Initial commit for deployment

app/models/document.py

@@ -0,0 +1,59 @@
+"""
+Document models for the application.
+"""
+
+from datetime import datetime
+import json
+from app.database.db import db
+
+class Document(db.Model):
+    """Document model representing a document in the library."""
+
+    __tablename__ = 'documents'
+
+    id = db.Column(db.Integer, primary_key=True)
+    title = db.Column(db.String(255), nullable=False)
+    description = db.Column(db.Text, nullable=True)
+    file_path = db.Column(db.String(255), nullable=True)
+    content_type = db.Column(db.String(50), nullable=False)
+    status = db.Column(db.String(20), default='pending')  # pending, processing, completed, error
+    created_at = db.Column(db.DateTime, default=datetime.utcnow)
+    updated_at = db.Column(db.DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+
+    # Foreign keys
+    uploaded_by = db.Column(db.Integer, db.ForeignKey('users.id'), nullable=False)
+
+    # Relationships
+    chunks = db.relationship('DocumentChunk', backref='document', lazy='dynamic', cascade='all, delete-orphan')
+
+    def __repr__(self):
+        return f'<Document {self.id}: {self.title}>'
+
+
+class DocumentChunk(db.Model):
+    """Model representing a chunk of a document for embedding."""
+
+    __tablename__ = 'document_chunks'
+
+    id = db.Column(db.Integer, primary_key=True)
+    content = db.Column(db.Text, nullable=False)
+    chunk_index = db.Column(db.Integer, nullable=False)
+    embedding_id = db.Column(db.String(100), nullable=True)  # ID in Pinecone
+    meta_data = db.Column(db.Text, nullable=True)  # JSON string of metadata
+    created_at = db.Column(db.DateTime, default=datetime.utcnow)
+
+    # Foreign keys
+    document_id = db.Column(db.Integer, db.ForeignKey('documents.id'), nullable=False)
+
+    def set_metadata(self, metadata_dict):
+        """Set metadata as JSON string."""
+        self.meta_data = json.dumps(metadata_dict)
+
+    def get_metadata(self):
+        """Get metadata as dictionary."""
+        if self.meta_data:
+            return json.loads(self.meta_data)
+        return {}
+
+    def __repr__(self):
+        return f'<DocumentChunk {self.id}: doc_id={self.document_id}, index={self.chunk_index}>'