app/models/document.py

"""Document model for pgvector-based knowledge base."""

from datetime import datetime
from sqlalchemy import Column, String, Text, DateTime, Integer, JSON
from pgvector.sqlalchemy import Vector
from uuid import uuid4
from app.database import Base


class Document(Base):
    """Vector store for course materials and knowledge base."""
    __tablename__ = "documents"

    id = Column(String(36), primary_key=True, default=lambda: str(uuid4()))
    content = Column(Text, nullable=False)
    embedding = Column(Vector(768), nullable=False)  # Google text-embedding-004 dimension
    meta = Column(JSON, nullable=True)  # Store lesson_id, module_id, source, etc.
    
    # File metadata
    filename = Column(String(500), nullable=True)
    file_path = Column(String(1000), nullable=True)
    chunk_index = Column(Integer, default=0)
    
    # Timestamps
    created_at = Column(DateTime, default=datetime.utcnow)
    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)

    def __repr__(self):
        return f"<Document {self.id[:8]}... from {self.filename}>"