- Allowing for multiple types of Catalogs

- Introduction of retrievers
- Ensuring processing information is collected from Catalog iso Tenant
- Introduction of a generic Form class to enable dynamic fields based on a configuration
- Realisation of Retriever functionality to support dynamic fields
This commit is contained in:
Josako
2024-10-25 14:11:47 +02:00
parent 30fec27488
commit aa358df28e
19 changed files with 753 additions and 145 deletions

View File

@@ -8,8 +8,10 @@ import sqlalchemy as sa
class Catalog(db.Model):
id = db.Column(db.Integer, primary_key=True)
parent_id = db.Column(db.Integer, db.ForeignKey('catalog.id'), nullable=True)
name = db.Column(db.String(50), nullable=False)
description = db.Column(db.Text, nullable=True)
type = db.Column(db.String(50), nullable=False, default="DEFAULT_CATALOG")
# Embedding variables
html_tags = db.Column(ARRAY(sa.String(10)), nullable=True, default=['p', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'li'])
@@ -21,17 +23,36 @@ class Catalog(db.Model):
min_chunk_size = db.Column(db.Integer, nullable=True, default=2000)
max_chunk_size = db.Column(db.Integer, nullable=True, default=3000)
# Embedding search variables ==> move to specialist?
es_k = db.Column(db.Integer, nullable=True, default=8)
es_similarity_threshold = db.Column(db.Float, nullable=True, default=0.4)
# Chat variables ==> Move to Specialist?
chat_RAG_temperature = db.Column(db.Float, nullable=True, default=0.3)
chat_no_RAG_temperature = db.Column(db.Float, nullable=True, default=0.5)
# Tuning enablers
embed_tuning = db.Column(db.Boolean, nullable=True, default=False)
rag_tuning = db.Column(db.Boolean, nullable=True, default=False) # Move to Specialist?
# Meta Data
user_metadata = db.Column(JSONB, nullable=True)
system_metadata = db.Column(JSONB, nullable=True)
configuration = db.Column(JSONB, 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=True)
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))
class Retriever(db.Model):
id = db.Column(db.Integer, primary_key=True)
name = db.Column(db.String(50), nullable=False)
description = db.Column(db.Text, nullable=True)
catalog_id = db.Column(db.Integer, db.ForeignKey('catalog.id'), nullable=True)
type = db.Column(db.String(50), nullable=False, default="DEFAULT_RAG")
# Meta Data
user_metadata = db.Column(JSONB, nullable=True)
system_metadata = db.Column(JSONB, nullable=True)
configuration = db.Column(JSONB, nullable=True)
# Versioning Information
created_at = db.Column(db.DateTime, nullable=False, server_default=db.func.now())