, and `api/vector-indexes` (`VectorIndexController`) gives Admin CRUD/inspection over the Redis vector indexes backing it.
|
||||
|
||||
### Configurable quiz generation
|
||||
|
||||
|
||||
Reference in new issue
Block a user