Removing DocumentLanguage, as both System Context and User Context are to be defined on DocumentVersion level.

Finetuning of embedding workers.
This commit is contained in:
Josako
2024-06-06 15:26:49 +02:00
parent 1a25313673
commit 27b6de8734
21 changed files with 301 additions and 295 deletions

View File

@@ -17,50 +17,22 @@ class Document(db.Model):
updated_by = db.Column(db.Integer, db.ForeignKey(User.id))
# Relations
languages = db.relationship('DocumentLanguage', backref='document', lazy=True)
versions = db.relationship('DocumentVersion', 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)
document_id = db.Column(db.Integer, db.ForeignKey(Document.id), nullable=False)
language = db.Column(db.String(2), nullable=False)
user_context = db.Column(db.Text, nullable=True)
system_context = db.Column(db.Text, nullable=True)
latest_version_id = db.Column(db.Integer, db.ForeignKey('document_version.id'), 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), 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='joined',
foreign_keys='DocumentVersion.doc_lang_id'
)
latest_version = db.relationship(
'DocumentVersion',
uselist=False,
foreign_keys=[latest_version_id]
)
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)
doc_id = db.Column(db.Integer, db.ForeignKey(Document.id), nullable=False)
url = db.Column(db.String(200), 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)
language = db.Column(db.String(2), nullable=False)
user_context = db.Column(db.Text, nullable=True)
system_context = db.Column(db.Text, nullable=True)
# Versioning Information
created_at = db.Column(db.DateTime, nullable=False, server_default=db.func.now())
@@ -81,7 +53,7 @@ class DocumentVersion(db.Model):
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}"
return f"{self.document.tenant_id}/{self.document.id}/{self.language}"
def calc_file_name(self):
return f"{self.id}.{self.file_type}"

View File

@@ -48,6 +48,10 @@ class Tenant(db.Model):
allowed_monthly_interactions = db.Column(db.Integer, nullable=True)
encrypted_chat_api_key = db.Column(db.String(500), nullable=True)
# Tuning enablers
embed_tuning = db.Column(db.Boolean, nullable=True, default=False)
rag_tuning = db.Column(db.Boolean, nullable=True, default=False)
# Relations
users = db.relationship('User', backref='tenant')
domains = db.relationship('TenantDomain', backref='tenant')
@@ -133,7 +137,10 @@ class TenantDomain(db.Model):
id = db.Column(db.Integer, primary_key=True)
tenant_id = db.Column(db.Integer, db.ForeignKey('public.tenant.id'), nullable=False)
domain = db.Column(db.String(255), unique=True, nullable=False)
# Originally, domain was required to be unique.
# However, several tenants can run from the same domain (e.g. for demo purposes,
# but also internal and external chat clients.
domain = db.Column(db.String(255), nullable=False)
valid_to = db.Column(db.Date, nullable=True)
# Versioning Information