
LecteurAide
Updated Nov 2025
PythonFastAPIVertex AI GeminiCloud TranslationNext.js
LecteurAide is a French reading companion for long-form PDFs. It ingests a book, segments it into scenes, translates sentences, extracts vocabulary, and generates comprehension questions before presenting everything in a purpose-built reading interface.
Six-stage pipeline: PDF extraction, heading stripping, sentence segmentation, Cloud Translation, chunking, and Gemini annotation
Context-aware scene segmentation that passes previous scene summaries to maintain narrative coherence across chunks
SSE-streaming upload progress, keyboard-navigable scene reader, and click-to-jump vocabulary highlighting
What I built
- FastAPI backend for book upload, scene segmentation, translation, vocabulary extraction, and persistence
- Next.js frontend for upload, library browsing, and scene-by-scene reading
- Vertex AI and Google Cloud Translation pipeline for turning raw PDFs into guided reading experiences
How it works
- 1Upload a French PDF and title via the ingestion API
- 2Segment the text into scenes and annotate it with translations, vocab, and questions
- 3Persist the processed book and render it through the web reader
Results
- ✓Turns static PDFs into an interactive reading workflow
- ✓Combines document ingestion, translation, and reader UX in one end-to-end product
Next steps
- Add screenshots and a richer sample book walkthrough
- Expand the reader with stronger review and spaced-repetition loops