b876f13fac
- 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>
53 lines
1.6 KiB
Python
53 lines
1.6 KiB
Python
import logging
|
|
|
|
from app.tasks import celery_app
|
|
from app.database import SessionLocal
|
|
from app.models.pdf_document import PDFDocument
|
|
from app.services import pdf_service, vector_service
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
@celery_app.task(name="process_pdf")
|
|
def process_pdf(document_id: int, file_path: str):
|
|
"""Background task: extract PDF text and store in ChromaDB."""
|
|
db = SessionLocal()
|
|
try:
|
|
doc = db.query(PDFDocument).filter(PDFDocument.id == document_id).first()
|
|
if not doc:
|
|
logger.error(f"Document {document_id} not found")
|
|
return
|
|
|
|
# Get page count
|
|
total_pages = pdf_service.get_page_count(file_path)
|
|
doc.total_pages = total_pages
|
|
db.commit()
|
|
|
|
# Extract text from all pages
|
|
pages = pdf_service.extract_text_by_page(file_path)
|
|
if not pages:
|
|
doc.status = "error"
|
|
doc.error_message = "No text could be extracted from the PDF"
|
|
db.commit()
|
|
return
|
|
|
|
# Store in ChromaDB
|
|
vector_service.store_pages(document_id, pages)
|
|
|
|
# Mark as ready
|
|
doc.status = "ready"
|
|
db.commit()
|
|
logger.info(f"Document {document_id} processed: {total_pages} pages, {len(pages)} with text")
|
|
|
|
except Exception as e:
|
|
logger.exception(f"Error processing document {document_id}")
|
|
try:
|
|
doc = db.query(PDFDocument).filter(PDFDocument.id == document_id).first()
|
|
if doc:
|
|
doc.status = "error"
|
|
doc.error_message = str(e)[:500]
|
|
db.commit()
|
|
except Exception:
|
|
pass
|
|
finally:
|
|
db.close()
|