Update Document domain models to use pgvector (extension of PostgreSQL)

This commit is contained in:
Josako
2024-04-30 15:09:32 +02:00
parent 8e069cc653
commit ffa60b4616
5 changed files with 46 additions and 2 deletions

View File

@@ -1,5 +1,6 @@
from ..extensions import db
from .user import User, Tenant
from pgvector.sqlalchemy import Vector
class Document(db.Model):
@@ -15,6 +16,12 @@ class Document(db.Model):
updated_at = db.Column(db.DateTime, nullable=False, server_default=db.func.now(), onupdate=db.func.now())
updated_by = db.Column(db.Integer, db.ForeignKey(User.id))
# Relations
languages = db.relationship('DocumentLanguage', backref='document', lazy=True)
def __repr__(self):
return f"<Document {self.id}: {self.name}>"
class DocumentLanguage(db.Model):
id = db.Column(db.Integer, primary_key=True)
@@ -24,15 +31,48 @@ class DocumentLanguage(db.Model):
# Versioning Information
created_at = db.Column(db.DateTime, nullable=False, server_default=db.func.now())
created_by = db.Column(db.Integer, db.ForeignKey(User.id), nullable=False)
updated_at = db.Column(db.DateTime, nullable=False, server_default=db.func.now(), onupdate=db.func.now())
updated_by = db.Column(db.Integer, db.ForeignKey(User.id))
# Relations
versions = db.relationship('DocumentVersion', backref='document_language', lazy=True)
def __repr__(self):
return f"<DocumentLanguage {self.document_id}.{self.language}>"
class DocumentVersion(db.Model):
id = db.Column(db.Integer, primary_key=True)
doc_lang_id = db.Column(db.Integer, db.ForeignKey(DocumentLanguage.id), nullable=False)
url = db.Column(db.String(200), nullable=True)
embeddings = db.Column(db.PickleType, nullable=True)
file_location = db.Column(db.String(255), nullable=True)
file_name = db.Column(db.String(200), nullable=True)
file_type = db.Column(db.String(20), nullable=True)
# Versioning Information
created_at = db.Column(db.DateTime, nullable=False, server_default=db.func.now())
created_by = db.Column(db.Integer, db.ForeignKey(User.id))
updated_at = db.Column(db.DateTime, nullable=False, server_default=db.func.now(), onupdate=db.func.now())
updated_by = db.Column(db.Integer, db.ForeignKey(User.id))
# Relations
embeddings = db.relationship('EmbeddingMistral', backref='document_version', lazy=True)
def __repr__(self):
return f"<DocumentVersion {self.document_language.document_id}.{self.document_language.language}>.{self.id}>"
def calc_file_location(self):
return f"{self.document_language.document.tenant.id}/{self.document_language.document.id}/{self.document_language.language}"
def calc_file_name(self):
return f"{self.id}.{self.file_type}"
class EmbeddingMistral(db.Model):
id = db.Column(db.Integer, primary_key=True)
doc_vers_id = db.Column(db.Integer, db.ForeignKey(DocumentVersion.id), nullable=False)
active = db.Column(db.Boolean, nullable=False, default=True)
# 1024 is the MISTRAL Embedding dimension.
# If another embedding model is chosen, this dimension may need to be changed.
embedding = db.Column(Vector(1024), nullable=False)

View File

View File

View File

@@ -8,6 +8,9 @@ from sqlalchemy import NullPool, engine_from_config, text
from eveai_app.models.user import Tenant
import pgvector
from pgvector.sqlalchemy import Vector
# this is the Alembic Config object, which provides
# access to the values within the .ini file in use.

View File

@@ -3,3 +3,4 @@ WTForms~=3.1.2
SQLAlchemy~=2.0.29
alembic~=1.13.1
Werkzeug~=3.0.2
pgvector~=0.2.5